1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-01 05:01:59 +01:00
llvm-mirror/test/CodeGen/AArch64/arm64-abi-varargs.ll
Florian Hahn 300cd7b42b [AArch64] Teach Load/Store optimizier to rename store operands for pairing.
In some cases, we can rename a store operand, in order to enable pairing
of stores.  For store pairs, that cannot be merged because the first
tored register is defined in between the second store, we try to find
suitable rename register.

First, we check if we can rename the given register:

1. The first store register must be killed at the store, which means we
   do not have to rename instructions after the first store.
2. We scan backwards from the first store, to find the definition of the
   stored register and check all uses in between are renamable. Along
   they way, we collect the minimal register classes of the uses for
   overlapping (sub/super)registers.

Second, we try to find an available register from the minimal physical
register class of the original register. A suitable register must not be

1. defined before FirstMI
2. between the previous definition of the register to rename
3. a callee saved register.

We use KILL flags to clear defined registers while scanning from the
beginning to the end of the block.

This triggers quite often, here are the top changes for MultiSource,
SPEC2000, SPEC2006 compiled with -O3 for iOS:

Metric: aarch64-ldst-opt.NumPairCreated

Program                                        base     patch    diff
 test-suite...nch/fourinarow/fourinarow.test     2.00    39.00   1850.0%
 test-suite...s/ASC_Sequoia/IRSmk/IRSmk.test    46.00    80.00   73.9%
 test-suite...chmarks/Olden/power/power.test    70.00    96.00   37.1%
 test-suite...cations/hexxagon/hexxagon.test    29.00    39.00   34.5%
 test-suite...nchmarks/McCat/05-eks/eks.test   100.00   132.00   32.0%
 test-suite.../Trimaran/enc-rc4/enc-rc4.test    46.00    59.00   28.3%
 test-suite...T2006/473.astar/473.astar.test   160.00   200.00   25.0%
 test-suite.../Trimaran/enc-md5/enc-md5.test     8.00    10.00   25.0%
 test-suite...telecomm-gsm/telecomm-gsm.test   113.00   139.00   23.0%
 test-suite...ediabench/gsm/toast/toast.test   113.00   139.00   23.0%
 test-suite...Source/Benchmarks/sim/sim.test    91.00   111.00   22.0%
 test-suite...C/CFP2000/179.art/179.art.test    41.00    49.00   19.5%
 test-suite...peg2/mpeg2dec/mpeg2decode.test   245.00   279.00   13.9%
 test-suite...marks/Olden/health/health.test    16.00    18.00   12.5%
 test-suite...ks/Prolangs-C/cdecl/cdecl.test    90.00   101.00   12.2%
 test-suite...fice-ispell/office-ispell.test    91.00   100.00    9.9%
 test-suite...oxyApps-C/miniGMG/miniGMG.test   430.00   465.00    8.1%
 test-suite...lowfish/security-blowfish.test    39.00    42.00    7.7%
 test-suite.../Applications/spiff/spiff.test    42.00    45.00    7.1%
 test-suite...arks/mafft/pairlocalalign.test   2473.00  2646.00   7.0%
 test-suite.../VersaBench/ecbdes/ecbdes.test    29.00    31.00    6.9%
 test-suite...nch/beamformer/beamformer.test   220.00   235.00    6.8%
 test-suite...CFP2000/177.mesa/177.mesa.test   2110.00  2252.00   6.7%
 test-suite...ve-susan/automotive-susan.test   109.00   116.00    6.4%
 test-suite...s-C/unix-smail/unix-smail.test    65.00    69.00    6.2%
 test-suite...CI_Purple/SMG2000/smg2000.test   1194.00  1265.00   5.9%
 test-suite.../Benchmarks/nbench/nbench.test   472.00   500.00    5.9%
 test-suite...oxyApps-C/miniAMR/miniAMR.test   248.00   262.00    5.6%
 test-suite...quoia/CrystalMk/CrystalMk.test    18.00    19.00    5.6%
 test-suite...rks/tramp3d-v4/tramp3d-v4.test   7331.00  7710.00   5.2%
 test-suite.../Benchmarks/Bullet/bullet.test   5651.00  5938.00   5.1%
 test-suite...ternal/HMMER/hmmcalibrate.test   750.00   788.00    5.1%
 test-suite...T2006/456.hmmer/456.hmmer.test   764.00   802.00    5.0%
 test-suite...ications/JM/ldecod/ldecod.test   1028.00  1079.00   5.0%
 test-suite...CFP2006/444.namd/444.namd.test   1368.00  1434.00   4.8%
 test-suite...marks/7zip/7zip-benchmark.test   4471.00  4685.00   4.8%
 test-suite...6/464.h264ref/464.h264ref.test   3122.00  3271.00   4.8%
 test-suite...pplications/oggenc/oggenc.test   1497.00  1565.00   4.5%
 test-suite...T2000/300.twolf/300.twolf.test   742.00   774.00    4.3%
 test-suite.../Prolangs-C/loader/loader.test    24.00    25.00    4.2%
 test-suite...0.perlbench/400.perlbench.test   1983.00  2058.00   3.8%
 test-suite...ications/JM/lencod/lencod.test   4612.00  4785.00   3.8%
 test-suite...yApps-C++/PENNANT/PENNANT.test   995.00   1032.00   3.7%
 test-suite...arks/VersaBench/dbms/dbms.test    54.00    56.00    3.7%

