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/avx512vbmi2vl-intrinsics-up...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

1813 lines
104 KiB
LLVM
Raw Normal View History

[X86] Add test files for upgrade of vbmi2 expand load and compress store intrinsics that was done in r334381. llvm-svn: 334386
2018-06-11 14:20:24 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512vbmi2,+avx512vl --show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X86
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vbmi2,+avx512vl --show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X64
define <8 x i16> @test_mask_expand_load_w_128(i8* %addr, <8 x i16> %data, i8 %mask) {
; X86-LABEL: test_mask_expand_load_w_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vpexpandw (%eax), %xmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_load_w_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpexpandw (%rdi), %xmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.expand.load.w.128(i8* %addr, <8 x i16> %data, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_maskz_expand_load_w_128(i8* %addr, i8 %mask) {
; X86-LABEL: test_maskz_expand_load_w_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vpexpandw (%eax), %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_load_w_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpexpandw (%rdi), %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.expand.load.w.128(i8* %addr, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
}
declare <8 x i16> @llvm.x86.avx512.mask.expand.load.w.128(i8* %addr, <8 x i16> %data, i8 %mask)
define <8 x i16> @test_expand_load_w_128(i8* %addr, <8 x i16> %data) {
; X86-LABEL: test_expand_load_w_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT: vpexpandw (%eax), %xmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_expand_load_w_128:
; X64: # %bb.0:
; X64-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT: vpexpandw (%rdi), %xmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.expand.load.w.128(i8* %addr, <8 x i16> %data, i8 -1)
ret <8 x i16> %res
}
[X86] Add new variadic avx512 compress/expand intrinsics that use vXi1 types for the mask argument. Remove and autoupgrade the old intrinsics llvm-svn: 352343
2019-01-28 15:03:03 +08:00
define <8 x i16> @test_expand_w_128(<8 x i16> %data) {
; CHECK-LABEL: test_expand_w_128:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.expand.w.128(<8 x i16> %data, <8 x i16> undef, i8 -1)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_expand_w_128(<8 x i16> %data, <8 x i16> %passthru, i8 %mask) {
; X86-LABEL: test_mask_expand_w_128:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpexpandw %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0xc8]
; X86-NEXT: vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_w_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandw %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0xc8]
; X64-NEXT: vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.expand.w.128(<8 x i16> %data, <8 x i16> %passthru, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_maskz_expand_w_128(<8 x i16> %data, i8 %mask) {
; X86-LABEL: test_maskz_expand_w_128:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpexpandw %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x62,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_w_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandw %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x62,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.expand.w.128(<8 x i16> %data, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
}
declare <8 x i16> @llvm.x86.avx512.mask.expand.w.128(<8 x i16> %data, <8 x i16> %src0, i8 %mask)
[X86] Add test files for upgrade of vbmi2 expand load and compress store intrinsics that was done in r334381. llvm-svn: 334386
2018-06-11 14:20:24 +08:00
define <16 x i8> @test_mask_expand_load_b_128(i8* %addr, <16 x i8> %data, i16 %mask) {
; X86-LABEL: test_mask_expand_load_b_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpexpandb (%eax), %xmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_load_b_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpexpandb (%rdi), %xmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.expand.load.b.128(i8* %addr, <16 x i8> %data, i16 %mask)
ret <16 x i8> %res
}
define <16 x i8> @test_maskz_expand_load_b_128(i8* %addr, i16 %mask) {
; X86-LABEL: test_maskz_expand_load_b_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpexpandb (%eax), %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_load_b_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpexpandb (%rdi), %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.expand.load.b.128(i8* %addr, <16 x i8> zeroinitializer, i16 %mask)
ret <16 x i8> %res
}
declare <16 x i8> @llvm.x86.avx512.mask.expand.load.b.128(i8* %addr, <16 x i8> %data, i16 %mask)
define <16 x i8> @test_expand_load_b_128(i8* %addr, <16 x i8> %data) {
; X86-LABEL: test_expand_load_b_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT: vpexpandb (%eax), %xmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_expand_load_b_128:
; X64: # %bb.0:
; X64-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT: vpexpandb (%rdi), %xmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.expand.load.b.128(i8* %addr, <16 x i8> %data, i16 -1)
ret <16 x i8> %res
}
[X86] Add new variadic avx512 compress/expand intrinsics that use vXi1 types for the mask argument. Remove and autoupgrade the old intrinsics llvm-svn: 352343
2019-01-28 15:03:03 +08:00
define <16 x i8> @test_expand_b_128(<16 x i8> %data) {
; CHECK-LABEL: test_expand_b_128:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.expand.b.128(<16 x i8> %data, <16 x i8> undef, i16 -1)
ret <16 x i8> %res
}
define <16 x i8> @test_mask_expand_b_128(<16 x i8> %data, <16 x i8> %passthru, i16 %mask) {
; X86-LABEL: test_mask_expand_b_128:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpexpandb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0xc8]
; X86-NEXT: vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_b_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0xc8]
; X64-NEXT: vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.expand.b.128(<16 x i8> %data, <16 x i8> %passthru, i16 %mask)
ret <16 x i8> %res
}
define <16 x i8> @test_maskz_expand_b_128(<16 x i8> %data, i16 %mask) {
; X86-LABEL: test_maskz_expand_b_128:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpexpandb %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x62,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_b_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandb %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x62,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.expand.b.128(<16 x i8> %data, <16 x i8> zeroinitializer, i16 %mask)
ret <16 x i8> %res
}
declare <16 x i8> @llvm.x86.avx512.mask.expand.b.128(<16 x i8> %data, <16 x i8> %src0, i16 %mask)
[X86] Add test files for upgrade of vbmi2 expand load and compress store intrinsics that was done in r334381. llvm-svn: 334386
2018-06-11 14:20:24 +08:00
define void @test_mask_compress_store_w_128(i8* %addr, <8 x i16> %data, i8 %mask) {
; X86-LABEL: test_mask_compress_store_w_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vpcompressw %xmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_store_w_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpcompressw %xmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0x07]
; X64-NEXT: retq # encoding: [0xc3]
call void @llvm.x86.avx512.mask.compress.store.w.128(i8* %addr, <8 x i16> %data, i8 %mask)
ret void
}
declare void @llvm.x86.avx512.mask.compress.store.w.128(i8* %addr, <8 x i16> %data, i8 %mask)
define void @test_compress_store_w_128(i8* %addr, <8 x i16> %data) {
; X86-LABEL: test_compress_store_w_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT: vpcompressw %xmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_compress_store_w_128:
; X64: # %bb.0:
; X64-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT: vpcompressw %xmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0x07]
; X64-NEXT: retq # encoding: [0xc3]
call void @llvm.x86.avx512.mask.compress.store.w.128(i8* %addr, <8 x i16> %data, i8 -1)
ret void
}
[X86] Add new variadic avx512 compress/expand intrinsics that use vXi1 types for the mask argument. Remove and autoupgrade the old intrinsics llvm-svn: 352343
2019-01-28 15:03:03 +08:00
define <8 x i16> @test_mask_compress_w_128(<8 x i16> %data, <8 x i16> %passthru, i8 %mask) {
