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/shrink_vmul.ll

1457 lines
60 KiB
LLVM
Raw Normal View History

[X86] Add VPADD instructions to X86InstrInfo::isAssociativeAndCommutative. llvm-svn: 275769
2016-07-18 14:14:54 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X86
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X64
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
@c = external global i32*, align 8
; %val1 = load <2 x i8>
; %op1 = zext<2 x i32> %val1
; %val2 = load <2 x i8>
; %op2 = zext<2 x i32> %val2
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi8(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi8:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movzwl (%edx,%ecx), %edx
; X86-NEXT: movd %edx, %xmm0
; X86-NEXT: movzwl (%eax,%ecx), %eax
; X86-NEXT: movd %eax, %xmm1
; X86-NEXT: pxor %xmm2, %xmm2
; X86-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; X86-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X86-NEXT: pmullw %xmm0, %xmm1
; X86-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X86-NEXT: movq %xmm1, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi8:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movzwl (%rdi,%rdx), %ecx
; X64-NEXT: movd %ecx, %xmm0
; X64-NEXT: movzwl (%rsi,%rdx), %ecx
; X64-NEXT: movd %ecx, %xmm1
; X64-NEXT: pxor %xmm2, %xmm2
; X64-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; X64-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X64-NEXT: pmullw %xmm0, %xmm1
; X64-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X64-NEXT: movq %xmm1, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i8>*
%wide.load = load <2 x i8>, <2 x i8>* %tmp7, align 1
%tmp8 = zext <2 x i8> %wide.load to <2 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <2 x i8>*
%wide.load17 = load <2 x i8>, <2 x i8>* %tmp11, align 1
%tmp12 = zext <2 x i8> %wide.load17 to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <4 x i8>
; %op1 = zext<4 x i32> %val1
; %val2 = load <4 x i8>
; %op2 = zext<4 x i32> %val2
; %rst = mul <4 x i32> %op1, %op2
;
define void @mul_4xi8(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_4xi8:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X86-NEXT: pxor %xmm2, %xmm2
; X86-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; X86-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X86-NEXT: pmullw %xmm0, %xmm1
; X86-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X86-NEXT: movdqu %xmm1, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_4xi8:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X64-NEXT: pxor %xmm2, %xmm2
; X64-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; X64-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X64-NEXT: pmullw %xmm0, %xmm1
; X64-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X64-NEXT: movdqu %xmm1, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <4 x i8>*
%wide.load = load <4 x i8>, <4 x i8>* %tmp7, align 1
%tmp8 = zext <4 x i8> %wide.load to <4 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <4 x i8>*
%wide.load17 = load <4 x i8>, <4 x i8>* %tmp11, align 1
%tmp12 = zext <4 x i8> %wide.load17 to <4 x i32>
%tmp13 = mul nuw nsw <4 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <4 x i32>*
store <4 x i32> %tmp13, <4 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <8 x i8>
; %op1 = zext<8 x i32> %val1
; %val2 = load <8 x i8>
; %op2 = zext<8 x i32> %val2
; %rst = mul <8 x i32> %op1, %op2
;
define void @mul_8xi8(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_8xi8:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
; X86-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; X86-NEXT: pxor %xmm2, %xmm2
; X86-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; X86-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X86-NEXT: pmullw %xmm0, %xmm1
; X86-NEXT: movdqa %xmm1, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X86-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X86-NEXT: movdqu %xmm1, 16(%esi,%ecx,4)
; X86-NEXT: movdqu %xmm0, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_8xi8:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
; X64-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; X64-NEXT: pxor %xmm2, %xmm2
; X64-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; X64-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X64-NEXT: pmullw %xmm0, %xmm1
; X64-NEXT: movdqa %xmm1, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X64-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X64-NEXT: movdqu %xmm1, 16(%rax,%rdx,4)
; X64-NEXT: movdqu %xmm0, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <8 x i8>*
%wide.load = load <8 x i8>, <8 x i8>* %tmp7, align 1
%tmp8 = zext <8 x i8> %wide.load to <8 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <8 x i8>*
%wide.load17 = load <8 x i8>, <8 x i8>* %tmp11, align 1
%tmp12 = zext <8 x i8> %wide.load17 to <8 x i32>
%tmp13 = mul nuw nsw <8 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <8 x i32>*
store <8 x i32> %tmp13, <8 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <16 x i8>
; %op1 = zext<16 x i32> %val1
; %val2 = load <16 x i8>
; %op2 = zext<16 x i32> %val2
; %rst = mul <16 x i32> %op1, %op2
;
define void @mul_16xi8(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_16xi8:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movdqu (%edx,%ecx), %xmm0
; X86-NEXT: movdqu (%eax,%ecx), %xmm1
; X86-NEXT: pxor %xmm2, %xmm2
; X86-NEXT: movdqa %xmm0, %xmm3
