RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 02:52:53 +02:00
Code Issues Projects Releases Wiki Activity
dad288658b
llvm-mirror/lib/Target/AArch64/AArch64ISelLowering.h

762 lines
28 KiB
C
Raw Normal View History

AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 14:50:23 +02:00
//==-- AArch64ISelLowering.h - AArch64 DAG Lowering Interface ----*- C++ -*-==//
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
//
Update the file headers across all of the LLVM projects in the monorepo to reflect the new license. We understand that people may be surprised that we're moving the header entirely to discuss the new license. We checked this carefully with the Foundation's lawyer and we believe this is the correct approach. Essentially, all code in the project is now made available by the LLVM project under our new license, so you will see that the license headers include that license only. Some of our contributors have contributed code under our old license, and accordingly, we have retained a copy of our old license notice in the top-level files in each project and repository. llvm-svn: 351636
2019-01-19 09:50:56 +01:00
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
//
//===----------------------------------------------------------------------===//
//
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 14:50:23 +02:00
// This file defines the interfaces that AArch64 uses to lower LLVM code into a
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
// selection DAG.
//
//===----------------------------------------------------------------------===//
Canonicalize header guards into a common format. Add header guards to files that were missing guards. Remove #endif comments as they don't seem common in LLVM (we can easily add them back if we decide they're useful) Changes made by clang-tidy with minor tweaks. llvm-svn: 215558
2014-08-13 18:26:38 +02:00
#ifndef LLVM_LIB_TARGET_AARCH64_AARCH64ISELLOWERING_H
#define LLVM_LIB_TARGET_AARCH64_AARCH64ISELLOWERING_H
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[WinEH] Update exception pointer registers Summary: The CLR's personality routine passes these in rdx/edx, not rax/eax. Make getExceptionPointerRegister a virtual method parameterized by personality function to allow making this distinction. Similarly make getExceptionSelectorRegister a virtual method parameterized by personality function, for symmetry. Reviewers: pgavlin, majnemer, rnk Subscribers: jyknight, dsanders, llvm-commits Differential Revision: http://reviews.llvm.org/D14344 llvm-svn: 252383
2015-11-07 02:11:31 +01:00
#include "AArch64.h"
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
#include "llvm/CodeGen/CallingConvLower.h"
#include "llvm/CodeGen/SelectionDAG.h"
Fix a bunch more layering of CodeGen headers that are in Target All these headers already depend on CodeGen headers so moving them into CodeGen fixes the layering (since CodeGen depends on Target, not the other way around). llvm-svn: 318490
2017-11-17 02:07:10 +01:00
#include "llvm/CodeGen/TargetLowering.h"
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
#include "llvm/IR/CallingConv.h"
Prevent hoisting fmul from THEN/ELSE to IF if there is fmsub/fmadd opportunity. This patch adds the isProfitableToHoist API. For AArch64, we want to prevent a fmul from being hoisted in cases where it is more profitable to form a fmsub/fmadd. Phabricator Review: http://reviews.llvm.org/D7299 Patch by Lawrence Hu <lawrence@codeaurora.org> llvm-svn: 230241
2015-02-23 20:15:16 +01:00
#include "llvm/IR/Instruction.h"
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
namespace llvm {
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 14:50:23 +02:00
namespace AArch64ISD {
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
Change getTargetNodeName() to produce compiler warnings for missing cases, fix them llvm-svn: 236775
2015-05-07 23:33:59 +02:00
enum NodeType : unsigned {
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
FIRST_NUMBER = ISD::BUILTIN_OP_END,
WrapperLarge, // 4-instruction MOVZ/MOVK sequence for 64-bit addresses.
CALL, // Function call.
Fix PR22408 - LLVM producing AArch64 TLS relocations that GNU linkers cannot handle yet. As is described at http://llvm.org/bugs/show_bug.cgi?id=22408, the GNU linkers ld.bfd and ld.gold currently only support a subset of the whole range of AArch64 ELF TLS relocations. Furthermore, they assume that some of the code sequences to access thread-local variables are produced in a very specific sequence. When the sequence is not as the linker expects, it can silently mis-relaxe/mis-optimize the instructions. Even if that wouldn't be the case, it's good to produce the exact sequence, as that ensures that linkers can perform optimizing relaxations. This patch: * implements support for 16MiB TLS area size instead of 4GiB TLS area size. Ideally clang would grow an -mtls-size option to allow support for both, but that's not part of this patch. * by default doesn't produce local dynamic access patterns, as even modern ld.bfd and ld.gold linkers do not support the associated relocations. An option (-aarch64-elf-ldtls-generation) is added to enable generation of local dynamic code sequence, but is off by default. * makes sure that the exact expected code sequence for local dynamic and general dynamic accesses is produced, by making use of a new pseudo instruction. The patch also removes two (AArch64ISD::TLSDESC_BLR, AArch64ISD::TLSDESC_CALL) pre-existing AArch64-specific pseudo SDNode instructions that are superseded by the new one (TLSDESC_CALLSEQ). llvm-svn: 231227
2015-03-04 10:12:08 +01:00
// Produces the full sequence of instructions for getting the thread pointer
// offset of a variable into X0, using the TLSDesc model.
TLSDESC_CALLSEQ,
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
ADRP, // Page address of a TargetGlobalAddress operand.
[AArch64] Add Tiny Code Model for AArch64 This adds the plumbing for the Tiny code model for the AArch64 backend. This, instead of loading addresses through the normal ADRP;ADD pair used in the Small model, uses a single ADR. The 21 bit range of an ADR means that the code and its statically defined symbols need to be within 1MB of each other. This makes it mostly interesting for embedded applications where we want to fit as much as we can in as small a space as possible. Differential Revision: https://reviews.llvm.org/D49673 llvm-svn: 340397
2018-08-22 13:31:39 +02:00
ADR, // ADR
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
ADDlow, // Add the low 12 bits of a TargetGlobalAddress operand.
LOADgot, // Load from automatically generated descriptor (e.g. Global
// Offset Table, TLS record).
RET_FLAG, // Return with a flag operand. Operand 0 is the chain operand.
BRCOND, // Conditional branch instruction; "b.cond".
CSEL,
FCSEL, // Conditional move instruction.
CSINV, // Conditional select invert.
CSNEG, // Conditional select negate.
CSINC, // Conditional select increment.
// Pointer to the thread's local storage area. Materialised from TPIDR_EL0 on
// ELF.
THREAD_POINTER,
ADC,
SBC, // adc, sbc instructions
// Arithmetic instructions which write flags.
ADDS,
SUBS,
ADCS,
SBCS,
ANDS,
AArch64: Implement conditional compare sequence matching. This is a new iteration of the reverted r238793 / http://reviews.llvm.org/D8232 which wrongly assumed that any and/or trees can be represented by conditional compare sequences, however there are some restrictions to that. This version fixes this and adds comments that explain exactly what types of and/or trees can actually be implemented as conditional compare sequences. Related to http://llvm.org/PR20927, rdar://18326194 Differential Revision: http://reviews.llvm.org/D10579 llvm-svn: 242436
2015-07-16 22:02:37 +02:00
// Conditional compares. Operands: left,right,falsecc,cc,flags
CCMP,
CCMN,
FCCMP,
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
// Floating point comparison
FCMP,
// Scalar extract
EXTR,
// Scalar-to-vector duplication
DUP,
DUPLANE8,
DUPLANE16,
DUPLANE32,
DUPLANE64,
// Vector immedate moves
MOVI,
MOVIshift,
MOVIedit,
MOVImsl,
FMOV,
MVNIshift,
MVNImsl,
// Vector immediate ops
BICi,
ORRi,
AArch64/ARM64: port BSL logic from AArch64 & enable test. I enhanced it a little in the process. The decision shouldn't really be beased on whether a BUILD_VECTOR is a splat: any set of constants will do the job provided they're related in the correct way. Also, the BUILD_VECTOR could be any operand of the incoming AND nodes, so it's best to check for all 4 possibilities rather than assuming it'll be the RHS. llvm-svn: 206569
2014-04-18 11:31:01 +02:00
// Vector bit select: similar to ISD::VSELECT but not all bits within an
// element must be identical.
BSL,
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
// Vector arithmetic negation
NEG,
// Vector shuffles
ZIP1,
ZIP2,
UZP1,
UZP2,
TRN1,
TRN2,
REV16,
REV32,
REV64,
EXT,
// Vector shift by scalar
VSHL,
VLSHR,
VASHR,
// Vector shift by scalar (again)
SQSHL_I,
UQSHL_I,
SQSHLU_I,
SRSHR_I,
URSHR_I,
// Vector comparisons
CMEQ,
CMGE,
CMGT,
CMHI,
CMHS,
FCMEQ,
FCMGE,
FCMGT,
// Vector zero comparisons
CMEQz,
CMGEz,
CMGTz,
CMLEz,
CMLTz,
FCMEQz,
FCMGEz,
FCMGTz,
FCMLEz,
FCMLTz,
[AArch64] Avoid going through GPRs for across-vector instructions. This adds new node types for each intrinsic. For instance, for addv, we have AArch64ISD::UADDV, such that: (v4i32 (uaddv ...)) is the same as (v4i32 (scalar_to_vector (i32 (int_aarch64_neon_uaddv ...)))) that is, (v4i32 (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), (i32 (int_aarch64_neon_uaddv ...)), ssub) In a combine, we transform all such across-vector-lanes intrinsics to: (i32 (extract_vector_elt (uaddv ...), 0)) This has one big advantage: by making the extract_element explicit, we enable the existing patterns for lane-aware instructions to fire. This lets us avoid needlessly going through the GPRs. Consider: uint32x4_t test_mul(uint32x4_t a, uint32x4_t b) { return vmulq_n_u32(a, vaddvq_u32(b)); } We now generate: addv.4s s1, v1 mul.4s v0, v0, v1[0] instead of the previous: addv.4s s1, v1 fmov w8, s1 dup.4s v1, w8 mul.4s v0, v1, v0 rdar://20044838 llvm-svn: 231840
2015-03-10 21:45:38 +01:00
// Vector across-lanes addition
// Only the lower result lane is defined.
SADDV,
UADDV,
// Vector across-lanes min/max
// Only the lower result lane is defined.
SMINV,
UMINV,
SMAXV,
UMAXV,
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
// Vector bitwise negation
NOT,
// Vector bitwise selection
BIT,
// Compare-and-branch
CBZ,
CBNZ,
TBZ,
TBNZ,
// Tail calls
TC_RETURN,
// Custom prefetch handling
PREFETCH,
// {s|u}int to FP within a FP register.
SITOF,
AArch64/ARM64: Port NEON post-increment load/store with 2/3/4 vectors to ARM64 backend. llvm-svn: 208284
2014-05-08 09:38:13 +02:00
UITOF,
AArch64: fix big-endian immediate materialisation We were materialising big-endian constants using DAG nodes with types different from what was requested, followed by a bitcast. This is fine on little-endian machines where bitcasting is a nop, but we need a slightly different representation for big-endian. This adds a new set of NVCAST (natural-vector cast) operations which are always nops. Patch by Asiri Rathnayake. llvm-svn: 217138
2014-09-04 11:46:14 +02:00
/// Natural vector cast. ISD::BITCAST is not natural in the big-endian
/// world w.r.t vectors; which causes additional REV instructions to be
/// generated to compensate for the byte-swapping. But sometimes we do
/// need to re-interpret the data in SIMD vector registers in big-endian
/// mode without emitting such REV instructions.
NVCAST,
[AArch64] Generate vector signed/unsigned mul and mla/mls long. Phabricator Revision: http://reviews.llvm.org/D5589 Patch by Balaram Makam <bmakam@codeaurora.org>!! llvm-svn: 219276
2014-10-08 04:31:24 +02:00
SMULL,
UMULL,
[AArch64] Compute the Newton series for reciprocals natively Implement the Newton series for square root, its reciprocal and reciprocal natively using the specialized instructions in AArch64 to perform each series iteration. Differential revision: https://reviews.llvm.org/D26518 llvm-svn: 286907
2016-11-15 00:29:01 +01:00
// Reciprocal estimates and steps.