; X86-LABEL: test_mask_compress_w_128:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpcompressw %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0xc1]
; X86-NEXT: vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_w_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressw %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0xc1]
; X64-NEXT: vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.compress.w.128(<8 x i16> %data, <8 x i16> %passthru, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_maskz_compress_w_128(<8 x i16> %data, i8 %mask) {
; X86-LABEL: test_maskz_compress_w_128:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpcompressw %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x63,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_compress_w_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressw %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x63,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.compress.w.128(<8 x i16> %data, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_compress_w_128(<8 x i16> %data) {
; CHECK-LABEL: test_compress_w_128:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.compress.w.128(<8 x i16> %data, <8 x i16> undef, i8 -1)
ret <8 x i16> %res
}
declare <8 x i16> @llvm.x86.avx512.mask.compress.w.128(<8 x i16> %data, <8 x i16> %src0, i8 %mask)
[X86] Add test files for upgrade of vbmi2 expand load and compress store intrinsics that was done in r334381. llvm-svn: 334386
2018-06-11 14:20:24 +08:00
define void @test_mask_compress_store_b_128(i8* %addr, <16 x i8> %data, i16 %mask) {
; X86-LABEL: test_mask_compress_store_b_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpcompressb %xmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_store_b_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpcompressb %xmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0x07]
; X64-NEXT: retq # encoding: [0xc3]
call void @llvm.x86.avx512.mask.compress.store.b.128(i8* %addr, <16 x i8> %data, i16 %mask)
ret void
}
declare void @llvm.x86.avx512.mask.compress.store.b.128(i8* %addr, <16 x i8> %data, i16 %mask)
define void @test_compress_store_b_128(i8* %addr, <16 x i8> %data) {
; X86-LABEL: test_compress_store_b_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT: vpcompressb %xmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_compress_store_b_128:
; X64: # %bb.0:
; X64-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT: vpcompressb %xmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0x07]
; X64-NEXT: retq # encoding: [0xc3]
call void @llvm.x86.avx512.mask.compress.store.b.128(i8* %addr, <16 x i8> %data, i16 -1)
ret void
}
[X86] Add new variadic avx512 compress/expand intrinsics that use vXi1 types for the mask argument. Remove and autoupgrade the old intrinsics llvm-svn: 352343
2019-01-28 15:03:03 +08:00
define <16 x i8> @test_mask_compress_b_128(<16 x i8> %data, <16 x i8> %passthru, i16 %mask) {
; X86-LABEL: test_mask_compress_b_128:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpcompressb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0xc1]
; X86-NEXT: vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_b_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0xc1]
; X64-NEXT: vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.compress.b.128(<16 x i8> %data, <16 x i8> %passthru, i16 %mask)
ret <16 x i8> %res
}
define <16 x i8> @test_maskz_compress_b_128(<16 x i8> %data, i16 %mask) {
; X86-LABEL: test_maskz_compress_b_128:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpcompressb %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x63,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_compress_b_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressb %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x63,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.compress.b.128(<16 x i8> %data, <16 x i8> zeroinitializer, i16 %mask)
ret <16 x i8> %res
}
define <16 x i8> @test_compress_b_128(<16 x i8> %data) {
; CHECK-LABEL: test_compress_b_128:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.compress.b.128(<16 x i8> %data, <16 x i8> undef, i16 -1)
ret <16 x i8> %res
}
declare <16 x i8> @llvm.x86.avx512.mask.compress.b.128(<16 x i8> %data, <16 x i8> %src0, i16 %mask)
[X86] Add test files for upgrade of vbmi2 expand load and compress store intrinsics that was done in r334381. llvm-svn: 334386
2018-06-11 14:20:24 +08:00
define <16 x i16> @test_mask_expand_load_w_256(i8* %addr, <16 x i16> %data, i16 %mask) {
; X86-LABEL: test_mask_expand_load_w_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpexpandw (%eax), %ymm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_load_w_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpexpandw (%rdi), %ymm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.expand.load.w.256(i8* %addr, <16 x i16> %data, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_maskz_expand_load_w_256(i8* %addr, i16 %mask) {
; X86-LABEL: test_maskz_expand_load_w_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpexpandw (%eax), %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_load_w_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpexpandw (%rdi), %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.expand.load.w.256(i8* %addr, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
}
declare <16 x i16> @llvm.x86.avx512.mask.expand.load.w.256(i8* %addr, <16 x i16> %data, i16 %mask)
define <16 x i16> @test_expand_load_w_256(i8* %addr, <16 x i16> %data) {
; X86-LABEL: test_expand_load_w_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT: vpexpandw (%eax), %ymm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_expand_load_w_256:
; X64: # %bb.0:
; X64-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT: vpexpandw (%rdi), %ymm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.expand.load.w.256(i8* %addr, <16 x i16> %data, i16 -1)
ret <16 x i16> %res
}
[X86] Add new variadic avx512 compress/expand intrinsics that use vXi1 types for the mask argument. Remove and autoupgrade the old intrinsics llvm-svn: 352343
2019-01-28 15:03:03 +08:00
define <16 x i16> @test_expand_w_256(<16 x i16> %data) {
; CHECK-LABEL: test_expand_w_256:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.expand.w.256(<16 x i16> %data, <16 x i16> undef, i16 -1)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_expand_w_256(<16 x i16> %data, <16 x i16> %passthru, i16 %mask) {
; X86-LABEL: test_mask_expand_w_256:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpexpandw %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0xc8]
; X86-NEXT: vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_w_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandw %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0xc8]
; X64-NEXT: vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.expand.w.256(<16 x i16> %data, <16 x i16> %passthru, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_maskz_expand_w_256(<16 x i16> %data, i16 %mask) {
; X86-LABEL: test_maskz_expand_w_256:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpexpandw %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x62,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_w_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandw %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x62,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.expand.w.256(<16 x i16> %data, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
}
declare <16 x i16> @llvm.x86.avx512.mask.expand.w.256(<16 x i16> %data, <16 x i16> %src0, i16 %mask)
[X86] Add test files for upgrade of vbmi2 expand load and compress store intrinsics that was done in r334381. llvm-svn: 334386
2018-06-11 14:20:24 +08:00
define <32 x i8> @test_mask_expand_load_b_256(i8* %addr, <32 x i8> %data, i32 %mask) {
; X86-LABEL: test_mask_expand_load_b_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpexpandb (%eax), %ymm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_load_b_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpexpandb (%rdi), %ymm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.expand.load.b.256(i8* %addr, <32 x i8> %data, i32 %mask)
ret <32 x i8> %res
}
define <32 x i8> @test_maskz_expand_load_b_256(i8* %addr, i32 %mask) {
; X86-LABEL: test_maskz_expand_load_b_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpexpandb (%eax), %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_load_b_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpexpandb (%rdi), %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.expand.load.b.256(i8* %addr, <32 x i8> zeroinitializer, i32 %mask)