; X86-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; X86-NEXT: movdqa %xmm1, %xmm4
; X86-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
; X86-NEXT: pmullw %xmm3, %xmm4
; X86-NEXT: movdqa %xmm4, %xmm3
; X86-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3]
; X86-NEXT: punpckhwd {{.*#+}} xmm4 = xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
; X86-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8],xmm2[8],xmm0[9],xmm2[9],xmm0[10],xmm2[10],xmm0[11],xmm2[11],xmm0[12],xmm2[12],xmm0[13],xmm2[13],xmm0[14],xmm2[14],xmm0[15],xmm2[15]
; X86-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8],xmm2[8],xmm1[9],xmm2[9],xmm1[10],xmm2[10],xmm1[11],xmm2[11],xmm1[12],xmm2[12],xmm1[13],xmm2[13],xmm1[14],xmm2[14],xmm1[15],xmm2[15]
; X86-NEXT: pmullw %xmm0, %xmm1
; X86-NEXT: movdqa %xmm1, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X86-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X86-NEXT: movdqu %xmm1, 48(%esi,%ecx,4)
; X86-NEXT: movdqu %xmm0, 32(%esi,%ecx,4)
; X86-NEXT: movdqu %xmm4, 16(%esi,%ecx,4)
; X86-NEXT: movdqu %xmm3, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_16xi8:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movdqu (%rdi,%rdx), %xmm0
; X64-NEXT: movdqu (%rsi,%rdx), %xmm1
; X64-NEXT: pxor %xmm2, %xmm2
; X64-NEXT: movdqa %xmm0, %xmm3
; X64-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; X64-NEXT: movdqa %xmm1, %xmm4
; X64-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
; X64-NEXT: pmullw %xmm3, %xmm4
; X64-NEXT: movdqa %xmm4, %xmm3
; X64-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3]
; X64-NEXT: punpckhwd {{.*#+}} xmm4 = xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
; X64-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8],xmm2[8],xmm0[9],xmm2[9],xmm0[10],xmm2[10],xmm0[11],xmm2[11],xmm0[12],xmm2[12],xmm0[13],xmm2[13],xmm0[14],xmm2[14],xmm0[15],xmm2[15]
; X64-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8],xmm2[8],xmm1[9],xmm2[9],xmm1[10],xmm2[10],xmm1[11],xmm2[11],xmm1[12],xmm2[12],xmm1[13],xmm2[13],xmm1[14],xmm2[14],xmm1[15],xmm2[15]
; X64-NEXT: pmullw %xmm0, %xmm1
; X64-NEXT: movdqa %xmm1, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X64-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X64-NEXT: movdqu %xmm1, 48(%rax,%rdx,4)
; X64-NEXT: movdqu %xmm0, 32(%rax,%rdx,4)
; X64-NEXT: movdqu %xmm4, 16(%rax,%rdx,4)
; X64-NEXT: movdqu %xmm3, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <16 x i8>*
%wide.load = load <16 x i8>, <16 x i8>* %tmp7, align 1
%tmp8 = zext <16 x i8> %wide.load to <16 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <16 x i8>*
%wide.load17 = load <16 x i8>, <16 x i8>* %tmp11, align 1
%tmp12 = zext <16 x i8> %wide.load17 to <16 x i32>
%tmp13 = mul nuw nsw <16 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <16 x i32>*
store <16 x i32> %tmp13, <16 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <2 x i16>
; %op1 = zext<2 x i32> %val1
; %val2 = load <2 x i16>
; %op2 = zext<2 x i32> %val2
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi16(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi16:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X86-NEXT: movdqa %xmm1, %xmm2
; X86-NEXT: pmulhuw %xmm0, %xmm2
; X86-NEXT: pmullw %xmm0, %xmm1
; X86-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X86-NEXT: movq %xmm1, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi16:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X64-NEXT: movdqa %xmm1, %xmm2
; X64-NEXT: pmulhuw %xmm0, %xmm2
; X64-NEXT: pmullw %xmm0, %xmm1
; X64-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X64-NEXT: movq %xmm1, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i16>*
%wide.load = load <2 x i16>, <2 x i16>* %tmp7, align 1
%tmp8 = zext <2 x i16> %wide.load to <2 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <2 x i16>*
%wide.load17 = load <2 x i16>, <2 x i16>* %tmp11, align 1
%tmp12 = zext <2 x i16> %wide.load17 to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <4 x i16>
; %op1 = zext<4 x i32> %val1
; %val2 = load <4 x i16>
; %op2 = zext<4 x i32> %val2
; %rst = mul <4 x i32> %op1, %op2
;
define void @mul_4xi16(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_4xi16:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
; X86-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; X86-NEXT: movdqa %xmm1, %xmm2
; X86-NEXT: pmulhuw %xmm0, %xmm2
; X86-NEXT: pmullw %xmm0, %xmm1
; X86-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X86-NEXT: movdqu %xmm1, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_4xi16:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
; X64-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; X64-NEXT: movdqa %xmm1, %xmm2
; X64-NEXT: pmulhuw %xmm0, %xmm2
; X64-NEXT: pmullw %xmm0, %xmm1
; X64-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X64-NEXT: movdqu %xmm1, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <4 x i16>*
%wide.load = load <4 x i16>, <4 x i16>* %tmp7, align 1
%tmp8 = zext <4 x i16> %wide.load to <4 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <4 x i16>*
%wide.load17 = load <4 x i16>, <4 x i16>* %tmp11, align 1
%tmp12 = zext <4 x i16> %wide.load17 to <4 x i32>
%tmp13 = mul nuw nsw <4 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <4 x i32>*
store <4 x i32> %tmp13, <4 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <8 x i16>
; %op1 = zext<8 x i32> %val1
; %val2 = load <8 x i16>
; %op2 = zext<8 x i32> %val2