FRECPE, FRECPS,
FRSQRTE, FRSQRTS,
[AArch64] Optionally use the Newton series for reciprocal estimation Add support for estimating the square root or its reciprocal and division or reciprocal using the combiner generic Newton series. Differential revision: https://reviews.llvm.org/D25291 llvm-svn: 284986
2016-10-24 18:14:58 +02:00
AArch64/ARM64: Port NEON post-increment load/store with 2/3/4 vectors to ARM64 backend. llvm-svn: 208284
2014-05-08 09:38:13 +02:00
// NEON Load/Store with post-increment base updates
LD2post = ISD::FIRST_TARGET_MEMORY_OPCODE,
LD3post,
LD4post,
ST2post,
ST3post,
ST4post,
LD1x2post,
LD1x3post,
LD1x4post,
ST1x2post,
ST1x3post,
ST1x4post,
[ARM64]Implement NEON post-increment LD1(lane) and post-increment LD1R. llvm-svn: 208955
2014-05-16 11:39:02 +02:00
LD1DUPpost,
AArch64/ARM64: Port NEON post-increment load/store with 2/3/4 vectors to ARM64 backend. llvm-svn: 208284
2014-05-08 09:38:13 +02:00
LD2DUPpost,
LD3DUPpost,
LD4DUPpost,
[ARM64]Implement NEON post-increment LD1(lane) and post-increment LD1R. llvm-svn: 208955
2014-05-16 11:39:02 +02:00
LD1LANEpost,
AArch64/ARM64: Port NEON post-increment load/store with 2/3/4 vectors to ARM64 backend. llvm-svn: 208284
2014-05-08 09:38:13 +02:00
LD2LANEpost,
LD3LANEpost,
LD4LANEpost,
ST2LANEpost,
ST3LANEpost,
Basic codegen for MTE stack tagging. Implement IR intrinsics for stack tagging. Generated code is very unoptimized for now. Two special intrinsics, llvm.aarch64.irg.sp and llvm.aarch64.tagp are used to implement a tagged stack frame pointer in a virtual register. Differential Revision: https://reviews.llvm.org/D64172 llvm-svn: 366360
2019-07-17 21:24:02 +02:00
ST4LANEpost,
STG,
STZG,
ST2G,
STZ2G
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
};
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 14:50:23 +02:00
} // end namespace AArch64ISD
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[AArch64] Improve add/sub/cmp isel of uxtw forms. Don't match the UXTW extended reg forms of ADD/ADDS/SUB/SUBS if the 32-bit to 64-bit zero-extend can be done for free by taking advantage of the 32-bit defining instruction zeroing the upper 32-bits of the X register destination. This enables better instruction selection in a few cases, such as: sub x0, xzr, x8 instead of: mov x8, xzr sub x0, x8, w9, uxtw madd x0, x1, x1, x8 instead of: mul x9, x1, x1 add x0, x9, w8, uxtw cmp x2, x8 instead of: sub x8, x2, w8, uxtw cmp x8, #0 add x0, x8, x1, lsl #3 instead of: lsl x9, x1, #3 add x0, x9, w8, uxtw Reviewers: t.p.northover, jmolloy Subscribers: mcrosier, aemerson, llvm-commits, rengolin Differential Revision: https://reviews.llvm.org/D24747 llvm-svn: 282413
2016-09-26 17:34:47 +02:00
namespace {
// Any instruction that defines a 32-bit result zeros out the high half of the
// register. Truncate can be lowered to EXTRACT_SUBREG. CopyFromReg may
// be copying from a truncate. But any other 32-bit operation will zero-extend
// up to 64 bits.
// FIXME: X86 also checks for CMOV here. Do we need something similar?
static inline bool isDef32(const SDNode &N) {
unsigned Opc = N.getOpcode();
return Opc != ISD::TRUNCATE && Opc != TargetOpcode::EXTRACT_SUBREG &&
Opc != ISD::CopyFromReg;
}
} // end anonymous namespace
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 14:50:23 +02:00
class AArch64Subtarget;
class AArch64TargetMachine;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 14:50:23 +02:00
class AArch64TargetLowering : public TargetLowering {
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
public:
Remove getSubtargetImpl from AArch64ISelLowering and cache the correct subtarget by passing it in during the constructor as TargetLowering is Subtarget specific. llvm-svn: 227402
2015-01-29 01:19:42 +01:00
explicit AArch64TargetLowering(const TargetMachine &TM,
const AArch64Subtarget &STI);
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
Fix typos in comments, NFC Summary: Just fixing comments, no functional change. Test Plan: N/A Reviewers: jfb Subscribers: mcrosier, llvm-commits Differential Revision: http://reviews.llvm.org/D5130 llvm-svn: 216784
2014-08-29 23:53:01 +02:00
/// Selects the correct CCAssignFn for a given CallingConvention value.
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
CCAssignFn *CCAssignFnForCall(CallingConv::ID CC, bool IsVarArg) const;
GlobalISel: implement simple function calls on AArch64. We're still limited in the arguments we support, but this at least handles the basic cases. llvm-svn: 278293
2016-08-10 23:44:01 +02:00
/// Selects the correct CCAssignFn for a given CallingConvention value.
CCAssignFn *CCAssignFnForReturn(CallingConv::ID CC) const;
don't repeat function names in comments; NFC llvm-svn: 252502
2015-11-09 20:18:26 +01:00
/// Determine which of the bits specified in Mask are known to be either zero
/// or one and return them in the KnownZero/KnownOne bitsets.
[SelectionDAG] Use KnownBits struct in DAG's computeKnownBits and simplifyDemandedBits This patch replaces the separate APInts for KnownZero/KnownOne with a single KnownBits struct. This is similar to what was done to ValueTracking's version recently. This is largely a mechanical transformation from KnownZero to Known.Zero. Differential Revision: https://reviews.llvm.org/D32569 llvm-svn: 301620
2017-04-28 07:31:46 +02:00
void computeKnownBitsForTargetNode(const SDValue Op, KnownBits &Known,
const APInt &DemandedElts,
[DAGCombiner] Add vector demanded elements support to computeKnownBitsForTargetNode Follow up to D25691, this sets up the plumbing necessary to support vector demanded elements support in known bits calculations in target nodes. Differential Revision: https://reviews.llvm.org/D31249 llvm-svn: 299201
2017-03-31 13:24:16 +02:00
const SelectionDAG &DAG,
Rename ComputeMaskedBits to computeKnownBits. "Masked" has been inappropriate since it lost its Mask parameter in r154011. llvm-svn: 208811
2014-05-14 23:14:37 +02:00
unsigned Depth = 0) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[AArch64] Improve code generation for logical instructions taking immediate operands. This commit adds an AArch64 dag-combine that optimizes code generation for logical instructions taking immediate operands. The optimization uses demanded bits to change a logical instruction's immediate operand so that the immediate can be folded into the immediate field of the instruction. This recommits r300932 and r300930, which was causing dag-combine to loop forever. The problem was that optimizeLogicalImm was returning true even when there was no change to the immediate node (which happened when the immediate was all zeros or ones), which caused dag-combine to push and pop the same node to the work list over and over again without making any progress. This commit fixes the bug by returning false early in optimizeLogicalImm if the immediate is all zeros or ones. Also, it changes the code to compare the immediate with 0 or Mask rather than calling countPopulation. rdar://problem/18231627 Differential Revision: https://reviews.llvm.org/D5591 llvm-svn: 301019
2017-04-21 20:53:12 +02:00
bool targetShrinkDemandedConstant(SDValue Op, const APInt &Demanded,
TargetLoweringOpt &TLO) const override;
Re-instate the EVT parameter to getScalarShiftAmountTy() for OOT user A documentation for this function would be nice by the way. From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 241807
2015-07-09 17:12:23 +02:00
MVT getScalarShiftAmountTy(const DataLayout &DL, EVT) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
don't repeat function names in comments; NFC llvm-svn: 252502
2015-11-09 20:18:26 +01:00
/// Returns true if the target allows unaligned memory accesses of the
/// specified type.
[TargetLowering] Add MachineMemOperand::Flags to allowsMemoryAccess tests (PR42123) As discussed on D62910, we need to check whether particular types of memory access are allowed, not just their alignment/address-space. This NFC patch adds a MachineMemOperand::Flags argument to allowsMemoryAccess and allowsMisalignedMemoryAccesses, and wires up calls to pass the relevant flags to them. If people are happy with this approach I can then update X86TargetLowering::allowsMisalignedMemoryAccesses to handle misaligned NT load/stores. Differential Revision: https://reviews.llvm.org/D63075 llvm-svn: 363179
2019-06-12 19:14:03 +02:00
bool allowsMisalignedMemoryAccesses(
EVT VT, unsigned AddrSpace = 0, unsigned Align = 1,
MachineMemOperand::Flags Flags = MachineMemOperand::MONone,
bool *Fast = nullptr) const override;
[GlobalISel] Support for inlining memcpy, memset and memmove calls. This introduces a new family of combiner helper routines that re-use the target specific cost model from SelectionDAG, and generate inline implementations of the memcpy family of intrinsics. The combines are only enabled at optimization levels higher than -O0, and give very substantial performance improvements. Differential Revision: https://reviews.llvm.org/D65167 llvm-svn: 366951
2019-07-25 00:17:31 +02:00
/// LLT variant.
bool allowsMisalignedMemoryAccesses(
LLT Ty, unsigned AddrSpace, unsigned Align, MachineMemOperand::Flags Flags,
bool *Fast = nullptr) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
don't repeat function names in comments; NFC llvm-svn: 252502
2015-11-09 20:18:26 +01:00
/// Provide custom lowering hooks for some operations.
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
SDValue LowerOperation(SDValue Op, SelectionDAG &DAG) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
const char *getTargetNodeName(unsigned Opcode) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
SDValue PerformDAGCombine(SDNode *N, DAGCombinerInfo &DCI) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
/// Returns true if a cast between SrcAS and DestAS is a noop.
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
bool isNoopAddrSpaceCast(unsigned SrcAS, unsigned DestAS) const override {
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
// Addrspacecasts are always noops.
return true;
}
don't repeat function names in comments; NFC llvm-svn: 252502
2015-11-09 20:18:26 +01:00
/// This method returns a target specific FastISel object, or null if the
/// target does not support "fast" ISel.
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
FastISel *createFastISel(FunctionLoweringInfo &funcInfo,
const TargetLibraryInfo *libInfo) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
bool isOffsetFoldingLegal(const GlobalAddressSDNode *GA) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[TargetLowering] Add code size information on isFPImmLegal. NFC This allows better code size for aarch64 floating point materialization in a future patch. Reviewers: evandro Differential Revision: https://reviews.llvm.org/D58690 llvm-svn: 356389
2019-03-18 19:40:07 +01:00
bool isFPImmLegal(const APFloat &Imm, EVT VT,
bool ForCodeSize) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
don't repeat function names in comments; NFC llvm-svn: 252502
2015-11-09 20:18:26 +01:00
/// Return true if the given shuffle mask can be codegen'd directly, or if it
/// should be stack expanded.
TargetLowering: Change isShuffleMaskLegal's mask argument type to ArrayRef<int>. NFCI. Changing mask argument type from const SmallVectorImpl<int>& to ArrayRef<int>. This came up in D35700 where a mask is received as an ArrayRef<int> and we want to pass it to TargetLowering::isShuffleMaskLegal(). Also saves a few lines of code. llvm-svn: 309085
2017-07-26 10:06:58 +02:00
bool isShuffleMaskLegal(ArrayRef<int> M, EVT VT) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
don't repeat function names in comments; NFC llvm-svn: 252502
2015-11-09 20:18:26 +01:00
/// Return the ISD::SETCC ValueType.
