maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/avx2-nontemporal.ll

97 lines
4.1 KiB
LLVM
Raw Normal View History

[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-linux-gnu -mattr=+avx2 | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mattr=+avx2 | FileCheck %s --check-prefix=X64
Clean up patterns for MOVNT*. Not sure why there were floating point types on MOVNTPS and MOVNTDQ. And v4i64 was completely missing. llvm-svn: 147767
2012-01-09 14:52:46 +08:00
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
define i32 @f(<8 x float> %A, i8* %B, <4 x double> %C, <4 x i64> %E, <8 x i32> %F, <16 x i16> %G, <32 x i8> %H, i32* %loadptr) nounwind {
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
; X32-LABEL: f:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0:
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
; X32-NEXT: pushl %ebp
; X32-NEXT: movl %esp, %ebp
; X32-NEXT: andl $-32, %esp
; X32-NEXT: subl $32, %esp
; X32-NEXT: vmovdqa 104(%ebp), %ymm3
; X32-NEXT: vmovdqa 72(%ebp), %ymm4
; X32-NEXT: vmovdqa 40(%ebp), %ymm5
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
; X32-NEXT: movl 8(%ebp), %ecx
; X32-NEXT: movl 136(%ebp), %edx
; X32-NEXT: movl (%edx), %eax
; X32-NEXT: vaddps {{\.LCPI.*}}, %ymm0, %ymm0
; X32-NEXT: vmovntps %ymm0, (%ecx)
; X32-NEXT: vpaddq {{\.LCPI.*}}, %ymm2, %ymm0
; X32-NEXT: addl (%edx), %eax
; X32-NEXT: vmovntdq %ymm0, (%ecx)
; X32-NEXT: vaddpd {{\.LCPI.*}}, %ymm1, %ymm0
; X32-NEXT: addl (%edx), %eax
; X32-NEXT: vmovntpd %ymm0, (%ecx)
; X32-NEXT: vpaddd {{\.LCPI.*}}, %ymm5, %ymm0
; X32-NEXT: addl (%edx), %eax
; X32-NEXT: vmovntdq %ymm0, (%ecx)
; X32-NEXT: vpaddw {{\.LCPI.*}}, %ymm4, %ymm0
; X32-NEXT: addl (%edx), %eax
; X32-NEXT: vmovntdq %ymm0, (%ecx)
; X32-NEXT: vpaddb {{\.LCPI.*}}, %ymm3, %ymm0
; X32-NEXT: addl (%edx), %eax
; X32-NEXT: vmovntdq %ymm0, (%ecx)
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
; X32-NEXT: movl %ebp, %esp
; X32-NEXT: popl %ebp
; X32-NEXT: vzeroupper
; X32-NEXT: retl
;
; X64-LABEL: f:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0:
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
; X64-NEXT: movl (%rsi), %eax
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
; X64-NEXT: vaddps {{.*}}(%rip), %ymm0, %ymm0
; X64-NEXT: vmovntps %ymm0, (%rdi)
; X64-NEXT: vpaddq {{.*}}(%rip), %ymm2, %ymm0
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
; X64-NEXT: addl (%rsi), %eax
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
; X64-NEXT: vmovntdq %ymm0, (%rdi)
; X64-NEXT: vaddpd {{.*}}(%rip), %ymm1, %ymm0
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
; X64-NEXT: addl (%rsi), %eax
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
; X64-NEXT: vmovntpd %ymm0, (%rdi)
; X64-NEXT: vpaddd {{.*}}(%rip), %ymm3, %ymm0
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
; X64-NEXT: addl (%rsi), %eax
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
; X64-NEXT: vmovntdq %ymm0, (%rdi)
; X64-NEXT: vpaddw {{.*}}(%rip), %ymm4, %ymm0
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
; X64-NEXT: addl (%rsi), %eax
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
; X64-NEXT: vmovntdq %ymm0, (%rdi)
; X64-NEXT: vpaddb {{.*}}(%rip), %ymm5, %ymm0
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
; X64-NEXT: addl (%rsi), %eax
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
; X64-NEXT: vmovntdq %ymm0, (%rdi)
; X64-NEXT: vzeroupper
; X64-NEXT: retq
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
%v0 = load i32, i32* %loadptr, align 1
Clean up patterns for MOVNT*. Not sure why there were floating point types on MOVNTPS and MOVNTDQ. And v4i64 was completely missing. llvm-svn: 147767
2012-01-09 14:52:46 +08:00
%cast = bitcast i8* %B to <8 x float>*
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
%A2 = fadd <8 x float> %A, <float 1.0, float 2.0, float 3.0, float 4.0, float 5.0, float 6.0, float 7.0, float 8.0>
[X86][AVX2] Relaxed alignment on nontemporal store tests llvm-svn: 271646
2016-06-03 18:06:59 +08:00
store <8 x float> %A2, <8 x float>* %cast, align 32, !nontemporal !0
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
%v1 = load i32, i32* %loadptr, align 1
Clean up patterns for MOVNT*. Not sure why there were floating point types on MOVNTPS and MOVNTDQ. And v4i64 was completely missing. llvm-svn: 147767