Reviewers: efriedma, thegameg, samparker, dmgreen, paquette, evandro

Reviewed By: paquette

Differential Revision: https://reviews.llvm.org/D70450
2019-12-11 13:50:11 +00:00

275 lines
9.3 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=arm64-apple-ios7.0.0 -mcpu=cyclone -enable-misched=false | FileCheck %s
; rdar://13625505
; Here we have 9 fixed integer arguments the 9th argument in on stack, the
; varargs start right after at 8-byte alignment.
define void @fn9(i32* %a1, i32 %a2, i32 %a3, i32 %a4, i32 %a5, i32 %a6, i32 %a7, i32 %a8, i32 %a9, ...) nounwind noinline ssp {
; CHECK-LABEL: fn9:
; CHECK: ; %bb.0:
; CHECK-NEXT: sub sp, sp, #64 ; =64
; CHECK-NEXT: ldr w8, [sp, #64]
; CHECK-NEXT: stp w2, w1, [sp, #52]
; CHECK-NEXT: stp w4, w3, [sp, #44]
; CHECK-NEXT: stp w6, w5, [sp, #36]
; CHECK-NEXT: str w7, [sp, #32]
; CHECK-NEXT: str w8, [x0]
; CHECK-NEXT: ldr w9, [sp, #72]
; CHECK-NEXT: ldr w8, [sp, #80]
; CHECK-NEXT: stp w8, w9, [sp, #16]
; CHECK-NEXT: add x8, sp, #72 ; =72
; CHECK-NEXT: add x8, x8, #24 ; =24
; CHECK-NEXT: str x8, [sp, #24]
; CHECK-NEXT: ldr w8, [sp, #88]
; CHECK-NEXT: str w8, [sp, #12]
; CHECK-NEXT: add sp, sp, #64 ; =64
; CHECK-NEXT: ret
%1 = alloca i32, align 4
%2 = alloca i32, align 4
%3 = alloca i32, align 4
%4 = alloca i32, align 4
%5 = alloca i32, align 4
%6 = alloca i32, align 4
%7 = alloca i32, align 4
%8 = alloca i32, align 4
%9 = alloca i32, align 4
%args = alloca i8*, align 8
%a10 = alloca i32, align 4
%a11 = alloca i32, align 4
%a12 = alloca i32, align 4
store i32 %a2, i32* %2, align 4
store i32 %a3, i32* %3, align 4
store i32 %a4, i32* %4, align 4
store i32 %a5, i32* %5, align 4
store i32 %a6, i32* %6, align 4
store i32 %a7, i32* %7, align 4
store i32 %a8, i32* %8, align 4
store i32 %a9, i32* %9, align 4
store i32 %a9, i32* %a1
%10 = bitcast i8** %args to i8*
call void @llvm.va_start(i8* %10)
%11 = va_arg i8** %args, i32
store i32 %11, i32* %a10, align 4
%12 = va_arg i8** %args, i32
store i32 %12, i32* %a11, align 4
%13 = va_arg i8** %args, i32
store i32 %13, i32* %a12, align 4
ret void
}
declare void @llvm.va_start(i8*) nounwind
define i32 @main() nounwind ssp {
; CHECK-LABEL: main:
; CHECK: ; %bb.0:
; CHECK-NEXT: sub sp, sp, #96 ; =96
; CHECK-NEXT: stp x29, x30, [sp, #80] ; 16-byte Folded Spill
; CHECK-NEXT: mov w9, #1
; CHECK-NEXT: mov w8, #2
; CHECK-NEXT: stp w8, w9, [sp, #72]
; CHECK-NEXT: mov w9, #3
; CHECK-NEXT: mov w8, #4
; CHECK-NEXT: stp w8, w9, [sp, #64]
; CHECK-NEXT: mov w9, #5
; CHECK-NEXT: mov w8, #6
; CHECK-NEXT: stp w8, w9, [sp, #56]
; CHECK-NEXT: mov w9, #7
; CHECK-NEXT: mov w8, #8
; CHECK-NEXT: stp w8, w9, [sp, #48]
; CHECK-NEXT: mov w8, #9
; CHECK-NEXT: mov w9, #10
; CHECK-NEXT: stp w9, w8, [sp, #40]
; CHECK-NEXT: mov w10, #11
; CHECK-NEXT: mov w11, #12
; CHECK-NEXT: stp w11, w10, [sp, #32]
; CHECK-NEXT: stp x10, x11, [sp, #16]
; CHECK-NEXT: str x9, [sp, #8]
; CHECK-NEXT: str w8, [sp]
; CHECK-NEXT: add x0, sp, #76 ; =76
; CHECK-NEXT: mov w1, #2
; CHECK-NEXT: mov w2, #3
; CHECK-NEXT: mov w3, #4
; CHECK-NEXT: mov w4, #5