Make TargetLowering::getPointerTy() taking DataLayout as an argument Summary: This change is part of a series of commits dedicated to have a single DataLayout during compilation by using always the one owned by the module. Reviewers: echristo Subscribers: jholewinski, ted, yaron.keren, rafael, llvm-commits Differential Revision: http://reviews.llvm.org/D11028 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 241775
2015-07-09 04:09:04 +02:00
EVT getSetCCResultType(const DataLayout &DL, LLVMContext &Context,
EVT VT) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
SDValue ReconstructShuffle(SDValue Op, SelectionDAG &DAG) const;
CodeGen: Use MachineInstr& in TargetLowering, NFC This is a mechanical change to make TargetLowering API take MachineInstr& (instead of MachineInstr*), since the argument is expected to be a valid MachineInstr. In one case, changed a parameter from MachineInstr* to MachineBasicBlock::iterator, since it was used as an insertion point. As a side effect, this removes a bunch of MachineInstr* to MachineBasicBlock::iterator implicit conversions, a necessary step toward fixing PR26753. llvm-svn: 274287
2016-07-01 00:52:52 +02:00
MachineBasicBlock *EmitF128CSEL(MachineInstr &MI,
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
MachineBasicBlock *BB) const;
[ARM64] [Windows] Handle funclets This patch adds support for funclets in frame lowering and ISel lowering. Together with D50288 and D50166, it enables C++ exception handling. Patch by Sanjin Sijaric, with some fixes by me. Differential Revision: https://reviews.llvm.org/D51524 llvm-svn: 346568
2018-11-10 00:33:30 +01:00
MachineBasicBlock *EmitLoweredCatchRet(MachineInstr &MI,
MachineBasicBlock *BB) const;
MachineBasicBlock *EmitLoweredCatchPad(MachineInstr &MI,
MachineBasicBlock *BB) const;
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
MachineBasicBlock *
CodeGen: Use MachineInstr& in TargetLowering, NFC This is a mechanical change to make TargetLowering API take MachineInstr& (instead of MachineInstr*), since the argument is expected to be a valid MachineInstr. In one case, changed a parameter from MachineInstr* to MachineBasicBlock::iterator, since it was used as an insertion point. As a side effect, this removes a bunch of MachineInstr* to MachineBasicBlock::iterator implicit conversions, a necessary step toward fixing PR26753. llvm-svn: 274287
2016-07-01 00:52:52 +02:00
EmitInstrWithCustomInserter(MachineInstr &MI,
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
MachineBasicBlock *MBB) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
bool getTgtMemIntrinsic(IntrinsicInfo &Info, const CallInst &I,
TLI: Allow using PSV for intrinsic mem operands llvm-svn: 320756
2017-12-14 23:34:10 +01:00
MachineFunction &MF,
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
unsigned Intrinsic) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[AArch64] Don't reduce the width of loads if it prevents combining a shift Loads and stores can only shift the offset register by the size of the value being loaded, but currently the DAGCombiner will reduce the width of the load if it's followed by a trunc making it impossible to later combine the shift. Solve this by implementing shouldReduceLoadWidth for the AArch64 backend and make it prevent the width reduction if this is what would happen, though do allow it if reducing the load width will let us eliminate a later sign or zero extend. Differential Revision: https://reviews.llvm.org/D44794 llvm-svn: 328321
2018-03-23 15:47:07 +01:00
bool shouldReduceLoadWidth(SDNode *Load, ISD::LoadExtType ExtTy,
EVT NewVT) const override;
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
bool isTruncateFree(Type *Ty1, Type *Ty2) const override;
bool isTruncateFree(EVT VT1, EVT VT2) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
Prevent hoisting fmul from THEN/ELSE to IF if there is fmsub/fmadd opportunity. This patch adds the isProfitableToHoist API. For AArch64, we want to prevent a fmul from being hoisted in cases where it is more profitable to form a fmsub/fmadd. Phabricator Review: http://reviews.llvm.org/D7299 Patch by Lawrence Hu <lawrence@codeaurora.org> llvm-svn: 230241
2015-02-23 20:15:16 +01:00
bool isProfitableToHoist(Instruction *I) const override;
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
bool isZExtFree(Type *Ty1, Type *Ty2) const override;
bool isZExtFree(EVT VT1, EVT VT2) const override;
bool isZExtFree(SDValue Val, EVT VT2) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[CGP] Add support for sinking operands to their users, if they are free. This patch improves code generation for some AArch64 ACLE intrinsics. It adds support to CGP to duplicate and sink operands to their user, if they can be folded into a target instruction, like zexts and sub into usubl. It adds a TargetLowering hook shouldSinkOperands, which looks at the operands of instructions to see if sinking is profitable. I decided to add a new target hook, as for the sinking to be profitable, at least on AArch64, we have to look at multiple operands of an instruction, instead of looking at the users of a zext for example. The sinking is done in CGP, because it works around an instruction selection limitation. If instruction selection is not limited to a single basic block, this patch should not be needed any longer. Alternatively this could be done in the LoopSink pass, which tries to undo LICM for instructions in blocks that are not executed frequently. Note that we do not force the operands to sink to have a single user, because we duplicate them before sinking. Therefore this is only desirable if they really can be done for free. Additionally we could consider the impact on live ranges later on. This should fix https://bugs.llvm.org/show_bug.cgi?id=40025. As for performance, we have internal code that uses intrinsics and can be speed up by 10% by this change. Reviewers: SjoerdMeijer, t.p.northover, samparker, efriedma, RKSimon, spatel Reviewed By: samparker Differential Revision: https://reviews.llvm.org/D57377 llvm-svn: 353152
2019-02-05 11:27:40 +01:00
bool shouldSinkOperands(Instruction *I,
SmallVectorImpl<Use *> &Ops) const override;
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
bool hasPairedLoad(EVT LoadedType, unsigned &RequiredAligment) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[AArch64] Lower interleaved memory accesses to ldN/stN intrinsics. This patch also adds a function to calculate the cost of interleaved memory accesses. E.g. Lower an interleaved load: %wide.vec = load <8 x i32>, <8 x i32>* %ptr %v0 = shuffle %wide.vec, undef, <0, 2, 4, 6> %v1 = shuffle %wide.vec, undef, <1, 3, 5, 7> into: %ld2 = { <4 x i32>, <4 x i32> } call llvm.aarch64.neon.ld2(%ptr) %vec0 = extractelement { <4 x i32>, <4 x i32> } %ld2, i32 0 %vec1 = extractelement { <4 x i32>, <4 x i32> } %ld2, i32 1 E.g. Lower an interleaved store: %i.vec = shuffle <8 x i32> %v0, <8 x i32> %v1, <0, 4, 8, 1, 5, 9, 2, 6, 10, 3, 7, 11> store <12 x i32> %i.vec, <12 x i32>* %ptr into: %sub.v0 = shuffle <8 x i32> %v0, <8 x i32> v1, <0, 1, 2, 3> %sub.v1 = shuffle <8 x i32> %v0, <8 x i32> v1, <4, 5, 6, 7> %sub.v2 = shuffle <8 x i32> %v0, <8 x i32> v1, <8, 9, 10, 11> call void llvm.aarch64.neon.st3(%sub.v0, %sub.v1, %sub.v2, %ptr) Differential Revision: http://reviews.llvm.org/D10533 llvm-svn: 240754
2015-06-26 04:32:07 +02:00
unsigned getMaxSupportedInterleaveFactor() const override { return 4; }
bool lowerInterleavedLoad(LoadInst *LI,
ArrayRef<ShuffleVectorInst *> Shuffles,
ArrayRef<unsigned> Indices,
unsigned Factor) const override;
bool lowerInterleavedStore(StoreInst *SI, ShuffleVectorInst *SVI,
unsigned Factor) const override;
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
bool isLegalAddImmediate(int64_t) const override;
bool isLegalICmpImmediate(int64_t) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[CGP] Split large data structres to sink more GEPs Accessing the members of a large data structures needs a lot of GEPs which usually have large offsets due to the size of the underlying data structure. If the offsets are too large to fit into the r+i addressing mode, these GEPs cannot be sunk to their users' blocks and many extra registers are needed then to carry the values of these GEPs. This patch tries to split a large data struct starting from %base like the following. Before: BB0: %base = BB1: %gep0 = gep %base, off0 %gep1 = gep %base, off1 %gep2 = gep %base, off2 BB2: %load1 = load %gep0 %load2 = load %gep1 %load3 = load %gep2 After: BB0: %base = %new_base = gep %base, off0 BB1: %new_gep0 = %new_base %new_gep1 = gep %new_base, off1 - off0 %new_gep2 = gep %new_base, off2 - off0 BB2: %load1 = load i32, i32* %new_gep0 %load2 = load i32, i32* %new_gep1 %load3 = load i32, i32* %new_gep2 In the above example, the struct is split into two parts. The first part still starts from %base and the second part starts from %new_base. After the splitting, %new_gep1 and %new_gep2 have smaller offsets and then can be sunk to BB2 and folded into their users. The algorithm to split data structure is simple and very similar to the work of merging SExts. First, it collects GEPs that have large offsets when iterating the blocks. Second, it splits the underlying data structures and updates the collected GEPs to use smaller offsets. Differential Revision: https://reviews.llvm.org/D42759 llvm-svn: 332015
2018-05-10 20:27:36 +02:00
bool shouldConsiderGEPOffsetSplit() const override;
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
EVT getOptimalMemOpType(uint64_t Size, unsigned DstAlign, unsigned SrcAlign,
bool IsMemset, bool ZeroMemset, bool MemcpyStrSrc,
[TargetLowering] Change getOptimalMemOpType to take a function attribute list The MachineFunction wasn't used in getOptimalMemOpType, but more importantly, this allows reuse of findOptimalMemOpLowering that is calling getOptimalMemOpType. This is the groundwork for the changes in D59766 and D59787, that allows implementation of TTI::getMemcpyCost. Differential Revision: https://reviews.llvm.org/D59785 llvm-svn: 359537
2019-04-30 10:38:12 +02:00
const AttributeList &FuncAttributes) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[GlobalISel] Support for inlining memcpy, memset and memmove calls. This introduces a new family of combiner helper routines that re-use the target specific cost model from SelectionDAG, and generate inline implementations of the memcpy family of intrinsics. The combines are only enabled at optimization levels higher than -O0, and give very substantial performance improvements. Differential Revision: https://reviews.llvm.org/D65167 llvm-svn: 366951
2019-07-25 00:17:31 +02:00
LLT getOptimalMemOpLLT(uint64_t Size, unsigned DstAlign, unsigned SrcAlign,
bool IsMemset, bool ZeroMemset, bool MemcpyStrSrc,
const AttributeList &FuncAttributes) const override;
don't repeat function names in comments; NFC llvm-svn: 252502
2015-11-09 20:18:26 +01:00
/// Return true if the addressing mode represented by AM is legal for this
/// target, for a load/store of the specified type.
Make isLegalAddressingMode() taking DataLayout as an argument Summary: This change is part of a series of commits dedicated to have a single DataLayout during compilation by using always the one owned by the module. Reviewers: echristo Subscribers: jholewinski, llvm-commits, rafael, yaron.keren Differential Revision: http://reviews.llvm.org/D11040 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 241778
2015-07-09 04:09:40 +02:00
bool isLegalAddressingMode(const DataLayout &DL, const AddrMode &AM, Type *Ty,
[SystemZ, LoopStrengthReduce] This patch makes LSR generate better code for SystemZ in the cases of memory intrinsics, Load->Store pairs or comparison of immediate with memory. In order to achieve this, the following common code changes were made: * New TTI hook: LSRWithInstrQueries(), which defaults to false. Controls if LSR should do instruction-based addressing evaluations by calling isLegalAddressingMode() with the Instruction pointers. * In LoopStrengthReduce: handle address operands of memset, memmove and memcpy as address uses, and call isFoldableMemAccessOffset() for any LSRUse::Address, not just loads or stores. SystemZ changes: * isLSRCostLess() implemented with Insns first, and without ImmCost. * New function supportedAddressingMode() that is a helper for TTI methods looking at Instructions passed via pointers. Review: Ulrich Weigand, Quentin Colombet https://reviews.llvm.org/D35262 https://reviews.llvm.org/D35049 llvm-svn: 308729
2017-07-21 13:59:37 +02:00
unsigned AS,
Instruction *I = nullptr) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
Remove \brief commands from doxygen comments. We've been running doxygen with the autobrief option for a couple of years now. This makes the \brief markers into our comments redundant. Since they are a visual distraction and we don't want to encourage more \brief markers in new code either, this patch removes them all. Patch produced by for i in $(git grep -l '\\brief'); do perl -pi -e 's/\\brief //g' $i & done Differential Revision: https://reviews.llvm.org/D46290 llvm-svn: 331272
2018-05-01 17:54:18 +02:00
/// Return the cost of the scaling factor used in the addressing
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
/// mode represented by AM for this target, for a load/store
/// of the specified type.
/// If the AM is supported, the return value must be >= 0.
/// If the AM is not supported, it returns a negative value.
Make isLegalAddressingMode() taking DataLayout as an argument Summary: This change is part of a series of commits dedicated to have a single DataLayout during compilation by using always the one owned by the module. Reviewers: echristo Subscribers: jholewinski, llvm-commits, rafael, yaron.keren Differential Revision: http://reviews.llvm.org/D11040 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 241778
2015-07-09 04:09:40 +02:00
int getScalingFactorCost(const DataLayout &DL, const AddrMode &AM, Type *Ty,
Add address space argument to isLegalAddressingMode This is important because of different addressing modes depending on the address space for GPU targets. This only adds the argument, and does not update any of the uses to provide the correct address space. llvm-svn: 238723
2015-06-01 07:31:59 +02:00
unsigned AS) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
don't repeat function names in comments; NFC llvm-svn: 252502
2015-11-09 20:18:26 +01:00
/// Return true if an FMA operation is faster than a pair of fmul and fadd
/// instructions. fmuladd intrinsics will be expanded to FMAs when this method
/// returns true, otherwise fmuladd is expanded to fmul + fadd.
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
bool isFMAFasterThanFMulAndFAdd(EVT VT) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
Make consistent use of MCPhysReg instead of uint16_t throughout the tree. llvm-svn: 205610
2014-04-04 07:16:06 +02:00
const MCPhysReg *getScratchRegisters(CallingConv::ID CC) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
Remove \brief commands from doxygen comments. We've been running doxygen with the autobrief option for a couple of years now. This makes the \brief markers into our comments redundant. Since they are a visual distraction and we don't want to encourage more \brief markers in new code either, this patch removes them all. Patch produced by for i in $(git grep -l '\\brief'); do perl -pi -e 's/\\brief //g' $i & done Differential Revision: https://reviews.llvm.org/D46290 llvm-svn: 331272
2018-05-01 17:54:18 +02:00
/// Returns false if N is a bit extraction pattern of (X >> C) & Mask.
[ARM] Make PerformSHLSimplify add nodes to the DAG worklist correctly. Intentionally excluding nodes from the DAGCombine worklist is likely to lead to weird optimizations and infinite loops, so it's generally a bad idea. To avoid the infinite loops, fix DAGCombine to use the isDesirableToCommuteWithShift target hook before performing the transforms in question, and implement the target hook in the ARM backend disable the transforms in question. Fixes https://bugs.llvm.org/show_bug.cgi?id=38530 . (I don't have a reduced testcase for that bug. But we should have sufficient test coverage for PerformSHLSimplify given that we're not playing weird tricks with the worklist. I can try to bugpoint it if necessary, though.) Differential Revision: https://reviews.llvm.org/D50667 llvm-svn: 339734
2018-08-15 00:10:25 +02:00
bool isDesirableToCommuteWithShift(const SDNode *N,
CombineLevel Level) const override;
[ARM64] Prevent bit extraction to be adjusted by following shift For pattern like ((x >> C1) & Mask) << C2, DAG combiner may convert it into (x >> (C1-C2)) & (Mask << C2), which makes pattern matching of ubfx more difficult. For example: Given %shr = lshr i64 %x, 4 %and = and i64 %shr, 15 %arrayidx = getelementptr inbounds [8 x [64 x i64]]* @arr, i64 0, %i64 2, i64 %and %0 = load i64* %arrayidx With current shift folding, it takes 3 instrs to compute base address: lsr x8, x0, #1 and x8, x8, #0x78 add x8, x9, x8 If using ubfx, it only needs 2 instrs: ubfx x8, x0, #4, #4 add x8, x9, x8, lsl #3 This fixes bug 19589 llvm-svn: 207702
2014-04-30 23:07:24 +02:00
Remove \brief commands from doxygen comments. We've been running doxygen with the autobrief option for a couple of years now. This makes the \brief markers into our comments redundant. Since they are a visual distraction and we don't want to encourage more \brief markers in new code either, this patch removes them all. Patch produced by for i in $(git grep -l '\\brief'); do perl -pi -e 's/\\brief //g' $i & done Differential Revision: https://reviews.llvm.org/D46290 llvm-svn: 331272
2018-05-01 17:54:18 +02:00
/// Returns true if it is beneficial to convert a load of a constant
ARM64: switch to IR-based atomic operations. Goodbye code! (Game: spot the bug fixed by the change). llvm-svn: 206490
2014-04-17 22:00:33 +02:00
/// to just the constant itself.