ret <32 x i8> %res
}
declare <32 x i8> @llvm.x86.avx512.mask.expand.load.b.256(i8* %addr, <32 x i8> %data, i32 %mask)
define <32 x i8> @test_expand_load_b_256(i8* %addr, <32 x i8> %data) {
; X86-LABEL: test_expand_load_b_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kxnord %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfd,0x46,0xc8]
; X86-NEXT: vpexpandb (%eax), %ymm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_expand_load_b_256:
; X64: # %bb.0:
; X64-NEXT: kxnord %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfd,0x46,0xc8]
; X64-NEXT: vpexpandb (%rdi), %ymm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.expand.load.b.256(i8* %addr, <32 x i8> %data, i32 -1)
ret <32 x i8> %res
}
[X86] Add new variadic avx512 compress/expand intrinsics that use vXi1 types for the mask argument. Remove and autoupgrade the old intrinsics llvm-svn: 352343
2019-01-28 15:03:03 +08:00
define <32 x i8> @test_expand_b_256(<32 x i8> %data) {
; CHECK-LABEL: test_expand_b_256:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.expand.b.256(<32 x i8> %data, <32 x i8> undef, i32 -1)
ret <32 x i8> %res
}
define <32 x i8> @test_mask_expand_b_256(<32 x i8> %data, <32 x i8> %passthru, i32 %mask) {
; X86-LABEL: test_mask_expand_b_256:
; X86: # %bb.0:
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpexpandb %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0xc8]
; X86-NEXT: vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_b_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandb %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0xc8]
; X64-NEXT: vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.expand.b.256(<32 x i8> %data, <32 x i8> %passthru, i32 %mask)
ret <32 x i8> %res
}
define <32 x i8> @test_maskz_expand_b_256(<32 x i8> %data, i32 %mask) {
; X86-LABEL: test_maskz_expand_b_256:
; X86: # %bb.0:
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpexpandb %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x62,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_b_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandb %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x62,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.expand.b.256(<32 x i8> %data, <32 x i8> zeroinitializer, i32 %mask)
ret <32 x i8> %res
}
declare <32 x i8> @llvm.x86.avx512.mask.expand.b.256(<32 x i8> %data, <32 x i8> %src0, i32 %mask)
[X86] Add test files for upgrade of vbmi2 expand load and compress store intrinsics that was done in r334381. llvm-svn: 334386
2018-06-11 14:20:24 +08:00
define void @test_mask_compress_store_w_256(i8* %addr, <16 x i16> %data, i16 %mask) {
; X86-LABEL: test_mask_compress_store_w_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpcompressw %ymm0, (%eax) {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0x00]
; X86-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_store_w_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpcompressw %ymm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0x07]
; X64-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT: retq # encoding: [0xc3]
call void @llvm.x86.avx512.mask.compress.store.w.256(i8* %addr, <16 x i16> %data, i16 %mask)
ret void
}
declare void @llvm.x86.avx512.mask.compress.store.w.256(i8* %addr, <16 x i16> %data, i16 %mask)
define void @test_compress_store_w_256(i8* %addr, <16 x i16> %data) {
; X86-LABEL: test_compress_store_w_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT: vpcompressw %ymm0, (%eax) {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0x00]
; X86-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_compress_store_w_256:
; X64: # %bb.0:
; X64-NEXT: kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT: vpcompressw %ymm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0x07]
; X64-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT: retq # encoding: [0xc3]
call void @llvm.x86.avx512.mask.compress.store.w.256(i8* %addr, <16 x i16> %data, i16 -1)
ret void
}
[X86] Add new variadic avx512 compress/expand intrinsics that use vXi1 types for the mask argument. Remove and autoupgrade the old intrinsics llvm-svn: 352343
2019-01-28 15:03:03 +08:00
define <16 x i16> @test_mask_compress_w_256(<16 x i16> %data, <16 x i16> %passthru, i16 %mask) {
; X86-LABEL: test_mask_compress_w_256:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpcompressw %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0xc1]
; X86-NEXT: vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_w_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressw %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0xc1]
; X64-NEXT: vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.compress.w.256(<16 x i16> %data, <16 x i16> %passthru, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_maskz_compress_w_256(<16 x i16> %data, i16 %mask) {
; X86-LABEL: test_maskz_compress_w_256:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpcompressw %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x63,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_compress_w_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressw %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x63,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.compress.w.256(<16 x i16> %data, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_compress_w_256(<16 x i16> %data) {
; CHECK-LABEL: test_compress_w_256:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.compress.w.256(<16 x i16> %data, <16 x i16> undef, i16 -1)
ret <16 x i16> %res
}
declare <16 x i16> @llvm.x86.avx512.mask.compress.w.256(<16 x i16> %data, <16 x i16> %src0, i16 %mask)
[X86] Add test files for upgrade of vbmi2 expand load and compress store intrinsics that was done in r334381. llvm-svn: 334386
2018-06-11 14:20:24 +08:00
define void @test_mask_compress_store_b_256(i8* %addr, <32 x i8> %data, i32 %mask) {
; X86-LABEL: test_mask_compress_store_b_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpcompressb %ymm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0x00]
; X86-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_store_b_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpcompressb %ymm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0x07]
; X64-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT: retq # encoding: [0xc3]
call void @llvm.x86.avx512.mask.compress.store.b.256(i8* %addr, <32 x i8> %data, i32 %mask)
ret void
}
declare void @llvm.x86.avx512.mask.compress.store.b.256(i8* %addr, <32 x i8> %data, i32 %mask)
define void @test_compress_store_b_256(i8* %addr, <32 x i8> %data) {
; X86-LABEL: test_compress_store_b_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kxnord %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfd,0x46,0xc8]
; X86-NEXT: vpcompressb %ymm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0x00]
; X86-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_compress_store_b_256:
; X64: # %bb.0:
; X64-NEXT: kxnord %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfd,0x46,0xc8]
; X64-NEXT: vpcompressb %ymm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0x07]
; X64-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT: retq # encoding: [0xc3]
call void @llvm.x86.avx512.mask.compress.store.b.256(i8* %addr, <32 x i8> %data, i32 -1)
ret void
}
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
[X86] Add new variadic avx512 compress/expand intrinsics that use vXi1 types for the mask argument. Remove and autoupgrade the old intrinsics llvm-svn: 352343
2019-01-28 15:03:03 +08:00
define <32 x i8> @test_mask_compress_b_256(<32 x i8> %data, <32 x i8> %passthru, i32 %mask) {
; X86-LABEL: test_mask_compress_b_256:
; X86: # %bb.0:
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpcompressb %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0xc1]
; X86-NEXT: vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_b_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressb %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0xc1]
; X64-NEXT: vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.compress.b.256(<32 x i8> %data, <32 x i8> %passthru, i32 %mask)
ret <32 x i8> %res
}
define <32 x i8> @test_maskz_compress_b_256(<32 x i8> %data, i32 %mask) {
; X86-LABEL: test_maskz_compress_b_256:
; X86: # %bb.0:
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpcompressb %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x63,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_compress_b_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressb %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x63,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.compress.b.256(<32 x i8> %data, <32 x i8> zeroinitializer, i32 %mask)
ret <32 x i8> %res
}
define <32 x i8> @test_compress_b_256(<32 x i8> %data) {
; CHECK-LABEL: test_compress_b_256:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.compress.b.256(<32 x i8> %data, <32 x i8> undef, i32 -1)
ret <32 x i8> %res
}
declare <32 x i8> @llvm.x86.avx512.mask.compress.b.256(<32 x i8> %data, <32 x i8> %src0, i32 %mask)
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
define <4 x i32>@test_int_x86_avx512_mask_vpshld_d_128(<4 x i32> %x0, <4 x i32> %x1,<4 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_d_128:
; X86: # %bb.0:
; X86-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x71,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x71,0xd1,0x16]
; X86-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x71,0xc1,0x16]
; X86-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X86-NEXT: vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_d_128:
; X64: # %bb.0:
; X64-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x71,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x71,0xd1,0x16]
; X64-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x71,0xc1,0x16]
; X64-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X64-NEXT: vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.vpshld.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22, <4 x i32> %x3, i8 %x4)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.vpshld.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22, <4 x i32> %x3, i8 -1)
%res2 = call <4 x i32> @llvm.x86.avx512.mask.vpshld.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22, <4 x i32> zeroinitializer,i8 %x4)
%res3 = add <4 x i32> %res, %res1
%res4 = add <4 x i32> %res3, %res2
ret <4 x i32> %res4
}
declare <4 x i32> @llvm.x86.avx512.mask.vpshld.d.128(<4 x i32>, <4 x i32>, i32, <4 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_vpshld_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_d_256:
; X86: # %bb.0:
; X86-NEXT: vpshldd $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0x7d,0x28,0x71,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshldd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x71,0xd1,0x16]
; X86-NEXT: vpaddd %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_d_256:
; X64: # %bb.0:
; X64-NEXT: vpshldd $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0x7d,0x28,0x71,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x71,0xd1,0x16]
; X64-NEXT: vpaddd %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.vpshld.d.256(<8 x i32> %x0, <8 x i32> %x1, i32 22, <8 x i32> %x3, i8 %x4)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.vpshld.d.256(<8 x i32> %x0, <8 x i32> %x1, i32 22, <8 x i32> %x3, i8 -1)
%res2 = add <8 x i32> %res, %res1
ret <8 x i32> %res2
}
declare <8 x i32> @llvm.x86.avx512.mask.vpshld.d.256(<8 x i32>, <8 x i32>, i32, <8 x i32>, i8)
define <2 x i64>@test_int_x86_avx512_mask_vpshld_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_q_128:
; X86: # %bb.0:
; X86-NEXT: vpshldq $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x71,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshldq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x71,0xd1,0x16]
; X86-NEXT: vpaddq %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_q_128:
; X64: # %bb.0:
; X64-NEXT: vpshldq $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x71,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x71,0xd1,0x16]
; X64-NEXT: vpaddq %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.vpshld.q.128(<2 x i64> %x0, <2 x i64> %x1, i32 22, <2 x i64> %x3, i8 %x4)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.vpshld.q.128(<2 x i64> %x0, <2 x i64> %x1, i32 22, <2 x i64> %x3, i8 -1)
%res2 = add <2 x i64> %res, %res1
ret <2 x i64> %res2
}
declare <2 x i64> @llvm.x86.avx512.mask.vpshld.q.128(<2 x i64>, <2 x i64>, i32, <2 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_vpshld_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_q_256:
; X86: # %bb.0:
; X86-NEXT: vpshldq $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x71,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshldq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x71,0xd1,0x16]
; X86-NEXT: vpaddq %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_q_256:
; X64: # %bb.0:
; X64-NEXT: vpshldq $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x71,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x71,0xd1,0x16]
; X64-NEXT: vpaddq %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.vpshld.q.256(<4 x i64> %x0, <4 x i64> %x1, i32 22, <4 x i64> %x3, i8 %x4)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.vpshld.q.256(<4 x i64> %x0, <4 x i64> %x1, i32 22, <4 x i64> %x3, i8 -1)
%res2 = add <4 x i64> %res, %res1
ret <4 x i64> %res2
}
declare <4 x i64> @llvm.x86.avx512.mask.vpshld.q.256(<4 x i64>, <4 x i64>, i32, <4 x i64>, i8)
define <8 x i16>@test_int_x86_avx512_mask_vpshld_w_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_w_128:
; X86: # %bb.0:
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X86-NEXT: vpshldw $6, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x70,0xd9,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X86-NEXT: vpshldw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x70,0xd1,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X86-NEXT: vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_w_128:
; X64: # %bb.0:
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X64-NEXT: vpshldw $6, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x70,0xd9,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X64-NEXT: vpshldw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x70,0xd1,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X64-NEXT: vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
%res = call <8 x i16> @llvm.x86.avx512.mask.vpshld.w.128(<8 x i16> %x0, <8 x i16> %x1, i32 6, <8 x i16> %x3, i8 %x4)
%res1 = call <8 x i16> @llvm.x86.avx512.mask.vpshld.w.128(<8 x i16> %x0, <8 x i16> %x1, i32 6, <8 x i16> %x3, i8 -1)
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
%res2 = add <8 x i16> %res, %res1
ret <8 x i16> %res2
}
declare <8 x i16> @llvm.x86.avx512.mask.vpshld.w.128(<8 x i16>, <8 x i16>, i32, <8 x i16>, i8)
define <16 x i16>@test_int_x86_avx512_mask_vpshld_w_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x3, i16 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_w_256:
; X86: # %bb.0:
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X86-NEXT: vpshldw $6, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x70,0xd9,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X86-NEXT: vpshldw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x70,0xd1,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X86-NEXT: vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_w_256:
; X64: # %bb.0:
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X64-NEXT: vpshldw $6, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x70,0xd9,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X64-NEXT: vpshldw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x70,0xd1,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X64-NEXT: vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
%res = call <16 x i16> @llvm.x86.avx512.mask.vpshld.w.256(<16 x i16> %x0, <16 x i16> %x1, i32 6, <16 x i16> %x3, i16 %x4)
%res1 = call <16 x i16> @llvm.x86.avx512.mask.vpshld.w.256(<16 x i16> %x0, <16 x i16> %x1, i32 6, <16 x i16> %x3, i16 -1)
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
%res2 = add <16 x i16> %res, %res1
ret <16 x i16> %res2
}
declare <16 x i16> @llvm.x86.avx512.mask.vpshld.w.256(<16 x i16>, <16 x i16>, i32, <16 x i16>, i16)
define <4 x i32>@test_int_x86_avx512_mask_vpshrd_d_128(<4 x i32> %x0, <4 x i32> %x1,<4 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_d_128:
; X86: # %bb.0:
; X86-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x73,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x73,0xd1,0x16]
; X86-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x73,0xc1,0x16]
; X86-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X86-NEXT: vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_d_128:
; X64: # %bb.0:
; X64-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x73,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x73,0xd1,0x16]