; %rst = mul <8 x i32> %op1, %op2
;
define void @mul_8xi16(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_8xi16:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movdqu (%edx,%ecx), %xmm0
; X86-NEXT: movdqu (%eax,%ecx), %xmm1
; X86-NEXT: movdqa %xmm1, %xmm2
; X86-NEXT: pmulhuw %xmm0, %xmm2
; X86-NEXT: pmullw %xmm0, %xmm1
; X86-NEXT: movdqa %xmm1, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X86-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X86-NEXT: movdqu %xmm1, 16(%esi,%ecx,4)
; X86-NEXT: movdqu %xmm0, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_8xi16:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movdqu (%rdi,%rdx), %xmm0
; X64-NEXT: movdqu (%rsi,%rdx), %xmm1
; X64-NEXT: movdqa %xmm1, %xmm2
; X64-NEXT: pmulhuw %xmm0, %xmm2
; X64-NEXT: pmullw %xmm0, %xmm1
; X64-NEXT: movdqa %xmm1, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X64-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X64-NEXT: movdqu %xmm1, 16(%rax,%rdx,4)
; X64-NEXT: movdqu %xmm0, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <8 x i16>*
%wide.load = load <8 x i16>, <8 x i16>* %tmp7, align 1
%tmp8 = zext <8 x i16> %wide.load to <8 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <8 x i16>*
%wide.load17 = load <8 x i16>, <8 x i16>* %tmp11, align 1
%tmp12 = zext <8 x i16> %wide.load17 to <8 x i32>
%tmp13 = mul nuw nsw <8 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <8 x i32>*
store <8 x i32> %tmp13, <8 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <16 x i16>
; %op1 = zext<16 x i32> %val1
; %val2 = load <16 x i16>
; %op2 = zext<16 x i32> %val2
; %rst = mul <16 x i32> %op1, %op2
;
define void @mul_16xi16(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_16xi16:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movdqu (%edx,%ecx), %xmm0
; X86-NEXT: movdqu 16(%edx,%ecx), %xmm1
; X86-NEXT: movdqu (%eax,%ecx), %xmm2
; X86-NEXT: movdqu 16(%eax,%ecx), %xmm3
; X86-NEXT: movdqa %xmm2, %xmm4
; X86-NEXT: pmulhuw %xmm0, %xmm4
; X86-NEXT: pmullw %xmm0, %xmm2
; X86-NEXT: movdqa %xmm2, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
; X86-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
; X86-NEXT: movdqa %xmm3, %xmm4
; X86-NEXT: pmulhuw %xmm1, %xmm4
; X86-NEXT: pmullw %xmm1, %xmm3
; X86-NEXT: movdqa %xmm3, %xmm1
; X86-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
; X86-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
; X86-NEXT: movdqu %xmm3, 48(%esi,%ecx,4)
; X86-NEXT: movdqu %xmm1, 32(%esi,%ecx,4)
; X86-NEXT: movdqu %xmm2, 16(%esi,%ecx,4)
; X86-NEXT: movdqu %xmm0, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_16xi16:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movdqu (%rdi,%rdx), %xmm0
; X64-NEXT: movdqu 16(%rdi,%rdx), %xmm1
; X64-NEXT: movdqu (%rsi,%rdx), %xmm2
; X64-NEXT: movdqu 16(%rsi,%rdx), %xmm3
; X64-NEXT: movdqa %xmm2, %xmm4
; X64-NEXT: pmulhuw %xmm0, %xmm4
; X64-NEXT: pmullw %xmm0, %xmm2
; X64-NEXT: movdqa %xmm2, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
; X64-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
; X64-NEXT: movdqa %xmm3, %xmm4
; X64-NEXT: pmulhuw %xmm1, %xmm4
; X64-NEXT: pmullw %xmm1, %xmm3
; X64-NEXT: movdqa %xmm3, %xmm1
; X64-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
; X64-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
; X64-NEXT: movdqu %xmm3, 48(%rax,%rdx,4)
; X64-NEXT: movdqu %xmm1, 32(%rax,%rdx,4)
; X64-NEXT: movdqu %xmm2, 16(%rax,%rdx,4)
; X64-NEXT: movdqu %xmm0, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <16 x i16>*
%wide.load = load <16 x i16>, <16 x i16>* %tmp7, align 1
%tmp8 = zext <16 x i16> %wide.load to <16 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <16 x i16>*
%wide.load17 = load <16 x i16>, <16 x i16>* %tmp11, align 1
%tmp12 = zext <16 x i16> %wide.load17 to <16 x i32>
%tmp13 = mul nuw nsw <16 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <16 x i32>*
store <16 x i32> %tmp13, <16 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <2 x i8>
; %op1 = sext<2 x i32> %val1
; %val2 = load <2 x i8>
; %op2 = sext<2 x i32> %val2
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi8_sext(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi8_sext:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movzwl (%edx,%ecx), %edx
; X86-NEXT: movd %edx, %xmm0
; X86-NEXT: movzwl (%eax,%ecx), %eax
; X86-NEXT: movd %eax, %xmm1
; X86-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X86-NEXT: psraw $8, %xmm0
; X86-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X86-NEXT: psraw $8, %xmm1
; X86-NEXT: pmullw %xmm0, %xmm1
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X86-NEXT: psrad $16, %xmm0
; X86-NEXT: movq %xmm0, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi8_sext:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movzwl (%rdi,%rdx), %ecx
; X64-NEXT: movd %ecx, %xmm0
; X64-NEXT: movzwl (%rsi,%rdx), %ecx
; X64-NEXT: movd %ecx, %xmm1
; X64-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X64-NEXT: psraw $8, %xmm0
; X64-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X64-NEXT: psraw $8, %xmm1
; X64-NEXT: pmullw %xmm0, %xmm1
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X64-NEXT: psrad $16, %xmm0
; X64-NEXT: movq %xmm0, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i8>*
%wide.load = load <2 x i8>, <2 x i8>* %tmp7, align 1
%tmp8 = sext <2 x i8> %wide.load to <2 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <2 x i8>*
%wide.load17 = load <2 x i8>, <2 x i8>* %tmp11, align 1