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
bool shouldConvertConstantLoadToIntImm(const APInt &Imm,
Type *Ty) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[AArch64] define isExtractSubvectorCheap Following the ARM-neon backend, define isExtractSubvectorCheap to return true when extracting low and high part of a neon register. The patch disables a test in llvm/test/CodeGen/AArch64/arm64-ext.ll This testcase is fragile in the sense that it requires a BUILD_VECTOR to "survive" all DAG transforms until ISelLowering. The testcase is supposed to check that AArch64TargetLowering::ReconstructShuffle() works, and for that we need a BUILD_VECTOR in ISelLowering. As we now transform the BUILD_VECTOR earlier into an VEXT + vector_shuffle, we don't have the BUILD_VECTOR pattern when we get to ISelLowering. As there is no way to disable the combiner to only exercise the code in ISelLowering, the patch disables the testcase. Differential revision: https://reviews.llvm.org/D43973 llvm-svn: 326811
2018-03-06 17:54:55 +01:00
/// Return true if EXTRACT_SUBVECTOR is cheap for this result type
/// with this index.
bool isExtractSubvectorCheap(EVT ResVT, EVT SrcVT,
unsigned Index) const override;
ARM64: switch to IR-based atomic operations. Goodbye code! (Game: spot the bug fixed by the change). llvm-svn: 206490
2014-04-17 22:00:33 +02:00
Value *emitLoadLinked(IRBuilder<> &Builder, Value *Addr,
AtomicOrdering Ord) const override;
Value *emitStoreConditional(IRBuilder<> &Builder, Value *Val,
Value *Addr, AtomicOrdering Ord) const override;
[AArch64] Emit clrex in the expanded cmpxchg fail block. In the comparison failure block of a cmpxchg expansion, the initial ldrex/ldxr will not be followed by a matching strex/stxr. On ARM/AArch64, this unnecessarily ties up the execution monitor, which might have a negative performance impact on some uarchs. Instead, release the monitor in the failure block. The clrex instruction was designed for this: use it. Also see ARMARM v8-A B2.10.2: "Exclusive access instructions and Shareable memory locations". Differential Revision: http://reviews.llvm.org/D13033 llvm-svn: 248291
2015-09-22 19:21:44 +02:00
void emitAtomicCmpXchgNoStoreLLBalance(IRBuilder<> &Builder) const override;
[CodeGen] Refactor TLI/AtomicExpand interface to make LLSC explicit. We used to have this magic "hasLoadLinkedStoreConditional()" callback, which really meant two things: - expand cmpxchg (to ll/sc). - expand atomic loads using ll/sc (rather than cmpxchg). Remove it, and, instead, introduce explicit callbacks: - bool shouldExpandAtomicCmpXchgInIR(inst) - AtomicExpansionKind shouldExpandAtomicLoadInIR(inst) Differential Revision: http://reviews.llvm.org/D12557 llvm-svn: 247429
2015-09-11 19:08:28 +02:00
TargetLoweringBase::AtomicExpansionKind
shouldExpandAtomicLoadInIR(LoadInst *LI) const override;
Refactor AtomicExpandPass and add a generic isAtomic() method to Instruction Summary: Split shouldExpandAtomicInIR() into different versions for Stores/Loads/RMWs/CmpXchgs. Makes runOnFunction cleaner (no more redundant checking/casting), and will help moving the X86 backend to this pass. This requires a way of easily detecting which instructions are atomic. I followed the pattern of mayReadFromMemory, mayWriteOrReadMemory, etc.. in making isAtomic() a method of Instruction implemented by a switch on the opcodes. Test Plan: make check Reviewers: jfb Subscribers: mcrosier, llvm-commits Differential Revision: http://reviews.llvm.org/D5035 llvm-svn: 217080
2014-09-03 23:29:59 +02:00
bool shouldExpandAtomicStoreInIR(StoreInst *SI) const override;
[CodeGen] Rename AtomicRMWExpansionKind to AtomicExpansionKind. This lets us generalize its usage to the other atomic instructions. llvm-svn: 247428
2015-09-11 19:08:17 +02:00
TargetLoweringBase::AtomicExpansionKind
Mutate TargetLowering::shouldExpandAtomicRMWInIR to specifically dictate how AtomicRMWInsts are expanded. Summary: In PNaCl, most atomic instructions have their own @llvm.nacl.atomic.* function, each one, with a few exceptions, represents a consistent behaviour across all NaCl-supported targets. Unfortunately, the atomic RMW operations nand, [u]min, and [u]max aren't directly represented by any such @llvm.nacl.atomic.* function. This patch refines shouldExpandAtomicRMWInIR in TargetLowering so that a future `Le32TargetLowering` class can selectively inform the caller how the target desires the atomic RMW instruction to be expanded (ie via load-linked/store-conditional for ARM/AArch64, via cmpxchg for X86/others?, or not at all for Mips) if at all. This does not represent a behavioural change and as such no tests were added. Patch by: Richard Diamond. Reviewers: jfb Reviewed By: jfb Subscribers: jfb, aemerson, t.p.northover, llvm-commits Differential Revision: http://reviews.llvm.org/D7713 llvm-svn: 231250
2015-03-04 16:47:57 +01:00
shouldExpandAtomicRMWInIR(AtomicRMWInst *AI) const override;
ARM64: switch to IR-based atomic operations. Goodbye code! (Game: spot the bug fixed by the change). llvm-svn: 206490
2014-04-17 22:00:33 +02:00
[AtomicExpandPass]: Add a hook for custom cmpxchg expansion in IR This involves changing the shouldExpandAtomicCmpXchgInIR interface, but I have updated the in-tree backends using this hook (ARM, AArch64, Hexagon) so they will see no functional change. Previously this hook returned bool, but it now returns AtomicExpansionKind. This hook allows targets to select how a given cmpxchg is to be expanded. D48131 uses this to expand part-word cmpxchg to a target-specific intrinsic. See my associated RFC for more info on the motivation for this change <http://lists.llvm.org/pipermail/llvm-dev/2018-June/123993.html>. Differential Revision: https://reviews.llvm.org/D48130 llvm-svn: 342550
2018-09-19 16:51:42 +02:00
TargetLoweringBase::AtomicExpansionKind
shouldExpandAtomicCmpXchgInIR(AtomicCmpXchgInst *AI) const override;
[CodeGen] Refactor TLI/AtomicExpand interface to make LLSC explicit. We used to have this magic "hasLoadLinkedStoreConditional()" callback, which really meant two things: - expand cmpxchg (to ll/sc). - expand atomic loads using ll/sc (rather than cmpxchg). Remove it, and, instead, introduce explicit callbacks: - bool shouldExpandAtomicCmpXchgInIR(inst) - AtomicExpansionKind shouldExpandAtomicLoadInIR(inst) Differential Revision: http://reviews.llvm.org/D12557 llvm-svn: 247429
2015-09-11 19:08:28 +02:00
[stack protector] Fix a potential security bug in stack protector where the address of the stack guard was being spilled to the stack. Previously the address of the stack guard would get spilled to the stack if it was impossible to keep it in a register. This patch introduces a new target independent node and pseudo instruction which gets expanded post-RA to a sequence of instructions that load the stack guard value. Register allocator can now just remat the value when it can't keep it in a register. <rdar://problem/12475629> llvm-svn: 213967
2014-07-25 21:31:34 +02:00
bool useLoadStackGuardNode() const override;
[codegen,aarch64] Add a target hook to the code generator to control vector type legalization strategies in a more fine grained manner, and change the legalization of several v1iN types and v1f32 to be widening rather than scalarization on AArch64. This fixes an assertion failure caused by scalarizing nodes like "v1i32 trunc v1i64". As v1i64 is legal it will fail to scalarize v1i32. This also provides a foundation for other targets to have more granular control over how vector types are legalized. Patch by Hao Liu, reviewed by Tim Northover. I'm committing it to allow some work to start taking place on top of this patch as it adds some really important hooks to the backend that I'd like to immediately start using. =] http://reviews.llvm.org/D4322 llvm-svn: 212242
2014-07-03 02:23:43 +02:00
TargetLoweringBase::LegalizeTypeAction
[TargetLowering] Change TargetLoweringBase::getPreferredVectorAction to take an MVT instead of an EVT. NFC The main caller of this already has an MVT and several targets called getSimpleVT inside without checking isSimple. This makes the simpleness explicit. llvm-svn: 346180
2018-11-06 00:26:13 +01:00
getPreferredVectorAction(MVT VT) const override;
[codegen,aarch64] Add a target hook to the code generator to control vector type legalization strategies in a more fine grained manner, and change the legalization of several v1iN types and v1f32 to be widening rather than scalarization on AArch64. This fixes an assertion failure caused by scalarizing nodes like "v1i32 trunc v1i64". As v1i64 is legal it will fail to scalarize v1i32. This also provides a foundation for other targets to have more granular control over how vector types are legalized. Patch by Hao Liu, reviewed by Tim Northover. I'm committing it to allow some work to start taking place on top of this patch as it adds some really important hooks to the backend that I'd like to immediately start using. =] http://reviews.llvm.org/D4322 llvm-svn: 212242
2014-07-03 02:23:43 +02:00
Faster stack-protector for Android/AArch64. Bionic has a defined thread-local location for the stack protector cookie. Emit a direct load instead of going through __stack_chk_guard. llvm-svn: 265481
2016-04-06 00:41:50 +02:00
/// If the target has a standard location for the stack protector cookie,
/// returns the address of that location. Otherwise, returns nullptr.
[SSP] Remove llvm.stackprotectorcheck. This is a cleanup patch for SSP support in LLVM. There is no functional change. llvm.stackprotectorcheck is not needed, because SelectionDAG isn't actually lowering it in SelectBasicBlock; rather, it adds check code in FinishBasicBlock, ignoring the position where the intrinsic is inserted (See FindSplitPointForStackProtector()). llvm-svn: 265851
2016-04-08 23:26:31 +02:00
Value *getIRStackGuard(IRBuilder<> &IRB) const override;
Faster stack-protector for Android/AArch64. Bionic has a defined thread-local location for the stack protector cookie. Emit a direct load instead of going through __stack_chk_guard. llvm-svn: 265481
2016-04-06 00:41:50 +02:00
[COFF, ARM64] Add support for MSVC buffer security check Reviewers: rnk, mstorsjo, compnerd, efriedma, TomTan Reviewed By: rnk Subscribers: javed.absar, kristof.beyls, chrib, llvm-commits Differential Revision: https://reviews.llvm.org/D54248 llvm-svn: 346469
2018-11-09 03:48:36 +01:00
void insertSSPDeclarations(Module &M) const override;
Value *getSDagStackGuard(const Module &M) const override;
[opaque pointer types] Pass function types to CallInst creation. This cleans up all CallInst creation in LLVM to explicitly pass a function type rather than deriving it from the pointer's element-type. Differential Revision: https://reviews.llvm.org/D57170 llvm-svn: 352909
2019-02-01 21:43:25 +01:00
Function *getSSPStackGuardCheck(const Module &M) const override;
[COFF, ARM64] Add support for MSVC buffer security check Reviewers: rnk, mstorsjo, compnerd, efriedma, TomTan Reviewed By: rnk Subscribers: javed.absar, kristof.beyls, chrib, llvm-commits Differential Revision: https://reviews.llvm.org/D54248 llvm-svn: 346469
2018-11-09 03:48:36 +01:00
[safestack] Fast access to the unsafe stack pointer on AArch64/Android. Android libc provides a fixed TLS slot for the unsafe stack pointer, and this change implements direct access to that slot on AArch64 via __builtin_thread_pointer() + offset. This change also moves more code into TargetLowering and its target-specific subclasses to get rid of target-specific codegen in SafeStackPass. This change does not touch the ARM backend because ARM lowers builting_thread_pointer as aeabi_read_tp, which is not available on Android. The previous iteration of this change was reverted in r250461. This version leaves the generic, compiler-rt based implementation in SafeStack.cpp instead of moving it to TargetLoweringBase in order to allow testing without a TargetMachine. llvm-svn: 251324
2015-10-26 19:28:25 +01:00
/// If the target has a standard location for the unsafe stack pointer,
/// returns the address of that location. Otherwise, returns nullptr.