; CHECK-NEXT: mov w5, #6
; CHECK-NEXT: mov w6, #7
; CHECK-NEXT: mov w7, #8
; CHECK-NEXT: bl _fn9
; CHECK-NEXT: mov w0, #0
; CHECK-NEXT: ldp x29, x30, [sp, #80] ; 16-byte Folded Reload
; CHECK-NEXT: add sp, sp, #96 ; =96
; CHECK-NEXT: ret
%a1 = alloca i32, align 4
%a2 = alloca i32, align 4
%a3 = alloca i32, align 4
%a4 = alloca i32, align 4
%a5 = alloca i32, align 4
%a6 = alloca i32, align 4
%a7 = alloca i32, align 4
%a8 = alloca i32, align 4
%a9 = alloca i32, align 4
%a10 = alloca i32, align 4
%a11 = alloca i32, align 4
%a12 = alloca i32, align 4
store i32 1, i32* %a1, align 4
store i32 2, i32* %a2, align 4
store i32 3, i32* %a3, align 4
store i32 4, i32* %a4, align 4
store i32 5, i32* %a5, align 4
store i32 6, i32* %a6, align 4
store i32 7, i32* %a7, align 4
store i32 8, i32* %a8, align 4
store i32 9, i32* %a9, align 4
store i32 10, i32* %a10, align 4
store i32 11, i32* %a11, align 4
store i32 12, i32* %a12, align 4
%1 = load i32, i32* %a1, align 4
%2 = load i32, i32* %a2, align 4
%3 = load i32, i32* %a3, align 4
%4 = load i32, i32* %a4, align 4
%5 = load i32, i32* %a5, align 4
%6 = load i32, i32* %a6, align 4
%7 = load i32, i32* %a7, align 4
%8 = load i32, i32* %a8, align 4
%9 = load i32, i32* %a9, align 4
%10 = load i32, i32* %a10, align 4
%11 = load i32, i32* %a11, align 4
%12 = load i32, i32* %a12, align 4
call void (i32*, i32, i32, i32, i32, i32, i32, i32, i32, ...) @fn9(i32* %a1, i32 %2, i32 %3, i32 %4, i32 %5, i32 %6, i32 %7, i32 %8, i32 %9, i32 %10, i32 %11, i32 %12)
ret i32 0
}
;rdar://13668483
@.str = private unnamed_addr constant [4 x i8] c"fmt\00", align 1
define void @foo(i8* %fmt, ...) nounwind {
; CHECK-LABEL: foo:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: sub sp, sp, #48 ; =48
; CHECK-NEXT: ldr w8, [sp, #48]
; CHECK-NEXT: str w8, [sp, #28]
; CHECK-NEXT: add x8, sp, #48 ; =48
; CHECK-NEXT: add x8, x8, #23 ; =23
; CHECK-NEXT: and x8, x8, #0xfffffffffffffff0
; CHECK-NEXT: add x9, x8, #16 ; =16
; CHECK-NEXT: stp x9, x0, [sp, #32]
; CHECK-NEXT: ldr q0, [x8]
; CHECK-NEXT: str q0, [sp], #48
; CHECK-NEXT: ret
entry:
%fmt.addr = alloca i8*, align 8
%args = alloca i8*, align 8
%vc = alloca i32, align 4
%vv = alloca <4 x i32>, align 16
store i8* %fmt, i8** %fmt.addr, align 8
%args1 = bitcast i8** %args to i8*
call void @llvm.va_start(i8* %args1)
%0 = va_arg i8** %args, i32
store i32 %0, i32* %vc, align 4
%1 = va_arg i8** %args, <4 x i32>
store <4 x i32> %1, <4 x i32>* %vv, align 16
ret void
}
define void @bar(i32 %x, <4 x i32> %y) nounwind {
; CHECK-LABEL: bar:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: sub sp, sp, #80 ; =80
; CHECK-NEXT: stp x29, x30, [sp, #64] ; 16-byte Folded Spill
; CHECK-NEXT: ; kill: def $w0 killed $w0 def $x0
; CHECK-NEXT: str w0, [sp, #60]
; CHECK-NEXT: stp q0, q0, [sp, #16]
; CHECK-NEXT: str x0, [sp]
; CHECK-NEXT: Lloh0:
; CHECK-NEXT: adrp x0, l_.str@PAGE
; CHECK-NEXT: Lloh1:
; CHECK-NEXT: add x0, x0, l_.str@PAGEOFF
; CHECK-NEXT: bl _foo
; CHECK-NEXT: ldp x29, x30, [sp, #64] ; 16-byte Folded Reload
