RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
Code Issues Projects Releases Wiki Activity
c46fc6adbe
llvm-mirror/test/CodeGen/ARM/fast-isel-call.ll
Simon Tatham cf702a78f5 [ARM] Code-generation infrastructure for MVE. 
This provides the low-level support to start using MVE vector types in
LLVM IR, loading and storing them, passing them to __asm__ statements
containing hand-written MVE vector instructions, and *if* you have the
hard-float ABI turned on, using them as function parameters.

(In the soft-float ABI, vector types are passed in integer registers,
and combining all those 32-bit integers into a q-reg requires support
for selection DAG nodes like insert_vector_elt and build_vector which
aren't implemented yet for MVE. In fact I've also had to add
`arm_aapcs_vfpcc` to a couple of existing tests to avoid that
problem.)

Specifically, this commit adds support for:

 * spills, reloads and register moves for MVE vector registers

 * ditto for the VPT predication mask that lives in VPR.P0

 * make all the MVE vector types legal in ISel, and provide selection
   DAG patterns for BITCAST, LOAD and STORE

 * make loads and stores of scalar FP types conditional on
   `hasFPRegs()` rather than `hasVFP2Base()`. As a result a few
   existing tests needed their llc command lines updating to use
   `-mattr=-fpregs` as their method of turning off all hardware FP
   support.

Reviewers: dmgreen, samparker, SjoerdMeijer

Subscribers: javed.absar, kristof.beyls, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D60708

