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/avx512vlcd-intrinsics-fast-...

76 lines
3.0 KiB
LLVM
Raw Normal View History

[x86][AVX512] Lowering Broadcastm intrinsics to LLVM IR This patch, together with a matching clang patch (https://reviews.llvm.org/D38683), implements the lowering of X86 broadcastm intrinsics to IR. Differential Revision: https://reviews.llvm.org/D38684 Change-Id: I709ac0b34641095397e994c8ff7e15d1315b3540 llvm-svn: 317458
2017-11-06 15:09:24 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -fast-isel -mtriple=x86_64-unknown-unknown -mattr=+avx512cd,+avx512vl | FileCheck %s
define <2 x i64> @test_mm_broadcastmb_epi64(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test_mm_broadcastmb_epi64:
[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
; CHECK: # %bb.0: # %entry
[x86][AVX512] Lowering Broadcastm intrinsics to LLVM IR This patch, together with a matching clang patch (https://reviews.llvm.org/D38683), implements the lowering of X86 broadcastm intrinsics to IR. Differential Revision: https://reviews.llvm.org/D38684 Change-Id: I709ac0b34641095397e994c8ff7e15d1315b3540 llvm-svn: 317458
2017-11-06 15:09:24 +08:00
; CHECK-NEXT: vpcmpeqd %xmm1, %xmm0, %k0
; CHECK-NEXT: vpbroadcastmb2q %k0, %xmm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <2 x i64> %a to <4 x i32>
%1 = bitcast <2 x i64> %b to <4 x i32>
%2 = icmp eq <4 x i32> %0, %1
%3 = shufflevector <4 x i1> %2, <4 x i1> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%4 = bitcast <8 x i1> %3 to i8
%conv.i = zext i8 %4 to i64
%vecinit.i.i = insertelement <2 x i64> undef, i64 %conv.i, i32 0
%vecinit1.i.i = shufflevector <2 x i64> %vecinit.i.i, <2 x i64> undef, <2 x i32> zeroinitializer
ret <2 x i64> %vecinit1.i.i
}
define <4 x i64> @test_mm256_broadcastmb_epi64(<4 x i64> %a, <4 x i64> %b) {
; CHECK-LABEL: test_mm256_broadcastmb_epi64:
[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
; CHECK: # %bb.0: # %entry
[x86][AVX512] Lowering Broadcastm intrinsics to LLVM IR This patch, together with a matching clang patch (https://reviews.llvm.org/D38683), implements the lowering of X86 broadcastm intrinsics to IR. Differential Revision: https://reviews.llvm.org/D38684 Change-Id: I709ac0b34641095397e994c8ff7e15d1315b3540 llvm-svn: 317458
2017-11-06 15:09:24 +08:00
; CHECK-NEXT: vpcmpeqq %ymm1, %ymm0, %k0
; CHECK-NEXT: vpbroadcastmb2q %k0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = icmp eq <4 x i64> %a, %b
%1 = shufflevector <4 x i1> %0, <4 x i1> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%2 = bitcast <8 x i1> %1 to i8
%conv.i = zext i8 %2 to i64
%vecinit.i.i = insertelement <4 x i64> undef, i64 %conv.i, i32 0
%vecinit3.i.i = shufflevector <4 x i64> %vecinit.i.i, <4 x i64> undef, <4 x i32> zeroinitializer
ret <4 x i64> %vecinit3.i.i
}
define <2 x i64> @test_mm_broadcastmw_epi32(<8 x i64> %a, <8 x i64> %b) {
; CHECK-LABEL: test_mm_broadcastmw_epi32:
[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
; CHECK: # %bb.0: # %entry
[x86][AVX512] Lowering Broadcastm intrinsics to LLVM IR This patch, together with a matching clang patch (https://reviews.llvm.org/D38683), implements the lowering of X86 broadcastm intrinsics to IR. Differential Revision: https://reviews.llvm.org/D38684 Change-Id: I709ac0b34641095397e994c8ff7e15d1315b3540 llvm-svn: 317458
2017-11-06 15:09:24 +08:00
; CHECK-NEXT: vpcmpeqd %zmm1, %zmm0, %k0
; CHECK-NEXT: vpbroadcastmw2d %k0, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
entry:
%0 = bitcast <8 x i64> %a to <16 x i32>
%1 = bitcast <8 x i64> %b to <16 x i32>
%2 = icmp eq <16 x i32> %0, %1
%3 = bitcast <16 x i1> %2 to i16
%conv.i = zext i16 %3 to i32
%vecinit.i.i = insertelement <4 x i32> undef, i32 %conv.i, i32 0
%vecinit3.i.i = shufflevector <4 x i32> %vecinit.i.i, <4 x i32> undef, <4 x i32> zeroinitializer
%4 = bitcast <4 x i32> %vecinit3.i.i to <2 x i64>
ret <2 x i64> %4
}
define <4 x i64> @test_mm256_broadcastmw_epi32(<8 x i64> %a, <8 x i64> %b) {
; CHECK-LABEL: test_mm256_broadcastmw_epi32:
[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
; CHECK: # %bb.0: # %entry
[x86][AVX512] Lowering Broadcastm intrinsics to LLVM IR This patch, together with a matching clang patch (https://reviews.llvm.org/D38683), implements the lowering of X86 broadcastm intrinsics to IR. Differential Revision: https://reviews.llvm.org/D38684 Change-Id: I709ac0b34641095397e994c8ff7e15d1315b3540 llvm-svn: 317458
2017-11-06 15:09:24 +08:00
; CHECK-NEXT: vpcmpeqd %zmm1, %zmm0, %k0
; CHECK-NEXT: vpbroadcastmw2d %k0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <8 x i64> %a to <16 x i32>
%1 = bitcast <8 x i64> %b to <16 x i32>
%2 = icmp eq <16 x i32> %0, %1
%3 = bitcast <16 x i1> %2 to i16
%conv.i = zext i16 %3 to i32
%vecinit.i.i = insertelement <8 x i32> undef, i32 %conv.i, i32 0
%vecinit7.i.i = shufflevector <8 x i32> %vecinit.i.i, <8 x i32> undef, <8 x i32> zeroinitializer
%4 = bitcast <8 x i32> %vecinit7.i.i to <4 x i64>
ret <4 x i64> %4
}