; X64-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x73,0xc1,0x16]
; X64-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X64-NEXT: vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.vpshrd.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22, <4 x i32> %x3, i8 %x4)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.vpshrd.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22, <4 x i32> %x3, i8 -1)
%res2 = call <4 x i32> @llvm.x86.avx512.mask.vpshrd.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22, <4 x i32> zeroinitializer,i8 %x4)
%res3 = add <4 x i32> %res, %res1
%res4 = add <4 x i32> %res3, %res2
ret <4 x i32> %res4
}
declare <4 x i32> @llvm.x86.avx512.mask.vpshrd.d.128(<4 x i32>, <4 x i32>, i32, <4 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_vpshrd_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_d_256:
; X86: # %bb.0:
; X86-NEXT: vpshrdd $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0x7d,0x28,0x73,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshrdd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x73,0xd1,0x16]
; X86-NEXT: vpaddd %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_d_256:
; X64: # %bb.0:
; X64-NEXT: vpshrdd $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0x7d,0x28,0x73,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x73,0xd1,0x16]
; X64-NEXT: vpaddd %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.vpshrd.d.256(<8 x i32> %x0, <8 x i32> %x1, i32 22, <8 x i32> %x3, i8 %x4)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.vpshrd.d.256(<8 x i32> %x0, <8 x i32> %x1, i32 22, <8 x i32> %x3, i8 -1)
%res2 = add <8 x i32> %res, %res1
ret <8 x i32> %res2
}
declare <8 x i32> @llvm.x86.avx512.mask.vpshrd.d.256(<8 x i32>, <8 x i32>, i32, <8 x i32>, i8)
define <2 x i64>@test_int_x86_avx512_mask_vpshrd_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_q_128:
; X86: # %bb.0:
; X86-NEXT: vpshrdq $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x73,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshrdq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x73,0xd1,0x16]
; X86-NEXT: vpaddq %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_q_128:
; X64: # %bb.0:
; X64-NEXT: vpshrdq $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x73,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x73,0xd1,0x16]
; X64-NEXT: vpaddq %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.vpshrd.q.128(<2 x i64> %x0, <2 x i64> %x1, i32 22, <2 x i64> %x3, i8 %x4)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.vpshrd.q.128(<2 x i64> %x0, <2 x i64> %x1, i32 22, <2 x i64> %x3, i8 -1)
%res2 = add <2 x i64> %res, %res1
ret <2 x i64> %res2
}
declare <2 x i64> @llvm.x86.avx512.mask.vpshrd.q.128(<2 x i64>, <2 x i64>, i32, <2 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_vpshrd_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_q_256:
; X86: # %bb.0:
; X86-NEXT: vpshrdq $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x73,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshrdq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x73,0xd1,0x16]
; X86-NEXT: vpaddq %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_q_256:
; X64: # %bb.0:
; X64-NEXT: vpshrdq $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x73,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x73,0xd1,0x16]
; X64-NEXT: vpaddq %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.vpshrd.q.256(<4 x i64> %x0, <4 x i64> %x1, i32 22, <4 x i64> %x3, i8 %x4)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.vpshrd.q.256(<4 x i64> %x0, <4 x i64> %x1, i32 22, <4 x i64> %x3, i8 -1)
%res2 = add <4 x i64> %res, %res1
ret <4 x i64> %res2
}
declare <4 x i64> @llvm.x86.avx512.mask.vpshrd.q.256(<4 x i64>, <4 x i64>, i32, <4 x i64>, i8)
define <8 x i16>@test_int_x86_avx512_mask_vpshrd_w_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_w_128:
; X86: # %bb.0:
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X86-NEXT: vpshrdw $6, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x72,0xd9,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X86-NEXT: vpshrdw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x72,0xd1,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X86-NEXT: vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_w_128:
; X64: # %bb.0:
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X64-NEXT: vpshrdw $6, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x72,0xd9,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X64-NEXT: vpshrdw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x72,0xd1,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X64-NEXT: vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
%res = call <8 x i16> @llvm.x86.avx512.mask.vpshrd.w.128(<8 x i16> %x0, <8 x i16> %x1, i32 6, <8 x i16> %x3, i8 %x4)
%res1 = call <8 x i16> @llvm.x86.avx512.mask.vpshrd.w.128(<8 x i16> %x0, <8 x i16> %x1, i32 6, <8 x i16> %x3, i8 -1)
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
%res2 = add <8 x i16> %res, %res1
ret <8 x i16> %res2
}
declare <8 x i16> @llvm.x86.avx512.mask.vpshrd.w.128(<8 x i16>, <8 x i16>, i32, <8 x i16>, i8)
define <16 x i16>@test_int_x86_avx512_mask_vpshrd_w_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x3, i16 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_w_256:
; X86: # %bb.0:
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X86-NEXT: vpshrdw $6, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x72,0xd9,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X86-NEXT: vpshrdw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x72,0xd1,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X86-NEXT: vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_w_256:
; X64: # %bb.0:
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X64-NEXT: vpshrdw $6, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x72,0xd9,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
; X64-NEXT: vpshrdw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x72,0xd1,0x06]
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
; X64-NEXT: vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
[X86] Update VBMI2 vshld/vshrd tests to use an immediate that doesn't require a modulo. Planning to replace these with funnel shift intrinsics which would mask out the extra bits. This will help minimize test diffs. llvm-svn: 350504
2019-01-07 13:58:53 +08:00
%res = call <16 x i16> @llvm.x86.avx512.mask.vpshrd.w.256(<16 x i16> %x0, <16 x i16> %x1, i32 6, <16 x i16> %x3, i16 %x4)
%res1 = call <16 x i16> @llvm.x86.avx512.mask.vpshrd.w.256(<16 x i16> %x0, <16 x i16> %x1, i32 6, <16 x i16> %x3, i16 -1)
[X86] Remove masking from avx512vbmi2 concat and shift by immediate intrinsics. Use select in IR instead. llvm-svn: 334576
2018-06-13 15:19:21 +08:00
%res2 = add <16 x i16> %res, %res1
ret <16 x i16> %res2
}
declare <16 x i16> @llvm.x86.avx512.mask.vpshrd.w.256(<16 x i16>, <16 x i16>, i32, <16 x i16>, i16)
Recommit r350554 "[X86] Remove AVX512VBMI2 concat and shift intrinsics. Replace with target independent funnel shift intrinsics." The MSVC limit we hit on AutoUpgrade.cpp has been worked around for now. llvm-svn: 350567
2019-01-08 05:00:32 +08:00
define <4 x i32>@test_int_x86_avx512_mask_vpshld_d_128_2(<4 x i32> %x0, <4 x i32> %x1,<4 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_d_128_2:
; X86: # %bb.0:
; X86-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x71,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x71,0xd1,0x16]
; X86-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x71,0xc1,0x16]
; X86-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X86-NEXT: vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_d_128_2:
; X64: # %bb.0:
; X64-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x71,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x71,0xd1,0x16]
; X64-NEXT: vpshldd $22, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x71,0xc1,0x16]
; X64-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X64-NEXT: vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <4 x i32> @llvm.x86.avx512.vpshld.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22)
%2 = bitcast i8 %x4 to <8 x i1>
%extract1 = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%3 = select <4 x i1> %extract1, <4 x i32> %1, <4 x i32> %x3
%4 = call <4 x i32> @llvm.x86.avx512.vpshld.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22)
%5 = call <4 x i32> @llvm.x86.avx512.vpshld.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22)
%6 = bitcast i8 %x4 to <8 x i1>