llvm-svn: 364329
2019-06-25 16:48:46 +00:00

277 lines
8.9 KiB
LLVM
Raw Blame History

; RUN: llc -fast-isel-sink-local-values < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=armv7-apple-ios | FileCheck %s --check-prefix=ARM
; RUN: llc -fast-isel-sink-local-values < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=armv7-linux-gnueabi | FileCheck %s --check-prefix=ARM
; RUN: llc -fast-isel-sink-local-values < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=thumbv7-apple-ios | FileCheck %s --check-prefix=THUMB
; RUN: llc -fast-isel-sink-local-values < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=armv7-apple-ios -mattr=+long-calls | FileCheck %s --check-prefix=ARM-LONG --check-prefix=ARM-LONG-MACHO
; RUN: llc -fast-isel-sink-local-values < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=armv7-linux-gnueabi -mattr=+long-calls | FileCheck %s --check-prefix=ARM-LONG --check-prefix=ARM-LONG-ELF
; RUN: llc -fast-isel-sink-local-values < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=thumbv7-apple-ios -mattr=+long-calls | FileCheck %s --check-prefix=THUMB-LONG
; RUN: llc -fast-isel-sink-local-values < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=armv7-apple-ios -mattr=-fpregs | FileCheck %s --check-prefix=ARM-NOVFP
; RUN: llc -fast-isel-sink-local-values < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=armv7-linux-gnueabi -mattr=-fpregs | FileCheck %s --check-prefix=ARM-NOVFP
; RUN: llc -fast-isel-sink-local-values < %s -O0 -verify-machineinstrs -fast-isel-abort=1 -relocation-model=dynamic-no-pic -mtriple=thumbv7-apple-ios -mattr=-fpregs | FileCheck %s --check-prefix=THUMB-NOVFP
; Note that some of these tests assume that relocations are either
; movw/movt or constant pool loads. Different platforms will select
; different approaches.
define i32 @t0(i1 zeroext %a) nounwind {
%1 = zext i1 %a to i32
ret i32 %1
}
define i32 @t1(i8 signext %a) nounwind {
%1 = sext i8 %a to i32
ret i32 %1
}
define i32 @t2(i8 zeroext %a) nounwind {
%1 = zext i8 %a to i32
ret i32 %1
}
define i32 @t3(i16 signext %a) nounwind {
%1 = sext i16 %a to i32
ret i32 %1
}
define i32 @t4(i16 zeroext %a) nounwind {
%1 = zext i16 %a to i32
ret i32 %1
}
define void @foo(i8 %a, i16 %b) nounwind {
; ARM: foo
; THUMB: foo
;; Materialize i1 1
; ARM: movw r2, #1
;; zero-ext
; ARM: and r2, r2, #1
; THUMB: and r2, r2, #1
%1 = call i32 @t0(i1 zeroext 1)
; ARM: sxtb r2, r1
; ARM: mov r0, r2
; THUMB: sxtb r2, r1
; THUMB: mov r0, r2
%2 = call i32 @t1(i8 signext %a)
; ARM: and r2, r1, #255
; ARM: mov r0, r2
; THUMB: and r2, r1, #255
; THUMB: mov r0, r2
%3 = call i32 @t2(i8 zeroext %a)
; ARM: sxth r2, r1
; ARM: mov r0, r2
; THUMB: sxth r2, r1
; THUMB: mov r0, r2
%4 = call i32 @t3(i16 signext %b)
; ARM: uxth r2, r1
; ARM: mov r0, r2
; THUMB: uxth r2, r1
; THUMB: mov r0, r2
%5 = call i32 @t4(i16 zeroext %b)
;; A few test to check materialization
;; Note: i1 1 was materialized with t1 call
; ARM: movw r1, #255
%6 = call i32 @t2(i8 zeroext 255)
; ARM: movw r1, #65535
; THUMB: movw r1, #65535
%7 = call i32 @t4(i16 zeroext 65535)
ret void
}
define void @foo2() nounwind {
%1 = call signext i16 @t5()
%2 = call zeroext i16 @t6()
%3 = call signext i8 @t7()
%4 = call zeroext i8 @t8()
%5 = call zeroext i1 @t9()
ret void
}
declare signext i16 @t5();
declare zeroext i16 @t6();
declare signext i8 @t7();
declare zeroext i8 @t8();
declare zeroext i1 @t9();
define i32 @t10() {
entry:
; ARM: @t10
; ARM-DAG: movw [[R0:l?r[0-9]*]], #0
; ARM-DAG: movw [[R1:l?r[0-9]*]], #248
; ARM-DAG: movw [[R2:l?r[0-9]*]], #187
; ARM-DAG: movw [[R3:l?r[0-9]*]], #28
; ARM-DAG: movw [[R4:l?r[0-9]*]], #40
; ARM-DAG: movw [[R5:l?r[0-9]*]], #186
; ARM-DAG: and [[R0]], [[R0]], #255
; ARM-DAG: and [[R1]], [[R1]], #255
; ARM-DAG: and [[R2]], [[R2]], #255
; ARM-DAG: and [[R3]], [[R3]], #255
; ARM-DAG: and [[R4]], [[R4]], #255
; ARM-DAG: str [[R4]], [sp]
; ARM-DAG: and [[R4]], [[R5]], #255
; ARM-DAG: str [[R4]], [sp, #4]
; ARM: bl {{_?}}bar
; ARM-LONG-LABEL: @t10
; ARM-LONG-MACHO: {{(movw)|(ldr)}} [[R:l?r[0-9]*]], {{(:lower16:L_bar\$non_lazy_ptr)|(.LCPI)}}
; ARM-LONG-MACHO: {{(movt [[R]], :upper16:L_bar\$non_lazy_ptr)?}}
; ARM-LONG-MACHO: str [[R]], [r7, [[SLOT:#[-0-9]+]]] @ 4-byte Spill
; ARM-LONG-MACHO: ldr [[R:l?r[0-9]*]], [r7, [[SLOT]]] @ 4-byte Reload
; ARM-LONG-ELF: movw [[R:l?r[0-9]*]], :lower16:bar
; ARM-LONG-ELF: {{(movt [[R]], :upper16:L_bar\$non_lazy_ptr)?}}