Value *getSafeStackPointerLocation(IRBuilder<> &IRB) const override;
[WinEH] Update exception pointer registers Summary: The CLR's personality routine passes these in rdx/edx, not rax/eax. Make getExceptionPointerRegister a virtual method parameterized by personality function to allow making this distinction. Similarly make getExceptionSelectorRegister a virtual method parameterized by personality function, for symmetry. Reviewers: pgavlin, majnemer, rnk Subscribers: jyknight, dsanders, llvm-commits Differential Revision: http://reviews.llvm.org/D14344 llvm-svn: 252383
2015-11-07 02:11:31 +01:00
/// If a physical register, this returns the register that receives the
/// exception address on entry to an EH pad.
unsigned
getExceptionPointerRegister(const Constant *PersonalityFn) const override {
// FIXME: This is a guess. Has this been defined yet?
return AArch64::X0;
}
/// If a physical register, this returns the register that receives the
/// exception typeid on entry to a landing pad.
unsigned
getExceptionSelectorRegister(const Constant *PersonalityFn) const override {
// FIXME: This is a guess. Has this been defined yet?
return AArch64::X1;
}
Rename AttributeSet to AttributeList Summary: This class is a list of AttributeSetNodes corresponding the function prototype of a call or function declaration. This class used to be called ParamAttrListPtr, then AttrListPtr, then AttributeSet. It is typically accessed by parameter and return value index, so "AttributeList" seems like a more intuitive name. Rename AttributeSetImpl to AttributeListImpl to follow suit. It's useful to rename this class so that we can rename AttributeSetNode to AttributeSet later. AttributeSet is the set of attributes that apply to a single function, argument, or return value. Reviewers: sanjoy, javed.absar, chandlerc, pete Reviewed By: pete Subscribers: pete, jholewinski, arsenm, dschuff, mehdi_amini, jfb, nhaehnle, sbc100, void, llvm-commits Differential Revision: https://reviews.llvm.org/D31102 llvm-svn: 298393
2017-03-21 17:57:19 +01:00
bool isIntDivCheap(EVT VT, AttributeList Attr) const override;
[AArch64] Do not lower scalar sdiv/udiv to a shifts + mul sequence when optimizing for minsize Mimic what x86 does when optimizing sdiv/udiv for minsize. llvm-svn: 264606
2016-03-28 20:17:07 +02:00
Avoid store merge to f128 in context of noimpiccitfloat NFCI. Prevent store merge from merging stores into an invalid 128-bit store (realized as a f128 value in the context of the noimplicitfloat attribute). Previously, such stores are immediately split back into valid stores. llvm-svn: 308184
2017-07-17 17:09:47 +02:00
bool canMergeStoresTo(unsigned AddressSpace, EVT MemVT,
const SelectionDAG &DAG) const override {
// Do not merge to float value size (128 bytes) if no implicit
// float attribute is set.
MachineFunction: Return reference from getFunction(); NFC The Function can never be nullptr so we can return a reference. llvm-svn: 320884
2017-12-15 23:22:58 +01:00
bool NoFloat = DAG.getMachineFunction().getFunction().hasFnAttribute(
Avoid store merge to f128 in context of noimpiccitfloat NFCI. Prevent store merge from merging stores into an invalid 128-bit store (realized as a f128 value in the context of the noimplicitfloat attribute). Previously, such stores are immediately split back into valid stores. llvm-svn: 308184
2017-07-17 17:09:47 +02:00
Attribute::NoImplicitFloat);
if (NoFloat)
return (MemVT.getSizeInBits() <= 64);
return true;
}
[AArch64] add overrides for isCheapToSpeculateCttz() and isCheapToSpeculateCtlz() AArch64 has instructions for efficient count-leading/trailing-zeros, so this should be considered a cheap operation (and therefore fair game for speculation) for any AArch64 implementation. The net result of allowing this speculation for the regression tests in this patch is that we get this code: ctlz: clz w0, w0 ret cttz: rbit w8, w0 clz w0, w8 ret Instead of: ctlz: cbz w0, .LBB0_2 clz w0, w0 ret .LBB0_2: orr w0, wzr, #0x20 ret cttz: cbz w0, .LBB1_2 rbit w8, w0 clz w0, w8 ret .LBB1_2: orr w0, wzr, #0x20 ret See D14469 for the larger motivation. Differential Revision: http://reviews.llvm.org/D14505 llvm-svn: 252625
2015-11-10 19:11:37 +01:00
bool isCheapToSpeculateCttz() const override {
return true;
}
bool isCheapToSpeculateCtlz() const override {
return true;
}
transform obscured FP sign bit ops into a fabs/fneg using TLI hook This is effectively a revert of: http://reviews.llvm.org/rL249702 - [InstCombine] transform masking off of an FP sign bit into a fabs() intrinsic call (PR24886) and: http://reviews.llvm.org/rL249701 - [ValueTracking] teach computeKnownBits that a fabs() clears sign bits and a reimplementation as a DAG combine for targets that have IEEE754-compliant fabs/fneg instructions. This is intended to resolve the objections raised on the dev list: http://lists.llvm.org/pipermail/llvm-dev/2016-April/098154.html and: https://llvm.org/bugs/show_bug.cgi?id=24886#c4 In the interest of patch minimalism, I've only partly enabled AArch64. PowerPC, MIPS, x86 and others can enable later. Differential Revision: http://reviews.llvm.org/D19391 llvm-svn: 271573
2016-06-02 22:01:37 +02:00
[CodeGenPrepare] Sink and duplicate more 'and' instructions. Summary: Rework the code that was sinking/duplicating (icmp and, 0) sequences into blocks where they were being used by conditional branches to form more tbz instructions on AArch64. The new code is more general in that it just looks for 'and's that have all icmp 0's as users, with a target hook used to select which subset of 'and' instructions to consider. This change also enables 'and' sinking for X86, where it is more widely beneficial than on AArch64. The 'and' sinking/duplicating code is moved into the optimizeInst phase of CodeGenPrepare, where it can take advantage of the fact the OptimizeCmpExpression has already sunk/duplicated any icmps into the blocks where they are used. One minor complication from this change is that optimizeLoadExt needed to be updated to always mark 'and's it has determined should be in the same block as their feeding load in the InsertedInsts set to avoid an infinite loop of hoisting and sinking the same 'and'. This change fixes a regression on X86 in the tsan runtime caused by moving GVNHoist to a later place in the optimization pipeline (see PR31382). Reviewers: t.p.northover, qcolombet, MatzeB Subscribers: aemerson, mcrosier, sebpop, llvm-commits Differential Revision: https://reviews.llvm.org/D28813 llvm-svn: 295746
2017-02-21 19:53:14 +01:00
bool isMaskAndCmp0FoldingBeneficial(const Instruction &AndI) const override;
[DAGCombine][X86][AArch64] Masked merge unfolding: vector edition. Summary: This **appears** to be the last missing piece for the masked merge pattern handling in the backend. This is [[ https://bugs.llvm.org/show_bug.cgi?id=37104 | PR37104 ]]. [[ https://bugs.llvm.org/show_bug.cgi?id=6773 | PR6773 ]] will introduce an IR canonicalization that is likely bad for the end assembly. Previously, `andps`+`andnps` / `bsl` would be generated. (see `@out`) Now, they would no longer be generated (see `@in`), and we need to make sure that they are generated. Differential Revision: https://reviews.llvm.org/D46528 llvm-svn: 332904
2018-05-21 23:41:02 +02:00
bool hasAndNotCompare(SDValue V) const override {
// We can use bics for any scalar.
return V.getValueType().isScalarInteger();
}
bool hasAndNot(SDValue Y) const override {
EVT VT = Y.getValueType();
if (!VT.isVector())
return hasAndNotCompare(Y);
return VT.getSizeInBits() >= 64; // vector 'bic'
[AArch64] allow and-not-compare transform to form 'bics' This target hook was added with D19087: https://reviews.llvm.org/D19087 Differential Revision: https://reviews.llvm.org/D27221 llvm-svn: 288206
2016-11-29 23:28:58 +01:00
}
[Codegen] (X & (C l>>/<< Y)) ==/!= 0 --> ((X <</l>> Y) & C) ==/!= 0 fold Summary: This was originally reported in D62818. https://rise4fun.com/Alive/oPH InstCombine does the opposite fold, in hope that `C l>>/<< Y` expression will be hoisted out of a loop if `Y` is invariant and `X` is not. But as it is seen from the diffs here, if it didn't get hoisted, the produced assembly is almost universally worse. Much like with my recent "hoist add/sub by/from const" patches, we should get almost universal win if we hoist constant, there is almost always an "and/test by imm" instruction, but "shift of imm" not so much, so we may avoid having to materialize the immediate, and thus need one less register. And since we now shift not by constant, but by something else, the live-range of that something else may reduce. Special care needs to be applied not to disturb x86 `BT` / hexagon `tstbit` instruction pattern. And to not get into endless combine loop. Reviewers: RKSimon, efriedma, t.p.northover, craig.topper, spatel, arsenm Reviewed By: spatel Subscribers: hiraditya, MaskRay, wuzish, xbolva00, nikic, nemanjai, jvesely, wdng, nhaehnle, javed.absar, tpr, kristof.beyls, jsji, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62871 llvm-svn: 366955
2019-07-25 00:57:22 +02:00
bool shouldProduceAndByConstByHoistingConstFromShiftsLHSOfAnd(
SDValue X, ConstantSDNode *XC, ConstantSDNode *CC, SDValue Y,
unsigned OldShiftOpcode, unsigned NewShiftOpcode,
SelectionDAG &DAG) const override;
[SelectionDAG] Codesize: don't expand SHIFT to SHIFT_PARTS And instead just generate a libcall. My motivating example on ARM was a simple: shl i64 %A, %B for which the code bloat is quite significant. For other targets that also accept __int128/i128 such as AArch64 and X86, it is also beneficial for these cases to generate a libcall when optimising for minsize. On these 64-bit targets, the 64-bits shifts are of course unaffected because the SHIFT/SHIFT_PARTS lowering operation action is not set to custom/expand. Differential Revision: https://reviews.llvm.org/D57386 llvm-svn: 352736
2019-01-31 09:07:30 +01:00
bool shouldExpandShift(SelectionDAG &DAG, SDNode *N) const override {
[IR] Refactor attribute methods in Function class (NFC) Rename the functions that query the optimization kind attributes. Differential revision: https://reviews.llvm.org/D60287 llvm-svn: 357731
2019-04-05 00:40:06 +02:00
if (DAG.getMachineFunction().getFunction().hasMinSize())
[SelectionDAG] Codesize: don't expand SHIFT to SHIFT_PARTS And instead just generate a libcall. My motivating example on ARM was a simple: shl i64 %A, %B for which the code bloat is quite significant. For other targets that also accept __int128/i128 such as AArch64 and X86, it is also beneficial for these cases to generate a libcall when optimising for minsize. On these 64-bit targets, the 64-bits shifts are of course unaffected because the SHIFT/SHIFT_PARTS lowering operation action is not set to custom/expand. Differential Revision: https://reviews.llvm.org/D57386 llvm-svn: 352736
2019-01-31 09:07:30 +01:00
return false;
return true;
}
[X86][AArch64][DAGCombine] Unfold 'check for [no] signed truncation' pattern Summary: [[ https://bugs.llvm.org/show_bug.cgi?id=38149 | PR38149 ]] As discussed in https://reviews.llvm.org/D49179#1158957 and later, the IR for 'check for [no] signed truncation' pattern can be improved: https://rise4fun.com/Alive/gBf ^ that pattern will be produced by Implicit Integer Truncation sanitizer, https://reviews.llvm.org/D48958 https://bugs.llvm.org/show_bug.cgi?id=21530 in signed case, therefore it is probably a good idea to improve it. But the IR-optimal patter does not lower efficiently, so we want to undo it.. This handles the simple pattern. There is a second pattern with predicate and constants inverted. NOTE: we do not check uses here. we always do the transform. Reviewers: spatel, craig.topper, RKSimon, javed.absar Reviewed By: spatel Subscribers: kristof.beyls, llvm-commits Differential Revision: https://reviews.llvm.org/D49266 llvm-svn: 337166
2018-07-16 14:44:10 +02:00
bool shouldTransformSignedTruncationCheck(EVT XVT,
unsigned KeptBits) const override {
// For vectors, we don't have a preference..
if (XVT.isVector())
return false;
auto VTIsOk = [](EVT VT) -> bool {
return VT == MVT::i8 || VT == MVT::i16 || VT == MVT::i32 ||
VT == MVT::i64;
};
// We are ok with KeptBitsVT being byte/word/dword, what SXT supports.
// XVT will be larger than KeptBitsVT.