%extract = shufflevector <8 x i1> %6, <8 x i1> %6, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%7 = select <4 x i1> %extract, <4 x i32> %5, <4 x i32> zeroinitializer
%res3 = add <4 x i32> %3, %4
%res4 = add <4 x i32> %res3, %7
ret <4 x i32> %res4
}
declare <4 x i32> @llvm.x86.avx512.vpshld.d.128(<4 x i32>, <4 x i32>, i32)
define <8 x i32>@test_int_x86_avx512_mask_vpshld_d_256_2(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_d_256_2:
; X86: # %bb.0:
; X86-NEXT: vpshldd $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0x7d,0x28,0x71,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshldd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x71,0xd1,0x16]
; X86-NEXT: vpaddd %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_d_256_2:
; X64: # %bb.0:
; X64-NEXT: vpshldd $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0x7d,0x28,0x71,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x71,0xd1,0x16]
; X64-NEXT: vpaddd %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <8 x i32> @llvm.x86.avx512.vpshld.d.256(<8 x i32> %x0, <8 x i32> %x1, i32 22)
%2 = bitcast i8 %x4 to <8 x i1>
%3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %x3
%4 = call <8 x i32> @llvm.x86.avx512.vpshld.d.256(<8 x i32> %x0, <8 x i32> %x1, i32 22)
%res2 = add <8 x i32> %3, %4
ret <8 x i32> %res2
}
declare <8 x i32> @llvm.x86.avx512.vpshld.d.256(<8 x i32>, <8 x i32>, i32)
define <2 x i64>@test_int_x86_avx512_mask_vpshld_q_128_2(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_q_128_2:
; X86: # %bb.0:
; X86-NEXT: vpshldq $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x71,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshldq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x71,0xd1,0x16]
; X86-NEXT: vpaddq %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_q_128_2:
; X64: # %bb.0:
; X64-NEXT: vpshldq $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x71,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x71,0xd1,0x16]
; X64-NEXT: vpaddq %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <2 x i64> @llvm.x86.avx512.vpshld.q.128(<2 x i64> %x0, <2 x i64> %x1, i32 22)
%2 = bitcast i8 %x4 to <8 x i1>
%extract = shufflevector <8 x i1> %2, <8 x i1> %2, <2 x i32> <i32 0, i32 1>
%3 = select <2 x i1> %extract, <2 x i64> %1, <2 x i64> %x3
%4 = call <2 x i64> @llvm.x86.avx512.vpshld.q.128(<2 x i64> %x0, <2 x i64> %x1, i32 22)
%res2 = add <2 x i64> %3, %4
ret <2 x i64> %res2
}
declare <2 x i64> @llvm.x86.avx512.vpshld.q.128(<2 x i64>, <2 x i64>, i32)
define <4 x i64>@test_int_x86_avx512_mask_vpshld_q_256_2(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_q_256_2:
; X86: # %bb.0:
; X86-NEXT: vpshldq $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x71,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshldq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x71,0xd1,0x16]
; X86-NEXT: vpaddq %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_q_256_2:
; X64: # %bb.0:
; X64-NEXT: vpshldq $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x71,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x71,0xd1,0x16]
; X64-NEXT: vpaddq %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <4 x i64> @llvm.x86.avx512.vpshld.q.256(<4 x i64> %x0, <4 x i64> %x1, i32 22)
%2 = bitcast i8 %x4 to <8 x i1>
%extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%3 = select <4 x i1> %extract, <4 x i64> %1, <4 x i64> %x3
%4 = call <4 x i64> @llvm.x86.avx512.vpshld.q.256(<4 x i64> %x0, <4 x i64> %x1, i32 22)
%res2 = add <4 x i64> %3, %4
ret <4 x i64> %res2
}
declare <4 x i64> @llvm.x86.avx512.vpshld.q.256(<4 x i64>, <4 x i64>, i32)
define <8 x i16>@test_int_x86_avx512_mask_vpshld_w_128_2(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_w_128_2:
; X86: # %bb.0:
; X86-NEXT: vpshldw $6, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x70,0xd9,0x06]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshldw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x70,0xd1,0x06]
; X86-NEXT: vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_w_128_2:
; X64: # %bb.0:
; X64-NEXT: vpshldw $6, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x70,0xd9,0x06]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x70,0xd1,0x06]
; X64-NEXT: vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <8 x i16> @llvm.x86.avx512.vpshld.w.128(<8 x i16> %x0, <8 x i16> %x1, i32 6)
%2 = bitcast i8 %x4 to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %x3
%4 = call <8 x i16> @llvm.x86.avx512.vpshld.w.128(<8 x i16> %x0, <8 x i16> %x1, i32 6)
%res2 = add <8 x i16> %3, %4
ret <8 x i16> %res2
}
declare <8 x i16> @llvm.x86.avx512.vpshld.w.128(<8 x i16>, <8 x i16>, i32)
define <16 x i16>@test_int_x86_avx512_mask_vpshld_w_256_2(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x3, i16 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_w_256_2:
; X86: # %bb.0:
; X86-NEXT: vpshldw $6, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x70,0xd9,0x06]
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpshldw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x70,0xd1,0x06]
; X86-NEXT: vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_w_256_2:
; X64: # %bb.0:
; X64-NEXT: vpshldw $6, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x70,0xd9,0x06]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x70,0xd1,0x06]
; X64-NEXT: vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <16 x i16> @llvm.x86.avx512.vpshld.w.256(<16 x i16> %x0, <16 x i16> %x1, i32 6)
%2 = bitcast i16 %x4 to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %x3
%4 = call <16 x i16> @llvm.x86.avx512.vpshld.w.256(<16 x i16> %x0, <16 x i16> %x1, i32 6)
%res2 = add <16 x i16> %3, %4
ret <16 x i16> %res2
}
declare <16 x i16> @llvm.x86.avx512.vpshld.w.256(<16 x i16>, <16 x i16>, i32)
define <4 x i32>@test_int_x86_avx512_mask_vpshrd_d_128_2(<4 x i32> %x0, <4 x i32> %x1,<4 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_d_128_2:
; X86: # %bb.0:
; X86-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x73,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x73,0xd1,0x16]
; X86-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x73,0xc1,0x16]
; X86-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X86-NEXT: vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_d_128_2:
; X64: # %bb.0:
; X64-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x73,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x73,0xd1,0x16]
; X64-NEXT: vpshrdd $22, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x73,0xc1,0x16]
; X64-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X64-NEXT: vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <4 x i32> @llvm.x86.avx512.vpshrd.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22)
%2 = bitcast i8 %x4 to <8 x i1>
%extract1 = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%3 = select <4 x i1> %extract1, <4 x i32> %1, <4 x i32> %x3
%4 = call <4 x i32> @llvm.x86.avx512.vpshrd.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22)
%5 = call <4 x i32> @llvm.x86.avx512.vpshrd.d.128(<4 x i32> %x0, <4 x i32> %x1, i32 22)
%6 = bitcast i8 %x4 to <8 x i1>
%extract = shufflevector <8 x i1> %6, <8 x i1> %6, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%7 = select <4 x i1> %extract, <4 x i32> %5, <4 x i32> zeroinitializer
%res3 = add <4 x i32> %3, %4
%res4 = add <4 x i32> %res3, %7
ret <4 x i32> %res4
}
declare <4 x i32> @llvm.x86.avx512.vpshrd.d.128(<4 x i32>, <4 x i32>, i32)
define <8 x i32>@test_int_x86_avx512_mask_vpshrd_d_256_2(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_d_256_2:
; X86: # %bb.0:
; X86-NEXT: vpshrdd $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0x7d,0x28,0x73,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshrdd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x73,0xd1,0x16]
; X86-NEXT: vpaddd %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_d_256_2:
; X64: # %bb.0:
; X64-NEXT: vpshrdd $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0x7d,0x28,0x73,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x73,0xd1,0x16]
; X64-NEXT: vpaddd %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <8 x i32> @llvm.x86.avx512.vpshrd.d.256(<8 x i32> %x0, <8 x i32> %x1, i32 22)
%2 = bitcast i8 %x4 to <8 x i1>
%3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %x3
%4 = call <8 x i32> @llvm.x86.avx512.vpshrd.d.256(<8 x i32> %x0, <8 x i32> %x1, i32 22)
%res2 = add <8 x i32> %3, %4
ret <8 x i32> %res2
}
declare <8 x i32> @llvm.x86.avx512.vpshrd.d.256(<8 x i32>, <8 x i32>, i32)
define <2 x i64>@test_int_x86_avx512_mask_vpshrd_q_128_2(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_q_128_2:
; X86: # %bb.0:
; X86-NEXT: vpshrdq $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x73,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshrdq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x73,0xd1,0x16]
; X86-NEXT: vpaddq %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_q_128_2:
; X64: # %bb.0:
; X64-NEXT: vpshrdq $22, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x73,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x73,0xd1,0x16]
; X64-NEXT: vpaddq %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <2 x i64> @llvm.x86.avx512.vpshrd.q.128(<2 x i64> %x0, <2 x i64> %x1, i32 22)
%2 = bitcast i8 %x4 to <8 x i1>
%extract = shufflevector <8 x i1> %2, <8 x i1> %2, <2 x i32> <i32 0, i32 1>
%3 = select <2 x i1> %extract, <2 x i64> %1, <2 x i64> %x3
%4 = call <2 x i64> @llvm.x86.avx512.vpshrd.q.128(<2 x i64> %x0, <2 x i64> %x1, i32 22)
%res2 = add <2 x i64> %3, %4
ret <2 x i64> %res2
}
declare <2 x i64> @llvm.x86.avx512.vpshrd.q.128(<2 x i64>, <2 x i64>, i32)
define <4 x i64>@test_int_x86_avx512_mask_vpshrd_q_256_2(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_q_256_2:
; X86: # %bb.0:
; X86-NEXT: vpshrdq $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x73,0xd9,0x16]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshrdq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x73,0xd1,0x16]
; X86-NEXT: vpaddq %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_q_256_2:
; X64: # %bb.0:
; X64-NEXT: vpshrdq $22, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x73,0xd9,0x16]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x73,0xd1,0x16]
; X64-NEXT: vpaddq %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <4 x i64> @llvm.x86.avx512.vpshrd.q.256(<4 x i64> %x0, <4 x i64> %x1, i32 22)
%2 = bitcast i8 %x4 to <8 x i1>
%extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%3 = select <4 x i1> %extract, <4 x i64> %1, <4 x i64> %x3
%4 = call <4 x i64> @llvm.x86.avx512.vpshrd.q.256(<4 x i64> %x0, <4 x i64> %x1, i32 22)
%res2 = add <4 x i64> %3, %4
ret <4 x i64> %res2
}
declare <4 x i64> @llvm.x86.avx512.vpshrd.q.256(<4 x i64>, <4 x i64>, i32)
define <8 x i16>@test_int_x86_avx512_mask_vpshrd_w_128_2(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_w_128_2:
; X86: # %bb.0:
; X86-NEXT: vpshrdw $6, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x72,0xd9,0x06]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT: vpshrdw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x72,0xd1,0x06]
; X86-NEXT: vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_w_128_2:
; X64: # %bb.0:
; X64-NEXT: vpshrdw $6, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0xfd,0x08,0x72,0xd9,0x06]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x72,0xd1,0x06]
; X64-NEXT: vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <8 x i16> @llvm.x86.avx512.vpshrd.w.128(<8 x i16> %x0, <8 x i16> %x1, i32 6)
%2 = bitcast i8 %x4 to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %x3
%4 = call <8 x i16> @llvm.x86.avx512.vpshrd.w.128(<8 x i16> %x0, <8 x i16> %x1, i32 6)
%res2 = add <8 x i16> %3, %4
ret <8 x i16> %res2
}
declare <8 x i16> @llvm.x86.avx512.vpshrd.w.128(<8 x i16>, <8 x i16>, i32)
define <16 x i16>@test_int_x86_avx512_mask_vpshrd_w_256_2(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x3, i16 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_w_256_2:
; X86: # %bb.0:
; X86-NEXT: vpshrdw $6, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x72,0xd9,0x06]
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpshrdw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x72,0xd1,0x06]
; X86-NEXT: vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_w_256_2:
; X64: # %bb.0:
; X64-NEXT: vpshrdw $6, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0xfd,0x28,0x72,0xd9,0x06]
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x72,0xd1,0x06]
; X64-NEXT: vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <16 x i16> @llvm.x86.avx512.vpshrd.w.256(<16 x i16> %x0, <16 x i16> %x1, i32 6)
%2 = bitcast i16 %x4 to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %x3
%4 = call <16 x i16> @llvm.x86.avx512.vpshrd.w.256(<16 x i16> %x0, <16 x i16> %x1, i32 6)
%res2 = add <16 x i16> %3, %4
ret <16 x i16> %res2
}
declare <16 x i16> @llvm.x86.avx512.vpshrd.w.256(<16 x i16>, <16 x i16>, i32)
declare <8 x i32> @llvm.x86.avx512.mask.vpshrdv.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
declare <8 x i32> @llvm.x86.avx512.maskz.vpshrdv.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_vpshrdv_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32>* %x2p, <8 x i32> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_d_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT: vpshrdvd (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0x75,0x29,0x73,0x18]
; X86-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X86-NEXT: vpshrdvd %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0x75,0x28,0x73,0xe2]
; X86-NEXT: vpshrdvd %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xa9,0x73,0xc2]
; X86-NEXT: vpaddd %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xfe,0xc0]
; X86-NEXT: vpaddd %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_d_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT: vpshrdvd (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0x75,0x29,0x73,0x1f]
; X64-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X64-NEXT: vpshrdvd %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0x75,0x28,0x73,0xe2]
; X64-NEXT: vpshrdvd %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xa9,0x73,0xc2]
; X64-NEXT: vpaddd %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xfe,0xc0]
; X64-NEXT: vpaddd %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <8 x i32>, <8 x i32>* %x2p
%res = call <8 x i32> @llvm.x86.avx512.mask.vpshrdv.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.vpshrdv.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x4, i8 -1)
%res2 = call <8 x i32> @llvm.x86.avx512.maskz.vpshrdv.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x4, i8 %x3)
%res3 = add <8 x i32> %res, %res1
%res4 = add <8 x i32> %res2, %res3
ret <8 x i32> %res4
}
declare <4 x i32> @llvm.x86.avx512.mask.vpshrdv.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
declare <4 x i32> @llvm.x86.avx512.maskz.vpshrdv.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <4 x i32>@test_int_x86_avx512_mask_vpshrdv_d_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32>* %x2p, <4 x i32> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_d_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT: vpshrdvd (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x09,0x73,0x18]
; X86-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X86-NEXT: vpshrdvd %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0x75,0x08,0x73,0xe2]
; X86-NEXT: vpshrdvd %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0x89,0x73,0xc2]
; X86-NEXT: vpaddd %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xfe,0xc0]
; X86-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_d_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT: vpshrdvd (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x09,0x73,0x1f]
; X64-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X64-NEXT: vpshrdvd %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0x75,0x08,0x73,0xe2]
; X64-NEXT: vpshrdvd %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0x89,0x73,0xc2]
; X64-NEXT: vpaddd %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xfe,0xc0]
; X64-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <4 x i32>, <4 x i32>* %x2p
%res = call <4 x i32> @llvm.x86.avx512.mask.vpshrdv.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.vpshrdv.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x4, i8 -1)
%res2 = call <4 x i32> @llvm.x86.avx512.maskz.vpshrdv.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x4, i8 %x3)
%res3 = add <4 x i32> %res, %res1
%res4 = add <4 x i32> %res2, %res3
ret <4 x i32> %res4
}
declare <4 x i64> @llvm.x86.avx512.mask.vpshrdv.q.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
declare <4 x i64> @llvm.x86.avx512.maskz.vpshrdv.q.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_vpshrdv_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64>* %x2p, <4 x i64> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_q_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT: vpshrdvq (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x73,0x18]