; ARM-LONG: blx [[R]]
; THUMB: @t10
; THUMB-DAG: movs [[R0:l?r[0-9]*]], #0
; THUMB-DAG: movs [[R1:l?r[0-9]*]], #248
; THUMB-DAG: movs [[R2:l?r[0-9]*]], #187
; THUMB-DAG: movs [[R3:l?r[0-9]*]], #28
; THUMB-DAG: movw [[R4:l?r[0-9]*]], #40
; THUMB-DAG: movw [[R5:l?r[0-9]*]], #186
; THUMB-DAG: and [[R0]], [[R0]], #255
; THUMB-DAG: and [[R1]], [[R1]], #255
; THUMB-DAG: and [[R2]], [[R2]], #255
; THUMB-DAG: and [[R3]], [[R3]], #255
; THUMB-DAG: and [[R4]], [[R4]], #255
; THUMB-DAG: str.w [[R4]], [sp]
; THUMB-DAG: and [[R4]], [[R5]], #255
; THUMB-DAG: str.w [[R4]], [sp, #4]
; THUMB: bl {{_?}}bar
; THUMB-LONG-LABEL: @t10
; THUMB-LONG: {{(movw)|(ldr.n)}} [[R:l?r[0-9]*]], {{(:lower16:L_bar\$non_lazy_ptr)|(.LCPI)}}
; THUMB-LONG: {{(movt [[R]], :upper16:L_bar\$non_lazy_ptr)?}}
; THUMB-LONG: ldr{{(.w)?}} [[R]], {{\[}}[[R]]{{\]}}
; THUMB-LONG: str [[R]], [sp, [[SLOT:#[-0-9]+]]] @ 4-byte Spill
; THUMB-LONG: ldr.w [[R:l?r[0-9]*]], [sp, [[SLOT]]] @ 4-byte Reload
; THUMB-LONG: blx [[R]]
%call = call i32 @bar(i8 zeroext 0, i8 zeroext -8, i8 zeroext -69, i8 zeroext 28, i8 zeroext 40, i8 zeroext -70)
ret i32 0
}
declare i32 @bar(i8 zeroext, i8 zeroext, i8 zeroext, i8 zeroext, i8 zeroext, i8 zeroext)
define i32 @bar0(i32 %i) nounwind {
ret i32 0
}
define void @foo3() uwtable {
; ARM: @foo3
; ARM: {{(movw r[0-9]+, :lower16:_?bar0)|(ldr r[0-9]+, .LCPI)}}
; ARM: {{(movt r[0-9]+, :upper16:_?bar0)|(ldr r[0-9]+, \[r[0-9]+\])}}
; ARM: movw {{r[0-9]+}}, #0
; ARM: blx {{r[0-9]+}}
; THUMB: {{(movw r[0-9]+, :lower16:_?bar0)|(ldr.n r[0-9]+, .LCPI)}}
; THUMB: {{(movt r[0-9]+, :upper16:_?bar0)|(ldr r[0-9]+, \[r[0-9]+\])}}
; THUMB: movs {{r[0-9]+}}, #0
; THUMB: blx {{r[0-9]+}}
%fptr = alloca i32 (i32)*, align 8
store i32 (i32)* @bar0, i32 (i32)** %fptr, align 8
%1 = load i32 (i32)*, i32 (i32)** %fptr, align 8
%call = call i32 %1(i32 0)
ret void
}
define i32 @LibCall(i32 %a, i32 %b) {
entry:
; ARM: LibCall
; ARM: bl {{___udivsi3|__aeabi_uidiv}}
; ARM-LONG-LABEL: LibCall
; ARM-LONG-MACHO: {{(movw r2, :lower16:L___udivsi3\$non_lazy_ptr)|(ldr r2, .LCPI)}}
; ARM-LONG-MACHO: {{(movt r2, :upper16:L___udivsi3\$non_lazy_ptr)?}}
; ARM-LONG-MACHO: ldr r2, [r2]
; ARM-LONG-ELF: movw r2, :lower16:__aeabi_uidiv
; ARM-LONG-ELF: movt r2, :upper16:__aeabi_uidiv
; ARM-LONG: blx r2
; THUMB: LibCall
; THUMB: bl {{___udivsi3|__aeabi_uidiv}}
; THUMB-LONG-LABEL: LibCall
; THUMB-LONG: {{(movw r2, :lower16:L___udivsi3\$non_lazy_ptr)|(ldr.n r2, .LCPI)}}
; THUMB-LONG: {{(movt r2, :upper16:L___udivsi3\$non_lazy_ptr)?}}
; THUMB-LONG: ldr r2, [r2]
; THUMB-LONG: blx r2
%tmp1 = udiv i32 %a, %b ; <i32> [#uses=1]
ret i32 %tmp1
}
; Test fastcc
define fastcc void @fast_callee(float %i) ssp {
entry:
; ARM: fast_callee
; ARM: vmov r0, s0
; THUMB: fast_callee
; THUMB: vmov r0, s0
; ARM-NOVFP: fast_callee
; ARM-NOVFP-NOT: s0
; THUMB-NOVFP: fast_callee
; THUMB-NOVFP-NOT: s0
call void @print(float %i)
ret void
}
define void @fast_caller() ssp {
entry:
; ARM: fast_caller
; ARM: vldr s0,
; THUMB: fast_caller
; THUMB: vldr s0,
; ARM-NOVFP: fast_caller
; ARM-NOVFP: movw r0, #13107
; ARM-NOVFP: movt r0, #16611
; THUMB-NOVFP: fast_caller
; THUMB-NOVFP: movw r0, #13107
; THUMB-NOVFP: movt r0, #16611
call fastcc void @fast_callee(float 0x401C666660000000)
ret void
}
define void @no_fast_callee(float %i) ssp {
entry:
; ARM: no_fast_callee
; ARM: vmov s0, r0
; THUMB: no_fast_callee
; THUMB: vmov s0, r0
; ARM-NOVFP: no_fast_callee
; ARM-NOVFP-NOT: s0
; THUMB-NOVFP: no_fast_callee
; THUMB-NOVFP-NOT: s0
call void @print(float %i)
ret void
}
define void @no_fast_caller() ssp {
entry:
; ARM: no_fast_caller
; ARM: vmov r0, s0
; THUMB: no_fast_caller
; THUMB: vmov r0, s0
; ARM-NOVFP: no_fast_caller
; ARM-NOVFP: movw r0, #13107
; ARM-NOVFP: movt r0, #16611
; THUMB-NOVFP: no_fast_caller
; THUMB-NOVFP: movw r0, #13107
; THUMB-NOVFP: movt r0, #16611
call void @no_fast_callee(float 0x401C666660000000)
ret void
}
declare void @bar2(i32 %a1, i32 %a2, i32 %a3, i32 %a4, i32 %a5, i32 %a6)
define void @call_undef_args() {
; ARM-LABEL: call_undef_args
; ARM: movw r0, #1
; ARM-NEXT: movw r1, #2
; ARM-NEXT: movw r2, #3
; ARM-NEXT: movw r3, #4
; ARM-NOT: str {{r[0-9]+}}, [sp]
; ARM: movw [[REG:l?r[0-9]*]], #6
; ARM-NEXT: str [[REG]], [sp, #4]
call void @bar2(i32 1, i32 2, i32 3, i32 4, i32 undef, i32 6)
ret void
}
declare void @print(float)
Reference in New Issue View Git Blame Copy Permalink