%tmp12 = sext <2 x i8> %wide.load17 to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <2 x i8>
; %op1 = sext<2 x i32> %val1
; %val2 = load <2 x i8>
; %op2 = zext<2 x i32> %val2
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi8_sext_zext(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi8_sext_zext:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movzwl (%edx,%ecx), %edx
; X86-NEXT: movd %edx, %xmm0
; X86-NEXT: movzwl (%eax,%ecx), %eax
; X86-NEXT: movd %eax, %xmm1
; X86-NEXT: pxor %xmm2, %xmm2
; X86-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X86-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X86-NEXT: psraw $8, %xmm0
; X86-NEXT: movdqa %xmm1, %xmm2
; X86-NEXT: pmulhw %xmm0, %xmm2
; X86-NEXT: pmullw %xmm1, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X86-NEXT: movq %xmm0, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi8_sext_zext:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movzwl (%rdi,%rdx), %ecx
; X64-NEXT: movd %ecx, %xmm0
; X64-NEXT: movzwl (%rsi,%rdx), %ecx
; X64-NEXT: movd %ecx, %xmm1
; X64-NEXT: pxor %xmm2, %xmm2
; X64-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; X64-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X64-NEXT: psraw $8, %xmm0
; X64-NEXT: movdqa %xmm1, %xmm2
; X64-NEXT: pmulhw %xmm0, %xmm2
; X64-NEXT: pmullw %xmm1, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X64-NEXT: movq %xmm0, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i8>*
%wide.load = load <2 x i8>, <2 x i8>* %tmp7, align 1
%tmp8 = sext <2 x i8> %wide.load to <2 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <2 x i8>*
%wide.load17 = load <2 x i8>, <2 x i8>* %tmp11, align 1
%tmp12 = zext <2 x i8> %wide.load17 to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <2 x i16>
; %op1 = sext<2 x i32> %val1
; %val2 = load <2 x i16>
; %op2 = sext<2 x i32> %val2
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi16_sext(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi16_sext:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X86-NEXT: movdqa %xmm1, %xmm2
; X86-NEXT: pmulhw %xmm0, %xmm2
; X86-NEXT: pmullw %xmm0, %xmm1
; X86-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X86-NEXT: movq %xmm1, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi16_sext:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X64-NEXT: movdqa %xmm1, %xmm2
; X64-NEXT: pmulhw %xmm0, %xmm2
; X64-NEXT: pmullw %xmm0, %xmm1
; X64-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X64-NEXT: movq %xmm1, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i16>*
%wide.load = load <2 x i16>, <2 x i16>* %tmp7, align 1
%tmp8 = sext <2 x i16> %wide.load to <2 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <2 x i16>*
%wide.load17 = load <2 x i16>, <2 x i16>* %tmp11, align 1
%tmp12 = sext <2 x i16> %wide.load17 to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <2 x i16>
; %op1 = sext<2 x i32> %val1
; %val2 = load <2 x i16>
; %op2 = zext<2 x i32> %val2
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi16_sext_zext(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi16_sext_zext:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,0,2,1,4,5,6,7]
; X86-NEXT: psrad $16, %xmm0
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
; X86-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X86-NEXT: pxor %xmm2, %xmm2
; X86-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X86-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,1,1,3]
; X86-NEXT: movdqa %xmm1, %xmm2
; X86-NEXT: psrlq $32, %xmm2
; X86-NEXT: pmuludq %xmm0, %xmm2
; X86-NEXT: movdqa %xmm0, %xmm3
; X86-NEXT: psrlq $32, %xmm3
; X86-NEXT: pmuludq %xmm1, %xmm3
; X86-NEXT: paddq %xmm2, %xmm3
; X86-NEXT: psllq $32, %xmm3
; X86-NEXT: pmuludq %xmm0, %xmm1
; X86-NEXT: paddq %xmm3, %xmm1
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
; X86-NEXT: movq %xmm0, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi16_sext_zext:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,0,2,1,4,5,6,7]
; X64-NEXT: psrad $16, %xmm0
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
; X64-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X64-NEXT: pxor %xmm2, %xmm2
; X64-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,1,1,3]
; X64-NEXT: movdqa %xmm1, %xmm2
; X64-NEXT: psrlq $32, %xmm2
; X64-NEXT: pmuludq %xmm0, %xmm2
; X64-NEXT: movdqa %xmm0, %xmm3
; X64-NEXT: psrlq $32, %xmm3
; X64-NEXT: pmuludq %xmm1, %xmm3
; X64-NEXT: paddq %xmm2, %xmm3
; X64-NEXT: psllq $32, %xmm3
; X64-NEXT: pmuludq %xmm0, %xmm1
; X64-NEXT: paddq %xmm3, %xmm1
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
; X64-NEXT: movq %xmm0, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i16>*
%wide.load = load <2 x i16>, <2 x i16>* %tmp7, align 1
%tmp8 = sext <2 x i16> %wide.load to <2 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <2 x i16>*
%wide.load17 = load <2 x i16>, <2 x i16>* %tmp11, align 1
%tmp12 = zext <2 x i16> %wide.load17 to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val1 = load <16 x i16>
; %op1 = sext<16 x i32> %val1
; %val2 = load <16 x i16>
; %op2 = sext<16 x i32> %val2
; %rst = mul <16 x i32> %op1, %op2
;
define void @mul_16xi16_sext(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_16xi16_sext:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl c, %esi
; X86-NEXT: movdqu (%edx,%ecx), %xmm0
; X86-NEXT: movdqu 16(%edx,%ecx), %xmm1
; X86-NEXT: movdqu (%eax,%ecx), %xmm2
; X86-NEXT: movdqu 16(%eax,%ecx), %xmm3