MVT KeptBitsVT = MVT::getIntegerVT(KeptBits);
return VTIsOk(XVT) && VTIsOk(KeptBitsVT);
}
[Codegen][X86][AArch64][ARM][PowerPC] Inc-of-add vs sub-of-not (PR42457) Summary: This is the backend part of [[ https://bugs.llvm.org/show_bug.cgi?id=42457 | PR42457 ]]. In middle-end, we'd want to prefer the form with two adds - D63992, but as this diff shows, not every target will prefer that pattern. Out of 4 targets for which i added tests all seem to be ok with inc-of-add for scalars, but only X86 prefer that same pattern for vectors. Here i'm adding a new TLI hook, always defaulting to the inc-of-add, but adding AArch64,ARM,PowerPC overrides to prefer inc-of-add only for scalars. Reviewers: spatel, RKSimon, efriedma, t.p.northover, hfinkel Reviewed By: efriedma Subscribers: nemanjai, javed.absar, kristof.beyls, kbarton, jsji, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D64090 llvm-svn: 365010
2019-07-03 11:41:35 +02:00
bool preferIncOfAddToSubOfNot(EVT VT) const override;
transform obscured FP sign bit ops into a fabs/fneg using TLI hook This is effectively a revert of: http://reviews.llvm.org/rL249702 - [InstCombine] transform masking off of an FP sign bit into a fabs() intrinsic call (PR24886) and: http://reviews.llvm.org/rL249701 - [ValueTracking] teach computeKnownBits that a fabs() clears sign bits and a reimplementation as a DAG combine for targets that have IEEE754-compliant fabs/fneg instructions. This is intended to resolve the objections raised on the dev list: http://lists.llvm.org/pipermail/llvm-dev/2016-April/098154.html and: https://llvm.org/bugs/show_bug.cgi?id=24886#c4 In the interest of patch minimalism, I've only partly enabled AArch64. PowerPC, MIPS, x86 and others can enable later. Differential Revision: http://reviews.llvm.org/D19391 llvm-svn: 271573
2016-06-02 22:01:37 +02:00
bool hasBitPreservingFPLogic(EVT VT) const override {
// FIXME: Is this always true? It should be true for vectors at least.
return VT == MVT::f32 || VT == MVT::f64;
}
CXX_FAST_TLS calling convention: performance improvement for AArch64. The access function has a short entry and a short exit, the initialization block is only run the first time. To improve the performance, we want to have a short frame at the entry and exit. We explicitly handle most of the CSRs via copies. Only the CSRs that are not handled via copies will be in CSR_SaveList. Frame lowering and prologue/epilogue insertion will generate a short frame in the entry and exit according to CSR_SaveList. The majority of the CSRs will be handled by register allcoator. Register allocator will try to spill and reload them in the initialization block. We add CSRsViaCopy, it will be explicitly handled during lowering. 1> we first set FunctionLoweringInfo->SplitCSR if conditions are met (the target supports it for the given machine function and the function has only return exits). We also call TLI->initializeSplitCSR to perform initialization. 2> we call TLI->insertCopiesSplitCSR to insert copies from CSRsViaCopy to virtual registers at beginning of the entry block and copies from virtual registers to CSRsViaCopy at beginning of the exit blocks. 3> we also need to make sure the explicit copies will not be eliminated. The target independent portion was committed as r255353. rdar://problem/23557469 Differential Revision: http://reviews.llvm.org/D15341 llvm-svn: 255821
2015-12-16 22:04:19 +01:00
bool supportSplitCSR(MachineFunction *MF) const override {
MachineFunction: Return reference from getFunction(); NFC The Function can never be nullptr so we can return a reference. llvm-svn: 320884
2017-12-15 23:22:58 +01:00
return MF->getFunction().getCallingConv() == CallingConv::CXX_FAST_TLS &&
MF->getFunction().hasFnAttribute(Attribute::NoUnwind);
CXX_FAST_TLS calling convention: performance improvement for AArch64. The access function has a short entry and a short exit, the initialization block is only run the first time. To improve the performance, we want to have a short frame at the entry and exit. We explicitly handle most of the CSRs via copies. Only the CSRs that are not handled via copies will be in CSR_SaveList. Frame lowering and prologue/epilogue insertion will generate a short frame in the entry and exit according to CSR_SaveList. The majority of the CSRs will be handled by register allcoator. Register allocator will try to spill and reload them in the initialization block. We add CSRsViaCopy, it will be explicitly handled during lowering. 1> we first set FunctionLoweringInfo->SplitCSR if conditions are met (the target supports it for the given machine function and the function has only return exits). We also call TLI->initializeSplitCSR to perform initialization. 2> we call TLI->insertCopiesSplitCSR to insert copies from CSRsViaCopy to virtual registers at beginning of the entry block and copies from virtual registers to CSRsViaCopy at beginning of the exit blocks. 3> we also need to make sure the explicit copies will not be eliminated. The target independent portion was committed as r255353. rdar://problem/23557469 Differential Revision: http://reviews.llvm.org/D15341 llvm-svn: 255821
2015-12-16 22:04:19 +01:00
}
void initializeSplitCSR(MachineBasicBlock *Entry) const override;
void insertCopiesSplitCSR(
MachineBasicBlock *Entry,
const SmallVectorImpl<MachineBasicBlock *> &Exits) const override;
[AArch64] add overrides for isCheapToSpeculateCttz() and isCheapToSpeculateCtlz() AArch64 has instructions for efficient count-leading/trailing-zeros, so this should be considered a cheap operation (and therefore fair game for speculation) for any AArch64 implementation. The net result of allowing this speculation for the regression tests in this patch is that we get this code: ctlz: clz w0, w0 ret cttz: rbit w8, w0 clz w0, w8 ret Instead of: ctlz: cbz w0, .LBB0_2 clz w0, w0 ret .LBB0_2: orr w0, wzr, #0x20 ret cttz: cbz w0, .LBB1_2 rbit w8, w0 clz w0, w8 ret .LBB1_2: orr w0, wzr, #0x20 ret See D14469 for the larger motivation. Differential Revision: http://reviews.llvm.org/D14505 llvm-svn: 252625
2015-11-10 19:11:37 +01:00
Swift Calling Convention: swifterror target support. Differential Revision: http://reviews.llvm.org/D18716 llvm-svn: 265997
2016-04-11 23:08:06 +02:00
bool supportSwiftError() const override {
return true;
}
[AArch64] Enable aggressive FMA on T99 and provide AArch64 options for others. This patch enables aggressive FMA by default on T99, and provides a -mllvm option to enable the same on other AArch64 micro-arch's (-mllvm -aarch64-enable-aggressive-fma). Test case demonstrating the effects on T99 is included. Patch by: steleman (Stefan Teleman) Differential Revision: https://reviews.llvm.org/D40696 llvm-svn: 323474
2018-01-25 22:55:39 +01:00
/// Enable aggressive FMA fusion on targets that want it.
bool enableAggressiveFMAFusion(EVT VT) const override;
GlobalISel: translate @llvm.va_start intrinsic. Because we need to preserve the memory access being performed we need a separate instruction to represent this. llvm-svn: 294492
2017-02-08 18:57:20 +01:00
/// Returns the size of the platform's va_list object.
unsigned getVaListSizeInBits(const DataLayout &DL) const override;
[ARM/AArch64] Ensure valid vector element types for interleaved accesses This patch refactors and strengthens the type checks performed for interleaved accesses. The primary functional change is to ensure that the interleaved accesses have valid element types. The added test cases previously failed because the element type is f128. Differential Revision: https://reviews.llvm.org/D31817 llvm-svn: 299864
2017-04-10 20:34:37 +02:00
/// Returns true if \p VecTy is a legal interleaved access type. This
/// function checks the vector element type and the overall width of the
/// vector.
bool isLegalInterleavedAccessType(VectorType *VecTy,
const DataLayout &DL) const;
/// Returns the number of interleaved accesses that will be generated when
/// lowering accesses of the given type.
unsigned getNumInterleavedAccesses(VectorType *VecTy,
const DataLayout &DL) const;
[AArch64][Falkor] Avoid HW prefetcher tag collisions (step 1) Summary: This patch is the first step in reducing HW prefetcher instruction tag collisions in inner loops for Falkor. It adds a pass that annotates IR loads with metadata to indicate that they are known to be strided loads, and adds a target lowering hook that translates this metadata to a target-specific MachineMemOperand flag. A follow on change will use this MachineMemOperand flag to re-write instructions to reduce tag collisions. Reviewers: mcrosier, t.p.northover Subscribers: aemerson, rengolin, mgorny, javed.absar, kristof.beyls, llvm-commits Differential Revision: https://reviews.llvm.org/D34963 llvm-svn: 308059
2017-07-14 23:44:12 +02:00
MachineMemOperand::Flags getMMOFlags(const Instruction &I) const override;
GlobalISel (AArch64): fix ABI at border between GPRs and SP. If a struct would end up half in GPRs and half on SP the ABI says it should actually go entirely on the stack. We were getting this wrong in GlobalISel before, causing compatibility issues. llvm-svn: 311388
2017-08-21 23:56:11 +02:00
bool functionArgumentNeedsConsecutiveRegisters(Type *Ty,
CallingConv::ID CallConv,
bool isVarArg) const override;
[ARM64] [Windows] Handle funclets This patch adds support for funclets in frame lowering and ISel lowering. Together with D50288 and D50166, it enables C++ exception handling. Patch by Sanjin Sijaric, with some fixes by me. Differential Revision: https://reviews.llvm.org/D51524 llvm-svn: 346568
2018-11-10 00:33:30 +01:00
/// Used for exception handling on Win64.
bool needsFixedCatchObjects() const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
private:
don't repeat function names in comments; NFC llvm-svn: 252502
2015-11-09 20:18:26 +01:00
/// Keep a pointer to the AArch64Subtarget around so that we can
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
/// make the right decision when generating code for different targets.
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 14:50:23 +02:00
const AArch64Subtarget *Subtarget;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[AArch64] Fix PR32384: bump up the number of stores per memset and memcpy As suggested in https://bugs.llvm.org/show_bug.cgi?id=32384#c1, this change makes the inlining of `memset()` and `memcpy()` more aggressive when compiling for speed. The tuning remains the same when optimizing for size. Patch by: Sebastian Pop <s.pop@samsung.com> Evandro Menezes <e.menezes@samsung.com> Differential revision: https://reviews.llvm.org/D45098 llvm-svn: 333429
2018-05-29 17:58:50 +02:00
bool isExtFreeImpl(const Instruction *Ext) const override;
Use MVT instead of EVT to remove a bunch of unnecessary calls to getSimpleVT. llvm-svn: 266414
2016-04-15 08:20:21 +02:00
void addTypeForNEON(MVT VT, MVT PromotedBitwiseVT);
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
void addDRTypeForNEON(MVT VT);
void addQRTypeForNEON(MVT VT);
Pass DebugLoc and SDLoc by const ref. This used to be free, copying and moving DebugLocs became expensive after the metadata rewrite. Passing by reference eliminates a ton of track/untrack operations. No functionality change intended. llvm-svn: 272512
2016-06-12 17:39:02 +02:00
SDValue LowerFormalArguments(SDValue Chain, CallingConv::ID CallConv,
bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
const SDLoc &DL, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
SDValue LowerCall(CallLoweringInfo & /*CLI*/,
SmallVectorImpl<SDValue> &InVals) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
SDValue LowerCallResult(SDValue Chain, SDValue InFlag,
CallingConv::ID CallConv, bool isVarArg,
Pass DebugLoc and SDLoc by const ref. This used to be free, copying and moving DebugLocs became expensive after the metadata rewrite. Passing by reference eliminates a ton of track/untrack operations. No functionality change intended. llvm-svn: 272512
2016-06-12 17:39:02 +02:00
const SmallVectorImpl<ISD::InputArg> &Ins,
const SDLoc &DL, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals, bool isThisReturn,
SDValue ThisVal) const;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[AArch64] Add custom lowering for v4i8 trunc store This patch adds a custom trunc store lowering for v4i8 vector types. Since there is not v.4b register, the v4i8 is promoted to v4i16 (v.4h) and default action for v4i8 is to extract each element and issue 4 byte stores. A better strategy would be to extended the promoted v4i16 to v8i16 (with undef elements) and extract and store the word lane which represents the v4i8 subvectores. The construction: define void @foo(<4 x i16> %x, i8* nocapture %p) { %0 = trunc <4 x i16> %x to <4 x i8> %1 = bitcast i8* %p to <4 x i8>* store <4 x i8> %0, <4 x i8>* %1, align 4, !tbaa !2 ret void } Can be optimized from: umov w8, v0.h[3] umov w9, v0.h[2] umov w10, v0.h[1] umov w11, v0.h[0] strb w8, [x0, #3] strb w9, [x0, #2] strb w10, [x0, #1] strb w11, [x0] ret To: xtn v0.8b, v0.8h str s0, [x0] ret The patch also adjust the memory cost for autovectorization, so the C code: void foo (const int *src, int width, unsigned char *dst) { for (int i = 0; i < width; i++) *dst++ = *src++; } can be vectorized to: .LBB0_4: // %vector.body // =>This Inner Loop Header: Depth=1 ldr q0, [x0], #16 subs x12, x12, #4 // =4 xtn v0.4h, v0.4s xtn v0.8b, v0.8h st1 { v0.s }[0], [x2], #4 b.ne .LBB0_4 Instead of byte operations. llvm-svn: 335735
2018-06-27 15:58:46 +02:00
SDValue LowerSTORE(SDValue Op, SelectionDAG &DAG) const;
Implement __builtin_thread_pointer This path add the aarch64 lowering of __builtin_thread_pointer. It uses the already implemented AArch64ISD::THREAD_POINTER used in TLS generation. llvm-svn: 243412
2015-07-28 15:03:31 +02:00
SDValue LowerINTRINSIC_WO_CHAIN(SDValue Op, SelectionDAG &DAG) const;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
bool isEligibleForTailCallOptimization(
SDValue Callee, CallingConv::ID CalleeCC, bool isVarArg,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins, SelectionDAG &DAG) const;
[ARM64] Support aggressive fastcc/tailcallopt breaking ABI by popping out argument stack from callee. llvm-svn: 208837
2014-05-15 03:33:17 +02:00
/// Finds the incoming stack arguments which overlap the given fixed stack
/// object and incorporates their load into the current chain. This prevents
/// an upcoming store from clobbering the stack argument before it's used.