2012-01-09 14:52:46 +08:00
%cast1 = bitcast i8* %B to <4 x i64>*
%E2 = add <4 x i64> %E, <i64 1, i64 2, i64 3, i64 4>
[X86][AVX2] Relaxed alignment on nontemporal store tests llvm-svn: 271646
2016-06-03 18:06:59 +08:00
store <4 x i64> %E2, <4 x i64>* %cast1, align 32, !nontemporal !0
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
%v2 = load i32, i32* %loadptr, align 1
Clean up patterns for MOVNT*. Not sure why there were floating point types on MOVNTPS and MOVNTDQ. And v4i64 was completely missing. llvm-svn: 147767
2012-01-09 14:52:46 +08:00
%cast2 = bitcast i8* %B to <4 x double>*
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
%C2 = fadd <4 x double> %C, <double 1.0, double 2.0, double 3.0, double 4.0>
[X86][AVX2] Relaxed alignment on nontemporal store tests llvm-svn: 271646
2016-06-03 18:06:59 +08:00
store <4 x double> %C2, <4 x double>* %cast2, align 32, !nontemporal !0
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
%v3 = load i32, i32* %loadptr, align 1
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
%cast3 = bitcast i8* %B to <8 x i32>*
%F2 = add <8 x i32> %F, <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
[X86][AVX2] Relaxed alignment on nontemporal store tests llvm-svn: 271646
2016-06-03 18:06:59 +08:00
store <8 x i32> %F2, <8 x i32>* %cast3, align 32, !nontemporal !0
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
%v4 = load i32, i32* %loadptr, align 1
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
%cast4 = bitcast i8* %B to <16 x i16>*
%G2 = add <16 x i16> %G, <i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8>
[X86][AVX2] Relaxed alignment on nontemporal store tests llvm-svn: 271646
2016-06-03 18:06:59 +08:00
store <16 x i16> %G2, <16 x i16>* %cast4, align 32, !nontemporal !0
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
%v5 = load i32, i32* %loadptr, align 1
[X86][AVX2] Regenerated nontemporal store tests and added tests for all 256-bit vector types llvm-svn: 271645
2016-06-03 17:56:24 +08:00
%cast5 = bitcast i8* %B to <32 x i8>*
%H2 = add <32 x i8> %H, <i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8>
[X86][AVX2] Relaxed alignment on nontemporal store tests llvm-svn: 271646
2016-06-03 18:06:59 +08:00
store <32 x i8> %H2, <32 x i8>* %cast5, align 32, !nontemporal !0
[X86] Modify Nontemporal tests to avoid deadstore optimization. llvm-svn: 320379
2017-12-11 23:35:40 +08:00
%v6 = load i32, i32* %loadptr, align 1
%sum1 = add i32 %v0, %v1
%sum2 = add i32 %sum1, %v2
%sum3 = add i32 %sum2, %v3
%sum4 = add i32 %sum3, %v4
%sum5 = add i32 %sum4, %v5
%sum6 = add i32 %sum5, %v6
ret i32 %sum5
Clean up patterns for MOVNT*. Not sure why there were floating point types on MOVNTPS and MOVNTDQ. And v4i64 was completely missing. llvm-svn: 147767
2012-01-09 14:52:46 +08:00
}
IR: Make metadata typeless in assembly Now that `Metadata` is typeless, reflect that in the assembly. These are the matching assembly changes for the metadata/value split in r223802. - Only use the `metadata` type when referencing metadata from a call intrinsic -- i.e., only when it's used as a `Value`. - Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode` when referencing it from call intrinsics. So, assembly like this: define @foo(i32 %v) { call void @llvm.foo(metadata !{i32 %v}, metadata !0) call void @llvm.foo(metadata !{i32 7}, metadata !0) call void @llvm.foo(metadata !1, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{metadata !3}, metadata !0) ret void, !bar !2 } !0 = metadata !{metadata !2} !1 = metadata !{i32* @global} !2 = metadata !{metadata !3} !3 = metadata !{} turns into this: define @foo(i32 %v) { call void @llvm.foo(metadata i32 %v, metadata !0) call void @llvm.foo(metadata i32 7, metadata !0) call void @llvm.foo(metadata i32* @global, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{!3}, metadata !0) ret void, !bar !2 } !0 = !{!2} !1 = !{i32* @global} !2 = !{!3} !3 = !{} I wrote an upgrade script that handled almost all of the tests in llvm and many of the tests in cfe (even handling many `CHECK` lines). I've attached it (or will attach it in a moment if you're speedy) to PR21532 to help everyone update their out-of-tree testcases. This is part of PR21532. llvm-svn: 224257
2014-12-16 03:07:53 +08:00
!0 = !{i32 1}