; X86-NEXT: movdqa %xmm2, %xmm4
; X86-NEXT: pmulhw %xmm0, %xmm4
; X86-NEXT: pmullw %xmm0, %xmm2
; X86-NEXT: movdqa %xmm2, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
; X86-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
; X86-NEXT: movdqa %xmm3, %xmm4
; X86-NEXT: pmulhw %xmm1, %xmm4
; X86-NEXT: pmullw %xmm1, %xmm3
; X86-NEXT: movdqa %xmm3, %xmm1
; X86-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
; X86-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
; X86-NEXT: movdqu %xmm3, 48(%esi,%ecx,4)
; X86-NEXT: movdqu %xmm1, 32(%esi,%ecx,4)
; X86-NEXT: movdqu %xmm2, 16(%esi,%ecx,4)
; X86-NEXT: movdqu %xmm0, (%esi,%ecx,4)
; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: mul_16xi16_sext:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movdqu (%rdi,%rdx), %xmm0
; X64-NEXT: movdqu 16(%rdi,%rdx), %xmm1
; X64-NEXT: movdqu (%rsi,%rdx), %xmm2
; X64-NEXT: movdqu 16(%rsi,%rdx), %xmm3
; X64-NEXT: movdqa %xmm2, %xmm4
; X64-NEXT: pmulhw %xmm0, %xmm4
; X64-NEXT: pmullw %xmm0, %xmm2
; X64-NEXT: movdqa %xmm2, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
; X64-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
; X64-NEXT: movdqa %xmm3, %xmm4
; X64-NEXT: pmulhw %xmm1, %xmm4
; X64-NEXT: pmullw %xmm1, %xmm3
; X64-NEXT: movdqa %xmm3, %xmm1
; X64-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
; X64-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
; X64-NEXT: movdqu %xmm3, 48(%rax,%rdx,4)
; X64-NEXT: movdqu %xmm1, 32(%rax,%rdx,4)
; X64-NEXT: movdqu %xmm2, 16(%rax,%rdx,4)
; X64-NEXT: movdqu %xmm0, (%rax,%rdx,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <16 x i16>*
%wide.load = load <16 x i16>, <16 x i16>* %tmp7, align 1
%tmp8 = sext <16 x i16> %wide.load to <16 x i32>
%tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
%tmp11 = bitcast i8* %tmp10 to <16 x i16>*
%wide.load17 = load <16 x i16>, <16 x i16>* %tmp11, align 1
%tmp12 = sext <16 x i16> %wide.load17 to <16 x i32>
%tmp13 = mul nuw nsw <16 x i32> %tmp12, %tmp8
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <16 x i32>*
store <16 x i32> %tmp13, <16 x i32>* %tmp15, align 4
ret void
}
; %val = load <2 x i8>
; %op1 = zext<2 x i32> %val
; %op2 = const <2 x i32> {c1, c2} // c1 and c2 are within (0 ~ 255)
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi8_varconst1(i8* nocapture readonly %a, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi8_varconst1:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl c, %edx
; X86-NEXT: movzwl (%ecx,%eax), %ecx
; X86-NEXT: movd %ecx, %xmm0
; X86-NEXT: pxor %xmm1, %xmm1
; X86-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; X86-NEXT: pmullw {{\.LCPI.*}}, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X86-NEXT: movq %xmm0, (%edx,%eax,4)
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi8_varconst1:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movzwl (%rdi,%rsi), %ecx
; X64-NEXT: movd %ecx, %xmm0
; X64-NEXT: pxor %xmm1, %xmm1
; X64-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; X64-NEXT: pmullw {{.*}}(%rip), %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X64-NEXT: movq %xmm0, (%rax,%rsi,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i8>*
%wide.load = load <2 x i8>, <2 x i8>* %tmp7, align 1
%tmp8 = zext <2 x i8> %wide.load to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp8, <i32 0, i32 255>
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val = load <2 x i8>
; %op1 = sext<2 x i32> %val
; %op2 = const <2 x i32> {c1, c2} // c1 and c2 are within (-128 ~ 127)
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi8_varconst2(i8* nocapture readonly %a, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi8_varconst2:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl c, %edx
; X86-NEXT: movzwl (%ecx,%eax), %ecx
; X86-NEXT: movd %ecx, %xmm0
; X86-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X86-NEXT: psraw $8, %xmm0
; X86-NEXT: pmullw {{\.LCPI.*}}, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; X86-NEXT: psrad $16, %xmm0
; X86-NEXT: movq %xmm0, (%edx,%eax,4)
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi8_varconst2:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movzwl (%rdi,%rsi), %ecx
; X64-NEXT: movd %ecx, %xmm0
; X64-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X64-NEXT: psraw $8, %xmm0
; X64-NEXT: pmullw {{.*}}(%rip), %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; X64-NEXT: psrad $16, %xmm0
; X64-NEXT: movq %xmm0, (%rax,%rsi,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i8>*
%wide.load = load <2 x i8>, <2 x i8>* %tmp7, align 1
%tmp8 = sext <2 x i8> %wide.load to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp8, <i32 -128, i32 127>
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val = load <2 x i8>
; %op1 = zext<2 x i32> %val
; %op2 = const <2 x i32> {c1, c2} // c1 and c2 are within (0 ~ 256)
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi8_varconst3(i8* nocapture readonly %a, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi8_varconst3:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl c, %edx
; X86-NEXT: movzwl (%ecx,%eax), %ecx
; X86-NEXT: movd %ecx, %xmm0
; X86-NEXT: pxor %xmm1, %xmm1
; X86-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; X86-NEXT: movdqa {{.*#+}} xmm1 = <0,256,u,u,u,u,u,u>
; X86-NEXT: movdqa %xmm0, %xmm2
; X86-NEXT: pmulhw %xmm1, %xmm2
; X86-NEXT: pmullw %xmm1, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X86-NEXT: movq %xmm0, (%edx,%eax,4)