SDValue addTokenForArgument(SDValue Chain, SelectionDAG &DAG,
MachineFunction: Return reference for getFrameInfo(); NFC getFrameInfo() never returns nullptr so we should use a reference instead of a pointer. llvm-svn: 277017
2016-07-28 20:40:00 +02:00
MachineFrameInfo &MFI, int ClobberedFI) const;
[ARM64] Support aggressive fastcc/tailcallopt breaking ABI by popping out argument stack from callee. llvm-svn: 208837
2014-05-15 03:33:17 +02:00
bool DoesCalleeRestoreStack(CallingConv::ID CallCC, bool TailCallOpt) const;
Pass DebugLoc and SDLoc by const ref. This used to be free, copying and moving DebugLocs became expensive after the metadata rewrite. Passing by reference eliminates a ton of track/untrack operations. No functionality change intended. llvm-svn: 272512
2016-06-12 17:39:02 +02:00
void saveVarArgRegisters(CCState &CCInfo, SelectionDAG &DAG, const SDLoc &DL,
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
SDValue &Chain) const;
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
bool CanLowerReturn(CallingConv::ID CallConv, MachineFunction &MF,
bool isVarArg,
const SmallVectorImpl<ISD::OutputArg> &Outs,
LLVMContext &Context) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
SDValue LowerReturn(SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::OutputArg> &Outs,
Pass DebugLoc and SDLoc by const ref. This used to be free, copying and moving DebugLocs became expensive after the metadata rewrite. Passing by reference eliminates a ton of track/untrack operations. No functionality change intended. llvm-svn: 272512
2016-06-12 17:39:02 +02:00
const SmallVectorImpl<SDValue> &OutVals, const SDLoc &DL,
ARM64: override all the things. Actually, mostly only those in the top-level directory that already had a "virtual" attached. But it's the thought that counts and it's been a long day. llvm-svn: 205131
2014-03-30 09:25:18 +02:00
SelectionDAG &DAG) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[AArch64] Refactor instruction selection lowering for addresses. NFCI Factor out the common code used for generating addresses into common templated functions that call overloaded versions of a new function, getTargetNode. Tested with make check-llvm with targets AArch64. Differential Revision: https://reviews.llvm.org/D32169 llvm-svn: 301005
2017-04-21 19:31:03 +02:00
SDValue getTargetNode(GlobalAddressSDNode *N, EVT Ty, SelectionDAG &DAG,
unsigned Flag) const;
SDValue getTargetNode(JumpTableSDNode *N, EVT Ty, SelectionDAG &DAG,
unsigned Flag) const;
SDValue getTargetNode(ConstantPoolSDNode *N, EVT Ty, SelectionDAG &DAG,
unsigned Flag) const;
SDValue getTargetNode(BlockAddressSDNode *N, EVT Ty, SelectionDAG &DAG,
unsigned Flag) const;
template <class NodeTy>
[AArch64] Add support for dllimport of values and functions Previously, the dllimport attribute did the right thing in terms of treating it as a pointer to a value, but this makes sure the names get mangled properly, and calls to such functions load the function from the __imp_ pointer. This is based on SVN r212431 and r212430 where the same was implemented for ARM. Differential Revision: https://reviews.llvm.org/D38530 llvm-svn: 316555
2017-10-25 09:25:18 +02:00
SDValue getGOT(NodeTy *N, SelectionDAG &DAG, unsigned Flags = 0) const;
template <class NodeTy>
SDValue getAddrLarge(NodeTy *N, SelectionDAG &DAG, unsigned Flags = 0) const;
template <class NodeTy>
SDValue getAddr(NodeTy *N, SelectionDAG &DAG, unsigned Flags = 0) const;
[AArch64] Add Tiny Code Model for AArch64 This adds the plumbing for the Tiny code model for the AArch64 backend. This, instead of loading addresses through the normal ADRP;ADD pair used in the Small model, uses a single ADR. The 21 bit range of an ADR means that the code and its statically defined symbols need to be within 1MB of each other. This makes it mostly interesting for embedded applications where we want to fit as much as we can in as small a space as possible. Differential Revision: https://reviews.llvm.org/D49673 llvm-svn: 340397
2018-08-22 13:31:39 +02:00
template <class NodeTy>
SDValue getAddrTiny(NodeTy *N, SelectionDAG &DAG, unsigned Flags = 0) const;
[hwasan] Stack instrumentation. Summary: Very basic stack instrumentation using tagged pointers. Tag for N'th alloca in a function is built as XOR of: * base tag for the function, which is just some bits of SP (poor man's random) * small constant which is a function of N. Allocas are aligned to 16 bytes. On every ReturnInst allocas are re-tagged to catch use-after-return. This implementation has a bunch of issues that will be taken care of later: 1. lifetime intrinsics referring to tagged pointers are not recognized in SDAG. This effectively disables stack coloring. 2. Generated code is quite inefficient. There is one extra instruction at each memory access that adds the base tag to the untagged alloca address. It would be better to keep tagged SP in a callee-saved register and address allocas as an offset of that XOR retag, but that needs better coordination between hwasan instrumentation pass and prologue/epilogue insertion. 3. Lifetime instrinsics are ignored and use-after-scope is not implemented. This would be harder to do than in ASan, because we need to use a differently tagged pointer depending on which lifetime.start / lifetime.end the current instruction is dominated / post-dominated. Reviewers: kcc, alekseyshl Subscribers: srhines, kubamracek, javed.absar, hiraditya, llvm-commits Differential Revision: https://reviews.llvm.org/D41602 llvm-svn: 322324
2018-01-11 23:53:30 +01:00
SDValue LowerADDROFRETURNADDR(SDValue Op, SelectionDAG &DAG) const;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
SDValue LowerGlobalAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerDarwinGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerELFGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
Pass DebugLoc and SDLoc by const ref. This used to be free, copying and moving DebugLocs became expensive after the metadata rewrite. Passing by reference eliminates a ton of track/untrack operations. No functionality change intended. llvm-svn: 272512
2016-06-12 17:39:02 +02:00
SDValue LowerELFTLSDescCallSeq(SDValue SymAddr, const SDLoc &DL,
Fix PR22408 - LLVM producing AArch64 TLS relocations that GNU linkers cannot handle yet. As is described at http://llvm.org/bugs/show_bug.cgi?id=22408, the GNU linkers ld.bfd and ld.gold currently only support a subset of the whole range of AArch64 ELF TLS relocations. Furthermore, they assume that some of the code sequences to access thread-local variables are produced in a very specific sequence. When the sequence is not as the linker expects, it can silently mis-relaxe/mis-optimize the instructions. Even if that wouldn't be the case, it's good to produce the exact sequence, as that ensures that linkers can perform optimizing relaxations. This patch: * implements support for 16MiB TLS area size instead of 4GiB TLS area size. Ideally clang would grow an -mtls-size option to allow support for both, but that's not part of this patch. * by default doesn't produce local dynamic access patterns, as even modern ld.bfd and ld.gold linkers do not support the associated relocations. An option (-aarch64-elf-ldtls-generation) is added to enable generation of local dynamic code sequence, but is off by default. * makes sure that the exact expected code sequence for local dynamic and general dynamic accesses is produced, by making use of a new pseudo instruction. The patch also removes two (AArch64ISD::TLSDESC_BLR, AArch64ISD::TLSDESC_CALL) pre-existing AArch64-specific pseudo SDNode instructions that are superseded by the new one (TLSDESC_CALLSEQ). llvm-svn: 231227
2015-03-04 10:12:08 +01:00
SelectionDAG &DAG) const;
[AArch64] Implement native TLS for Windows Differential Revision: https://reviews.llvm.org/D43971 llvm-svn: 327220
2018-03-10 20:05:21 +01:00
SDValue LowerWindowsGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
SDValue LowerSETCC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBR_CC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSELECT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const;
AArch64: Don't lower ISD::SELECT to ISD::SELECT_CC Instead of lowering SELECT to SELECT_CC which is further lowered later immediately call the SELECT_CC lowering code. This is preferable because: - Avoids an unnecessary roundtrip through the legalization queues with an intermediate node. - More importantly: Lowered operations get visited last leading to SELECT_CC getting visited with legalized operands and unlegalized ones for preexisting SELECT_CC nodes. This does not hurt the current code (hence no testcase) but is required for another patch I am working on. Differential Revision: http://reviews.llvm.org/D8187 llvm-svn: 234334
2015-04-07 19:33:05 +02:00
SDValue LowerSELECT_CC(ISD::CondCode CC, SDValue LHS, SDValue RHS,
Pass DebugLoc and SDLoc by const ref. This used to be free, copying and moving DebugLocs became expensive after the metadata rewrite. Passing by reference eliminates a ton of track/untrack operations. No functionality change intended. llvm-svn: 272512
2016-06-12 17:39:02 +02:00
SDValue TVal, SDValue FVal, const SDLoc &dl,
AArch64: Don't lower ISD::SELECT to ISD::SELECT_CC Instead of lowering SELECT to SELECT_CC which is further lowered later immediately call the SELECT_CC lowering code. This is preferable because: - Avoids an unnecessary roundtrip through the legalization queues with an intermediate node. - More importantly: Lowered operations get visited last leading to SELECT_CC getting visited with legalized operands and unlegalized ones for preexisting SELECT_CC nodes. This does not hurt the current code (hence no testcase) but is required for another patch I am working on. Differential Revision: http://reviews.llvm.org/D8187 llvm-svn: 234334
2015-04-07 19:33:05 +02:00
SelectionDAG &DAG) const;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
SDValue LowerJumpTable(SDValue Op, SelectionDAG &DAG) const;
AArch64: add a pass to compress jump-table entries when possible. llvm-svn: 345188
2018-10-24 22:19:09 +02:00
SDValue LowerBR_JT(SDValue Op, SelectionDAG &DAG) const;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
SDValue LowerConstantPool(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBlockAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerAAPCS_VASTART(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerDarwin_VASTART(SDValue Op, SelectionDAG &DAG) const;
[AArch64] Implement support for windows style vararg functions Pass parameters properly in calls to such functions (pass all floats in integer registers), and handle va_start properly (allocate stack immediately below the arguments on the stack, to save the register arguments into a single continuous array). Differential Revision: https://reviews.llvm.org/D35006 llvm-svn: 307928
2017-07-13 19:03:12 +02:00
SDValue LowerWin64_VASTART(SDValue Op, SelectionDAG &DAG) const;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
SDValue LowerVASTART(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerVACOPY(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerVAARG(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFRAMEADDR(SDValue Op, SelectionDAG &DAG) const;
[COFF, ARM64] Implement Intrinsic.sponentry for AArch64 Summary: This patch adds Intrinsic.sponentry. This intrinsic is required to correctly support setjmp for AArch64 Windows platform. Patch by: Yin Ma (yinma@codeaurora.org) Reviewers: mgrang, ssijaric, eli.friedman, TomTan, mstorsjo, rnk, compnerd, efriedma Reviewed By: efriedma Subscribers: efriedma, javed.absar, kristof.beyls, chrib, llvm-commits Differential Revision: https://reviews.llvm.org/D53996 llvm-svn: 345909
2018-11-02 00:22:25 +01:00
SDValue LowerSPONENTRY(SDValue Op, SelectionDAG &DAG) const;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
SDValue LowerRETURNADDR(SDValue Op, SelectionDAG &DAG) const;
[AArch64] Implement FLT_ROUNDS macro. Very similar to ARM implementation, just maps to an MRS. Should fix PR25191. Patch by Michael Brase. llvm-svn: 335118
2018-06-20 14:09:01 +02:00
SDValue LowerFLT_ROUNDS_(SDValue Op, SelectionDAG &DAG) const;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
SDValue LowerINSERT_VECTOR_ELT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerEXTRACT_VECTOR_ELT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSCALAR_TO_VECTOR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBUILD_VECTOR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerEXTRACT_SUBVECTOR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerVectorSRA_SRL_SHL(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerShiftLeftParts(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerShiftRightParts(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerVSETCC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerCTPOP(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerF128Call(SDValue Op, SelectionDAG &DAG,
RTLIB::Libcall Call) const;
SDValue LowerFCOPYSIGN(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFP_EXTEND(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFP_ROUND(SDValue Op, SelectionDAG &DAG) const;
[AArch64] Improve FP16 instruction selection for vector round and vector conver from half instructions https://reviews.llvm.org/D58855 llvm-svn: 355545
2019-03-06 21:30:06 +01:00
SDValue LowerVectorFP_TO_INT(SDValue Op, SelectionDAG &DAG) const;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
SDValue LowerFP_TO_INT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerVectorOR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerCONCAT_VECTORS(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFSINCOS(SDValue Op, SelectionDAG &DAG) const;
Re-commit r302678, fixing PR33053. The issue was that the AArch64 TTI hook allowed unpacked integer cmp reductions which didn't have a lowering. llvm-svn: 303211
2017-05-16 23:29:22 +02:00
SDValue LowerVECREDUCE(SDValue Op, SelectionDAG &DAG) const;
[AArch64] Improve v8.1-A code-gen for atomic load-subtract Armv8.1-A added an atomic load-add instruction, but not a load-subtract instruction. Our current code-generation for atomic load-subtract always inserts a NEG instruction to negate it's argument, even if it could be folded into a constant or another instruction. This adds lowering early in selection DAG to convert a load-subtract operation into a subtract and a load-add, allowing the normal DAG optimisations to work on it. I've left the old tablegen patterns in because they are still needed for global isel. Some of the tests in this patch are copied from D35375 by Chad Rosier (which was abandoned). Differential revision: https://reviews.llvm.org/D42477 llvm-svn: 324892