; CHECK-NEXT: add sp, sp, #80 ; =80
; CHECK-NEXT: ret
; CHECK-NEXT: .loh AdrpAdd Lloh0, Lloh1
entry:
%x.addr = alloca i32, align 4
%y.addr = alloca <4 x i32>, align 16
store i32 %x, i32* %x.addr, align 4
store <4 x i32> %y, <4 x i32>* %y.addr, align 16
%0 = load i32, i32* %x.addr, align 4
%1 = load <4 x i32>, <4 x i32>* %y.addr, align 16
call void (i8*, ...) @foo(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i32 0, i32 0), i32 %0, <4 x i32> %1)
ret void
}
; rdar://13668927
; When passing 16-byte aligned small structs as vararg, make sure the caller
; side is 16-byte aligned on stack.
%struct.s41 = type { i32, i16, i32, i16 }
define void @foo2(i8* %fmt, ...) nounwind {
; CHECK-LABEL: foo2:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: sub sp, sp, #48 ; =48
; CHECK-NEXT: ldr w8, [sp, #48]
; CHECK-NEXT: str w8, [sp, #28]
; CHECK-NEXT: add x8, sp, #48 ; =48
; CHECK-NEXT: add x8, x8, #23 ; =23
; CHECK-NEXT: and x8, x8, #0xfffffffffffffff0
; CHECK-NEXT: add x9, x8, #16 ; =16
; CHECK-NEXT: stp x9, x0, [sp, #32]
; CHECK-NEXT: ldr q0, [x8]
; CHECK-NEXT: str q0, [sp], #48
; CHECK-NEXT: ret
entry:
%fmt.addr = alloca i8*, align 8
%args = alloca i8*, align 8
%vc = alloca i32, align 4
%vs = alloca %struct.s41, align 16
store i8* %fmt, i8** %fmt.addr, align 8
%args1 = bitcast i8** %args to i8*
call void @llvm.va_start(i8* %args1)
%0 = va_arg i8** %args, i32
store i32 %0, i32* %vc, align 4
%ap.cur = load i8*, i8** %args
%1 = getelementptr i8, i8* %ap.cur, i32 15
%2 = ptrtoint i8* %1 to i64
%3 = and i64 %2, -16
%ap.align = inttoptr i64 %3 to i8*
%ap.next = getelementptr i8, i8* %ap.align, i32 16
store i8* %ap.next, i8** %args
%4 = bitcast i8* %ap.align to %struct.s41*
%5 = bitcast %struct.s41* %vs to i8*
%6 = bitcast %struct.s41* %4 to i8*
call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %5, i8* align 16 %6, i64 16, i1 false)
ret void
}
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
define void @bar2(i32 %x, i128 %s41.coerce) nounwind {
; CHECK-LABEL: bar2:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: sub sp, sp, #80 ; =80
; CHECK-NEXT: stp x29, x30, [sp, #64] ; 16-byte Folded Spill
; CHECK-NEXT: ; kill: def $w0 killed $w0 def $x0
; CHECK-NEXT: str w0, [sp, #60]
; CHECK-NEXT: stp x1, x2, [sp, #32]
; CHECK-NEXT: stp x1, x2, [sp, #16]
; CHECK-NEXT: str x0, [sp]
; CHECK-NEXT: Lloh2:
; CHECK-NEXT: adrp x0, l_.str@PAGE
; CHECK-NEXT: Lloh3:
; CHECK-NEXT: add x0, x0, l_.str@PAGEOFF
; CHECK-NEXT: bl _foo2
; CHECK-NEXT: ldp x29, x30, [sp, #64] ; 16-byte Folded Reload
; CHECK-NEXT: add sp, sp, #80 ; =80
; CHECK-NEXT: ret
; CHECK-NEXT: .loh AdrpAdd Lloh2, Lloh3
entry:
%x.addr = alloca i32, align 4
%s41 = alloca %struct.s41, align 16
store i32 %x, i32* %x.addr, align 4
%0 = bitcast %struct.s41* %s41 to i128*
store i128 %s41.coerce, i128* %0, align 1
%1 = load i32, i32* %x.addr, align 4
%2 = bitcast %struct.s41* %s41 to i128*
%3 = load i128, i128* %2, align 1
call void (i8*, ...) @foo2(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i32 0, i32 0), i32 %1, i128 %3)
ret void
}