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi8_varconst3:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movzwl (%rdi,%rsi), %ecx
; X64-NEXT: movd %ecx, %xmm0
; X64-NEXT: pxor %xmm1, %xmm1
; X64-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; X64-NEXT: movdqa {{.*#+}} xmm1 = <0,256,u,u,u,u,u,u>
; X64-NEXT: movdqa %xmm0, %xmm2
; X64-NEXT: pmulhw %xmm1, %xmm2
; X64-NEXT: pmullw %xmm1, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X64-NEXT: movq %xmm0, (%rax,%rsi,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i8>*
%wide.load = load <2 x i8>, <2 x i8>* %tmp7, align 1
%tmp8 = zext <2 x i8> %wide.load to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp8, <i32 0, i32 256>
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val = load <2 x i8>
; %op1 = zext<2 x i32> %val
; %op2 = const <2 x i32> {c1, c2} // c1 and c2 are within (-1 ~ 255)
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi8_varconst4(i8* nocapture readonly %a, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi8_varconst4:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl c, %edx
; X86-NEXT: movzwl (%ecx,%eax), %ecx
; X86-NEXT: movd %ecx, %xmm0
; X86-NEXT: pxor %xmm1, %xmm1
; X86-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; X86-NEXT: movdqa {{.*#+}} xmm1 = <65535,255,u,u,u,u,u,u>
; X86-NEXT: movdqa %xmm0, %xmm2
; X86-NEXT: pmulhw %xmm1, %xmm2
; X86-NEXT: pmullw %xmm1, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X86-NEXT: movq %xmm0, (%edx,%eax,4)
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi8_varconst4:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movzwl (%rdi,%rsi), %ecx
; X64-NEXT: movd %ecx, %xmm0
; X64-NEXT: pxor %xmm1, %xmm1
; X64-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; X64-NEXT: movdqa {{.*#+}} xmm1 = <65535,255,u,u,u,u,u,u>
; X64-NEXT: movdqa %xmm0, %xmm2
; X64-NEXT: pmulhw %xmm1, %xmm2
; X64-NEXT: pmullw %xmm1, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X64-NEXT: movq %xmm0, (%rax,%rsi,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i8>*
%wide.load = load <2 x i8>, <2 x i8>* %tmp7, align 1
%tmp8 = zext <2 x i8> %wide.load to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp8, <i32 -1, i32 255>
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val = load <2 x i8>
; %op1 = sext<2 x i32> %val
; %op2 = const <2 x i32> {c1, c2} // c1 and c2 are within (-129 ~ 127)
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi8_varconst5(i8* nocapture readonly %a, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi8_varconst5:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl c, %edx
; X86-NEXT: movzwl (%ecx,%eax), %ecx
; X86-NEXT: movd %ecx, %xmm0
; X86-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X86-NEXT: psraw $8, %xmm0
; X86-NEXT: movdqa {{.*#+}} xmm1 = <65407,127,u,u,u,u,u,u>
; X86-NEXT: movdqa %xmm0, %xmm2
; X86-NEXT: pmulhw %xmm1, %xmm2
; X86-NEXT: pmullw %xmm1, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X86-NEXT: movq %xmm0, (%edx,%eax,4)
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi8_varconst5:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movzwl (%rdi,%rsi), %ecx
; X64-NEXT: movd %ecx, %xmm0
; X64-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X64-NEXT: psraw $8, %xmm0
; X64-NEXT: movdqa {{.*#+}} xmm1 = <65407,127,u,u,u,u,u,u>
; X64-NEXT: movdqa %xmm0, %xmm2
; X64-NEXT: pmulhw %xmm1, %xmm2
; X64-NEXT: pmullw %xmm1, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X64-NEXT: movq %xmm0, (%rax,%rsi,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i8>*
%wide.load = load <2 x i8>, <2 x i8>* %tmp7, align 1
%tmp8 = sext <2 x i8> %wide.load to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp8, <i32 -129, i32 127>
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val = load <2 x i8>
; %op1 = sext<2 x i32> %val
; %op2 = const <2 x i32> {c1, c2} // c1 and c2 are within (-128 ~ 128)
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi8_varconst6(i8* nocapture readonly %a, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi8_varconst6:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl c, %edx
; X86-NEXT: movzwl (%ecx,%eax), %ecx
; X86-NEXT: movd %ecx, %xmm0
; X86-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X86-NEXT: psraw $8, %xmm0
; X86-NEXT: movdqa {{.*#+}} xmm1 = <65408,128,u,u,u,u,u,u>
; X86-NEXT: movdqa %xmm0, %xmm2
; X86-NEXT: pmulhw %xmm1, %xmm2
; X86-NEXT: pmullw %xmm1, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X86-NEXT: movq %xmm0, (%edx,%eax,4)
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi8_varconst6:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movzwl (%rdi,%rsi), %ecx
; X64-NEXT: movd %ecx, %xmm0
; X64-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X64-NEXT: psraw $8, %xmm0
; X64-NEXT: movdqa {{.*#+}} xmm1 = <65408,128,u,u,u,u,u,u>
; X64-NEXT: movdqa %xmm0, %xmm2
; X64-NEXT: pmulhw %xmm1, %xmm2
; X64-NEXT: pmullw %xmm1, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X64-NEXT: movq %xmm0, (%rax,%rsi,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i8>*
%wide.load = load <2 x i8>, <2 x i8>* %tmp7, align 1
%tmp8 = sext <2 x i8> %wide.load to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp8, <i32 -128, i32 128>
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val = load <2 x i16>
; %op1 = zext<2 x i32> %val
; %op2 = const <2 x i32> {c1, c2} // c1 and c2 are within (0 ~ 65535)