2018-02-12 15:22:03 +01:00
SDValue LowerATOMIC_LOAD_SUB(SDValue Op, SelectionDAG &DAG) const;
[AArch64] Improve v8.1-A code-gen for atomic load-and Armv8.1-A added an atomic load-clear instruction (which performs bitwise and with the complement of it's operand), but not a load-and instruction. Our current code-generation for atomic load-and always inserts an MVN instruction to invert its argument, even if it could be folded into a constant or another instruction. This adds lowering early in selection DAG to convert a load-and operation into an xor with -1 and a load-clear, allowing the normal DAG optimisations to work on it. To do this, I've had to add a new ISD opcode, ATOMIC_LOAD_CLR. I don't see any easy way to do this with an AArch64-specific ISD node, because the code-generation for atomic operations assumes the SDNodes are of type AtomicSDNode. I've left the old tablegen patterns in because they are still needed for global isel. Differential revision: https://reviews.llvm.org/D42478 llvm-svn: 324908
2018-02-12 18:03:11 +01:00
SDValue LowerATOMIC_LOAD_AND(SDValue Op, SelectionDAG &DAG) const;
[AArch64] Implement dynamic stack probing for windows This makes sure that alloca() function calls properly probe the stack as needed. Differential Revision: https://reviews.llvm.org/D42356 llvm-svn: 325433
2018-02-17 15:26:32 +01:00
SDValue LowerDYNAMIC_STACKALLOC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerWindowsDYNAMIC_STACKALLOC(SDValue Op, SDValue Chain,
SDValue &Size,
SelectionDAG &DAG) const;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[AArch64] Lower sdiv x, pow2 using add + select + shift. The target-independent DAGcombiner will generate: asr w1, X, #31 w1 = splat sign bit. add X, X, w1, lsr #28 X = X + 0 or pow2-1 asr w0, X, asr #4 w0 = X/pow2 However, the add + shifts is expensive, so generate: add w0, X, 15 w0 = X + pow2-1 cmp X, wzr X - 0 csel X, w0, X, lt X = (X < 0) ? X + pow2-1 : X; asr w0, X, asr 4 w0 = X/pow2 llvm-svn: 213758
2014-07-23 16:57:52 +02:00
SDValue BuildSDIVPow2(SDNode *N, const APInt &Divisor, SelectionDAG &DAG,
[DAGCombiner][TargetLowering] Pass a SmallVector instead of a std::vector to BuildSDIV/BuildUDIV/etc. The vector contains the SDNodes that these functions create. The number of nodes is always a small number so we should use SmallVector to avoid a heap allocation. llvm-svn: 338329
2018-07-31 01:22:00 +02:00
SmallVectorImpl<SDNode *> &Created) const override;
[DAG Combiner] Fix the native computation of the Newton series for reciprocals The generic infrastructure to compute the Newton series for reciprocal and reciprocal square root was conceived to allow a target to compute the series itself. However, the original code did not properly consider this condition if returned by a target. This patch addresses the issues to allow a target to compute the series on its own. Differential revision: https://reviews.llvm.org/D22975 llvm-svn: 286523
2016-11-11 00:31:06 +01:00
SDValue getSqrtEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled,
int &ExtraSteps, bool &UseOneConst,
bool Reciprocal) const override;
[AArch64] Optionally use the Newton series for reciprocal estimation Add support for estimating the square root or its reciprocal and division or reciprocal using the combiner generic Newton series. Differential revision: https://reviews.llvm.org/D25291 llvm-svn: 284986
2016-10-24 18:14:58 +02:00
SDValue getRecipEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled,
int &ExtraSteps) const override;
fix TLI's combineRepeatedFPDivisors interface to return the minimum user threshold This fix was suggested as part of D11345 and is part of fixing PR24141. With this change, we can avoid walking the uses of a divisor node if the target doesn't want the combineRepeatedFPDivisors transform in the first place. There is no NFC-intended other than that. Differential Revision: http://reviews.llvm.org/D11531 llvm-svn: 243498
2015-07-29 01:05:48 +02:00
unsigned combineRepeatedFPDivisors() const override;
[AArch64] Lower sdiv x, pow2 using add + select + shift. The target-independent DAGcombiner will generate: asr w1, X, #31 w1 = splat sign bit. add X, X, w1, lsr #28 X = X + 0 or pow2-1 asr w0, X, asr #4 w0 = X/pow2 However, the add + shifts is expensive, so generate: add w0, X, 15 w0 = X + pow2-1 cmp X, wzr X - 0 csel X, w0, X, lt X = (X < 0) ? X + pow2-1 : X; asr w0, X, asr 4 w0 = X/pow2 llvm-svn: 213758
2014-07-23 16:57:52 +02:00
[TargetLowering] StringRefize asm constraint getters. There is some functional change here because it changes target code from atoi(3) to StringRef::getAsInteger which has error checking. For valid constraints there should be no difference. llvm-svn: 241411
2015-07-05 21:29:18 +02:00
ConstraintType getConstraintType(StringRef Constraint) const override;
Allow {e,r}bp as the target of {read,write}_register. This patch allows the read_register and write_register intrinsics to read/write the RBP/EBP registers on X86 iff the targeted register is the frame pointer for the containing function. Differential Revision: http://reviews.llvm.org/D10977 llvm-svn: 241827
2015-07-09 19:40:29 +02:00
unsigned getRegisterByName(const char* RegName, EVT VT,
SelectionDAG &DAG) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
/// Examine constraint string and operand type and determine a weight value.
/// The operand object must already have been set up with the operand type.
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. ARM64 edition llvm-svn: 207509
2014-04-29 09:58:25 +02:00
ConstraintWeight
getSingleConstraintMatchWeight(AsmOperandInfo &info,
const char *constraint) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
std::pair<unsigned, const TargetRegisterClass *>
getRegForInlineAsmConstraint wants to use TargetRegisterInfo for a lookup, pass that in rather than use a naked call to getSubtargetImpl. This involved passing down and around either a TargetMachine or TargetRegisterInfo. Update all callers/definitions around the targets and SelectionDAG. llvm-svn: 230699
2015-02-26 23:38:43 +01:00
getRegForInlineAsmConstraint(const TargetRegisterInfo *TRI,
[TargetLowering] StringRefize asm constraint getters. There is some functional change here because it changes target code from atoi(3) to StringRef::getAsInteger which has error checking. For valid constraints there should be no difference. llvm-svn: 241411
2015-07-05 21:29:18 +02:00
StringRef Constraint, MVT VT) const override;
[AArch64] Implement lowering of the X constraint on AArch64 Summary: This implements the lowering of the X constraint on AArch64. The default behaviour of the X constraint lowering is to restrict it to "f". This is a problem because the "f" constraint is not implemented on AArch64 and would be too restrictive anyway. Therefore, the AArch64 hook will lower this to "w" (if the operand is a floating point or vector) or "r" otherwise. The implementation is similar with the one added for ARM (r267411). This is the AArch64 side of the fix for http://llvm.org/PR26493 Reviewers: rengolin Subscribers: aemerson, rengolin, llvm-commits, t.p.northover Differential Revision: http://reviews.llvm.org/D19967 llvm-svn: 268907
2016-05-09 13:10:44 +02:00
const char *LowerXConstraint(EVT ConstraintVT) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
void LowerAsmOperandForConstraint(SDValue Op, std::string &Constraint,
std::vector<SDValue> &Ops,
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. ARM64 edition llvm-svn: 207509
2014-04-29 09:58:25 +02:00
SelectionDAG &DAG) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
[TargetLowering] StringRefize asm constraint getters. There is some functional change here because it changes target code from atoi(3) to StringRef::getAsInteger which has error checking. For valid constraints there should be no difference. llvm-svn: 241411
2015-07-05 21:29:18 +02:00
unsigned getInlineAsmMemConstraint(StringRef ConstraintCode) const override {
[aarch64] Distinguish the 'Q' and 'm' inline assembly memory constraints. Summary: But still handle them the same way since I don't know how they differ on this target. Clang also has code for 'Ump', 'Utf', 'Usa', and 'Ush' but calls llvm_unreachable() on this code path so they are not converted to a constraint id at the moment. No functional change intended. Reviewers: t.p.northover Subscribers: aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D8177 llvm-svn: 232941
2015-03-23 12:33:15 +01:00
if (ConstraintCode == "Q")
return InlineAsm::Constraint_Q;
// FIXME: clang has code for 'Ump', 'Utf', 'Usa', and 'Ush' but these are
// followed by llvm_unreachable so we'll leave them unimplemented in
// the backend for now.
return TargetLowering::getInlineAsmMemConstraint(ConstraintCode);
Make each target map all inline assembly memory constraints to InlineAsm::Constraint_m. NFC. Summary: This is instead of doing this in target independent code and is the last non-functional change before targets begin to distinguish between different memory constraints when selecting code for the ISD::INLINEASM node. Next, each target will individually move away from the idea that all memory constraints behave like 'm'. Subscribers: jholewinski, llvm-commits Differential Revision: http://reviews.llvm.org/D8173 llvm-svn: 232373
2015-03-16 14:13:41 +01:00
}
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. ARM64 edition llvm-svn: 207509
2014-04-29 09:58:25 +02:00
bool isUsedByReturnOnly(SDNode *N, SDValue &Chain) const override;
DAG: Make mayBeEmittedAsTailCall parameter const llvm-svn: 300603
2017-04-18 23:16:46 +02:00
bool mayBeEmittedAsTailCall(const CallInst *CI) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
bool getIndexedAddressParts(SDNode *Op, SDValue &Base, SDValue &Offset,
ISD::MemIndexedMode &AM, bool &IsInc,
SelectionDAG &DAG) const;
bool getPreIndexedAddressParts(SDNode *N, SDValue &Base, SDValue &Offset,
ISD::MemIndexedMode &AM,
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. ARM64 edition llvm-svn: 207509
2014-04-29 09:58:25 +02:00
SelectionDAG &DAG) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
bool getPostIndexedAddressParts(SDNode *N, SDNode *Op, SDValue &Base,
SDValue &Offset, ISD::MemIndexedMode &AM,
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. ARM64 edition llvm-svn: 207509
2014-04-29 09:58:25 +02:00
SelectionDAG &DAG) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
void ReplaceNodeResults(SDNode *N, SmallVectorImpl<SDValue> &Results,
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. ARM64 edition llvm-svn: 207509
2014-04-29 09:58:25 +02:00
SelectionDAG &DAG) const override;
AArch64: treat [N x Ty] as a block during procedure calls. The AAPCS treats small structs and homogeneous floating (or vector) aggregates specially, and guarantees they either get passed as a contiguous block of registers, or prevent any future use of those registers and get passed on the stack. This concept can fit quite neatly into LLVM's own type system, mapping an HFA to [N x float] and so on, and small structs to [N x i64]. Doing so allows front-ends to emit AAPCS compliant code without having to duplicate the register counting logic. llvm-svn: 222903
2014-11-27 22:02:42 +01:00
AArch64: Implement conditional compare sequence matching. This is a new iteration of the reverted r238793 / http://reviews.llvm.org/D8232 which wrongly assumed that any and/or trees can be represented by conditional compare sequences, however there are some restrictions to that. This version fixes this and adds comments that explain exactly what types of and/or trees can actually be implemented as conditional compare sequences. Related to http://llvm.org/PR20927, rdar://18326194 Differential Revision: http://reviews.llvm.org/D10579 llvm-svn: 242436
2015-07-16 22:02:37 +02:00
bool shouldNormalizeToSelectSequence(LLVMContext &, EVT) const override;
AArch64: Fix emergency spillslot being out of reach for large callframes Re-commit of r322200: The testcase shouldn't hit machineverifiers anymore with r322917 in place. Large callframes (calls with several hundreds or thousands or parameters) could lead to situations in which the emergency spillslot is out of range to be addressed relative to the stack pointer. This commit forces the use of a frame pointer in the presence of large callframes. This commit does several things: - Compute max callframe size at the end of instruction selection. - Add mirFileLoaded target callback. Use it to compute the max callframe size after loading a .mir file when the size wasn't specified in the file. - Let TargetFrameLowering::hasFP() return true if there exists a callframe > 255 bytes. - Always place the emergency spillslot close to FP if we have a frame pointer. - Note that `useFPForScavengingIndex()` would previously return false when a base pointer was available leading to the emergency spillslot getting allocated late (that's the whole effect of this callback). Which made no sense to me so I took this case out: Even though the emergency spillslot is technically not referenced by FP in this case we still want it allocated early. Differential Revision: https://reviews.llvm.org/D40876 llvm-svn: 322919
2018-01-19 04:16:36 +01:00
void finalizeLowering(MachineFunction &MF) const override;
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
};
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 14:50:23 +02:00
namespace AArch64 {
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
FastISel *createFastISel(FunctionLoweringInfo &funcInfo,
const TargetLibraryInfo *libInfo);
AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. llvm-svn: 209577
2014-05-24 14:50:23 +02:00
} // end namespace AArch64
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 11:18:08 +01:00
} // end namespace llvm
Canonicalize header guards into a common format. Add header guards to files that were missing guards. Remove #endif comments as they don't seem common in LLVM (we can easily add them back if we decide they're useful) Changes made by clang-tidy with minor tweaks. llvm-svn: 215558
2014-08-13 18:26:38 +02:00
#endif
Reference in New Issue Copy Permalink