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi16_varconst1(i8* nocapture readonly %a, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi16_varconst1:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl c, %edx
; X86-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-NEXT: movdqa {{.*#+}} xmm1 = <0,65535,u,u,u,u,u,u>
; X86-NEXT: movdqa %xmm0, %xmm2
; X86-NEXT: pmulhuw %xmm1, %xmm2
; X86-NEXT: pmullw %xmm1, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X86-NEXT: movq %xmm0, (%edx,%eax,4)
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi16_varconst1:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: movdqa {{.*#+}} xmm1 = <0,65535,u,u,u,u,u,u>
; X64-NEXT: movdqa %xmm0, %xmm2
; X64-NEXT: pmulhuw %xmm1, %xmm2
; X64-NEXT: pmullw %xmm1, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X64-NEXT: movq %xmm0, (%rax,%rsi,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i16>*
%wide.load = load <2 x i16>, <2 x i16>* %tmp7, align 1
%tmp8 = zext <2 x i16> %wide.load to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp8, <i32 0, i32 65535>
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val = load <2 x i16>
; %op1 = sext<2 x i32> %val
; %op2 = const <2 x i32> {c1, c2} // c1 and c2 are within (-32768 ~ 32767)
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi16_varconst2(i8* nocapture readonly %a, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi16_varconst2:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl c, %edx
; X86-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-NEXT: movdqa {{.*#+}} xmm1 = <32768,32767,u,u,u,u,u,u>
; X86-NEXT: movdqa %xmm0, %xmm2
; X86-NEXT: pmulhw %xmm1, %xmm2
; X86-NEXT: pmullw %xmm1, %xmm0
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X86-NEXT: movq %xmm0, (%edx,%eax,4)
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi16_varconst2:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: movdqa {{.*#+}} xmm1 = <32768,32767,u,u,u,u,u,u>
; X64-NEXT: movdqa %xmm0, %xmm2
; X64-NEXT: pmulhw %xmm1, %xmm2
; X64-NEXT: pmullw %xmm1, %xmm0
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; X64-NEXT: movq %xmm0, (%rax,%rsi,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i16>*
%wide.load = load <2 x i16>, <2 x i16>* %tmp7, align 1
%tmp8 = sext <2 x i16> %wide.load to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp8, <i32 -32768, i32 32767>
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val = load <2 x i16>
; %op1 = zext<2 x i32> %val
; %op2 = const <2 x i32> {c1, c2} // c1 and c2 are within (0 ~ 65536)
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi16_varconst3(i8* nocapture readonly %a, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi16_varconst3:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl c, %edx
; X86-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-NEXT: pxor %xmm1, %xmm1
; X86-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
; X86-NEXT: movdqa {{.*#+}} xmm1 = [0,0,65536,0]
; X86-NEXT: movdqa %xmm0, %xmm2
; X86-NEXT: pmuludq %xmm1, %xmm2
; X86-NEXT: psrlq $32, %xmm0
; X86-NEXT: pmuludq %xmm1, %xmm0
; X86-NEXT: psllq $32, %xmm0
; X86-NEXT: paddq %xmm2, %xmm0
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; X86-NEXT: movq %xmm0, (%edx,%eax,4)
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi16_varconst3:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: pxor %xmm1, %xmm1
; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
; X64-NEXT: movl $65536, %ecx # imm = 0x10000
; X64-NEXT: movq %rcx, %xmm1
; X64-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7]
; X64-NEXT: movdqa %xmm0, %xmm2
; X64-NEXT: pmuludq %xmm1, %xmm2
; X64-NEXT: psrlq $32, %xmm0
; X64-NEXT: pmuludq %xmm1, %xmm0
; X64-NEXT: psllq $32, %xmm0
; X64-NEXT: paddq %xmm2, %xmm0
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; X64-NEXT: movq %xmm0, (%rax,%rsi,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i16>*
%wide.load = load <2 x i16>, <2 x i16>* %tmp7, align 1
%tmp8 = zext <2 x i16> %wide.load to <2 x i32>
[X86] Add VPADD instructions to X86InstrInfo::isAssociativeAndCommutative. llvm-svn: 275769
2016-07-18 14:14:54 +08:00
%tmp13 = mul nuw nsw <2 x i32> %tmp8, <i32 0, i32 65536>
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
; %val = load <2 x i16>
; %op1 = sext<2 x i32> %val
; %op2 = const <2 x i32> {c1, c2} // c1 and c2 are within (0 ~ 32768)
; %rst = mul <2 x i32> %op1, %op2
;
define void @mul_2xi16_varconst4(i8* nocapture readonly %a, i64 %index) {
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-LABEL: mul_2xi16_varconst4:
[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
; X86: # %bb.0: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl c, %edx
; X86-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,0,2,1,4,5,6,7]
; X86-NEXT: psrad $16, %xmm0
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
; X86-NEXT: movdqa {{.*#+}} xmm1 = [0,0,32768,0]
; X86-NEXT: movdqa %xmm0, %xmm2
; X86-NEXT: pmuludq %xmm1, %xmm2
; X86-NEXT: psrlq $32, %xmm0
; X86-NEXT: pmuludq %xmm1, %xmm0
; X86-NEXT: psllq $32, %xmm0
; X86-NEXT: paddq %xmm2, %xmm0
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; X86-NEXT: movq %xmm0, (%edx,%eax,4)
; X86-NEXT: retl
;
; X64-LABEL: mul_2xi16_varconst4:
[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: # %entry
[X86][SSE] Test vector imul reduction on 32 and 64-bit targets llvm-svn: 315824
2017-10-15 03:46:08 +08:00
; X64-NEXT: movq {{.*}}(%rip), %rax
; X64-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,0,2,1,4,5,6,7]
; X64-NEXT: psrad $16, %xmm0
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
; X64-NEXT: movl $32768, %ecx # imm = 0x8000
; X64-NEXT: movq %rcx, %xmm1
; X64-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7]
; X64-NEXT: movdqa %xmm0, %xmm2
; X64-NEXT: pmuludq %xmm1, %xmm2
; X64-NEXT: psrlq $32, %xmm0
; X64-NEXT: pmuludq %xmm1, %xmm0
; X64-NEXT: psllq $32, %xmm0
; X64-NEXT: paddq %xmm2, %xmm0
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; X64-NEXT: movq %xmm0, (%rax,%rsi,4)
; X64-NEXT: retq
[X86] Reduce the width of multiplification when its operands are extended from i8 or i16 For <N x i32> type mul, pmuludq will be used for targets without SSE41, which often introduces many extra pack and unpack instructions in vectorized loop body because pmuludq generates <N/2 x i64> type value. However when the operands of <N x i32> mul are extended from smaller size values like i8 and i16, the type of mul may be shrunk to use pmullw + pmulhw/pmulhuw instead of pmuludq, which generates better code. For targets with SSE41, pmulld is supported so no shrinking is needed. Differential Revision: http://reviews.llvm.org/D20931 llvm-svn: 272694
2016-06-15 02:53:20 +08:00
entry:
%pre = load i32*, i32** @c
%tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
%tmp7 = bitcast i8* %tmp6 to <2 x i16>*
%wide.load = load <2 x i16>, <2 x i16>* %tmp7, align 1
%tmp8 = sext <2 x i16> %wide.load to <2 x i32>
%tmp13 = mul nuw nsw <2 x i32> %tmp8, <i32 0, i32 32768>
%tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
%tmp15 = bitcast i32* %tmp14 to <2 x i32>*
store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
ret void
}
[X86][SSE] Don't attempt to reduce the imul vector width of odd sized vectors (PR34947) llvm-svn: 315825
2017-10-15 03:57:19 +08:00
;
; Illegal Types
;
define void @PR34947() {
; X86-LABEL: PR34947:
[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
; X86: # %bb.0:
[X86][SSE] Don't attempt to reduce the imul vector width of odd sized vectors (PR34947) llvm-svn: 315825
2017-10-15 03:57:19 +08:00
; X86-NEXT: movdqa (%eax), %xmm0
; X86-NEXT: pshufd {{.*#+}} xmm1 = xmm0[3,1,2,3]
; X86-NEXT: movd %xmm1, %ecx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: divl %ecx
; X86-NEXT: movd %edx, %xmm1
; X86-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; X86-NEXT: movd %xmm2, %ecx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: divl %ecx
; X86-NEXT: movd %edx, %xmm2
; X86-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; X86-NEXT: movd %xmm0, %ecx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: divl %ecx
; X86-NEXT: movd %edx, %xmm1
; X86-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; X86-NEXT: movd %xmm0, %ecx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: divl %ecx
; X86-NEXT: movd %edx, %xmm0
; X86-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; X86-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: divl (%eax)
; X86-NEXT: movd %edx, %xmm0
; X86-NEXT: movdqa {{.*#+}} xmm2 = [8199,8199,8199,8199]
; X86-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
; X86-NEXT: pmuludq %xmm2, %xmm1
; X86-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; X86-NEXT: pmuludq %xmm2, %xmm3
; X86-NEXT: pshufd {{.*#+}} xmm2 = xmm3[0,2,2,3]
; X86-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; X86-NEXT: movl $8199, %eax # imm = 0x2007
; X86-NEXT: movd %eax, %xmm2
; X86-NEXT: pmuludq %xmm0, %xmm2
; X86-NEXT: movd %xmm2, (%eax)
; X86-NEXT: movdqa %xmm1, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: PR34947:
[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][SSE] Don't attempt to reduce the imul vector width of odd sized vectors (PR34947) llvm-svn: 315825
2017-10-15 03:57:19 +08:00
; X64-NEXT: movdqa (%rax), %xmm0
; X64-NEXT: pshufd {{.*#+}} xmm1 = xmm0[3,1,2,3]
; X64-NEXT: movd %xmm1, %ecx
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: divl %ecx
; X64-NEXT: movd %edx, %xmm1
; X64-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; X64-NEXT: movd %xmm2, %ecx
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: divl %ecx
; X64-NEXT: movd %edx, %xmm2
; X64-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; X64-NEXT: movd %xmm0, %ecx
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: divl %ecx
; X64-NEXT: movd %edx, %xmm1
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; X64-NEXT: movd %xmm0, %ecx
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: divl %ecx
; X64-NEXT: movd %edx, %xmm0
; X64-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; X64-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: divl (%rax)
; X64-NEXT: movd %edx, %xmm0
; X64-NEXT: movdqa {{.*#+}} xmm2 = [8199,8199,8199,8199]
; X64-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
; X64-NEXT: pmuludq %xmm2, %xmm1
; X64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; X64-NEXT: pmuludq %xmm2, %xmm3
; X64-NEXT: pshufd {{.*#+}} xmm2 = xmm3[0,2,2,3]
; X64-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; X64-NEXT: movl $8199, %eax # imm = 0x2007
; X64-NEXT: movd %eax, %xmm2
; X64-NEXT: pmuludq %xmm0, %xmm2
; X64-NEXT: movd %xmm2, (%rax)
; X64-NEXT: movdqa %xmm1, (%rax)
; X64-NEXT: retq
%tmp = load <9 x i32>, <9 x i32>* undef, align 64
%rem = urem <9 x i32> zeroinitializer, %tmp
%mul = mul <9 x i32> <i32 8199, i32 8199, i32 8199, i32 8199, i32 8199, i32 8199, i32 8199, i32 8199, i32 8199>, %rem
store <9 x i32> %mul, <9 x i32>* undef, align 64
ret void
}