; X86-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X86-NEXT: vpshrdvq %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0xf5,0x28,0x73,0xe2]
; X86-NEXT: vpshrdvq %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x73,0xc2]
; X86-NEXT: vpaddq %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xd4,0xc0]
; X86-NEXT: vpaddq %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xd4,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_q_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT: vpshrdvq (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x73,0x1f]
; X64-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X64-NEXT: vpshrdvq %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0xf5,0x28,0x73,0xe2]
; X64-NEXT: vpshrdvq %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x73,0xc2]
; X64-NEXT: vpaddq %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xd4,0xc0]
; X64-NEXT: vpaddq %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <4 x i64>, <4 x i64>* %x2p
%res = call <4 x i64> @llvm.x86.avx512.mask.vpshrdv.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %x3)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.vpshrdv.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x4, i8 -1)
%res2 = call <4 x i64> @llvm.x86.avx512.maskz.vpshrdv.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x4, i8 %x3)
%res3 = add <4 x i64> %res, %res1
%res4 = add <4 x i64> %res2, %res3
ret <4 x i64> %res4
}
declare <2 x i64> @llvm.x86.avx512.mask.vpshrdv.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
declare <2 x i64> @llvm.x86.avx512.maskz.vpshrdv.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
define <2 x i64>@test_int_x86_avx512_mask_vpshrdv_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64>* %x2p, <2 x i64> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_q_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT: vpshrdvq (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x73,0x18]
; X86-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X86-NEXT: vpshrdvq %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0xf5,0x08,0x73,0xe2]
; X86-NEXT: vpshrdvq %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x73,0xc2]
; X86-NEXT: vpaddq %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xd4,0xc0]
; X86-NEXT: vpaddq %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xd4,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_q_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT: vpshrdvq (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x73,0x1f]
; X64-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X64-NEXT: vpshrdvq %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0xf5,0x08,0x73,0xe2]
; X64-NEXT: vpshrdvq %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x73,0xc2]
; X64-NEXT: vpaddq %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xd4,0xc0]
; X64-NEXT: vpaddq %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <2 x i64>, <2 x i64>* %x2p
%res = call <2 x i64> @llvm.x86.avx512.mask.vpshrdv.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.vpshrdv.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x4, i8 -1)
%res2 = call <2 x i64> @llvm.x86.avx512.maskz.vpshrdv.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x4, i8 %x3)
%res3 = add <2 x i64> %res, %res1
%res4 = add <2 x i64> %res2, %res3
ret <2 x i64> %res4
}
declare <16 x i16> @llvm.x86.avx512.mask.vpshrdv.w.256(<16 x i16>, <16 x i16>, <16 x i16>, i16)
declare <16 x i16> @llvm.x86.avx512.maskz.vpshrdv.w.256(<16 x i16>, <16 x i16>, <16 x i16>, i16)
define <16 x i16>@test_int_x86_avx512_mask_vpshrdv_w_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16>* %x2p, <16 x i16> %x4, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_w_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT: vpshrdvw (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x72,0x18]
; X86-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X86-NEXT: vpshrdvw %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0xf5,0x28,0x72,0xe2]
; X86-NEXT: vpshrdvw %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x72,0xc2]
; X86-NEXT: vpaddw %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xfd,0xc0]
; X86-NEXT: vpaddw %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfd,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_w_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT: vpshrdvw (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x72,0x1f]
; X64-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X64-NEXT: vpshrdvw %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0xf5,0x28,0x72,0xe2]
; X64-NEXT: vpshrdvw %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x72,0xc2]
; X64-NEXT: vpaddw %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xfd,0xc0]
; X64-NEXT: vpaddw %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfd,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <16 x i16>, <16 x i16>* %x2p
%res = call <16 x i16> @llvm.x86.avx512.mask.vpshrdv.w.256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3)
%res1 = call <16 x i16> @llvm.x86.avx512.mask.vpshrdv.w.256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x4, i16 -1)
%res2 = call <16 x i16> @llvm.x86.avx512.maskz.vpshrdv.w.256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x4, i16 %x3)
%res3 = add <16 x i16> %res, %res1
%res4 = add <16 x i16> %res2, %res3
ret <16 x i16> %res4
}
declare <8 x i16> @llvm.x86.avx512.mask.vpshrdv.w.128(<8 x i16>, <8 x i16>, <8 x i16>, i8)
declare <8 x i16> @llvm.x86.avx512.maskz.vpshrdv.w.128(<8 x i16>, <8 x i16>, <8 x i16>, i8)
define <8 x i16>@test_int_x86_avx512_mask_vpshrdv_w_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16>* %x2p, <8 x i16> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_w_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT: vpshrdvw (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x72,0x18]
; X86-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X86-NEXT: vpshrdvw %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0xf5,0x08,0x72,0xe2]
; X86-NEXT: vpshrdvw %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x72,0xc2]
; X86-NEXT: vpaddw %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xfd,0xc0]
; X86-NEXT: vpaddw %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfd,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_w_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT: vpshrdvw (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x72,0x1f]
; X64-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X64-NEXT: vpshrdvw %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0xf5,0x08,0x72,0xe2]
; X64-NEXT: vpshrdvw %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x72,0xc2]
; X64-NEXT: vpaddw %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xfd,0xc0]
; X64-NEXT: vpaddw %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfd,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <8 x i16>, <8 x i16>* %x2p
%res = call <8 x i16> @llvm.x86.avx512.mask.vpshrdv.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3)
%res1 = call <8 x i16> @llvm.x86.avx512.mask.vpshrdv.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x4, i8 -1)
%res2 = call <8 x i16> @llvm.x86.avx512.maskz.vpshrdv.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x4, i8 %x3)
%res3 = add <8 x i16> %res, %res1
%res4 = add <8 x i16> %res2, %res3
ret <8 x i16> %res4
}
declare <8 x i32> @llvm.x86.avx512.mask.vpshldv.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
declare <8 x i32> @llvm.x86.avx512.maskz.vpshldv.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_vpshldv_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32>* %x2p, <8 x i32> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_d_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT: vpshldvd (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0x75,0x29,0x71,0x18]
; X86-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X86-NEXT: vpshldvd %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0x75,0x28,0x71,0xe2]
; X86-NEXT: vpshldvd %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xa9,0x71,0xc2]
; X86-NEXT: vpaddd %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xfe,0xc0]
; X86-NEXT: vpaddd %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_d_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT: vpshldvd (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0x75,0x29,0x71,0x1f]
; X64-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X64-NEXT: vpshldvd %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0x75,0x28,0x71,0xe2]
; X64-NEXT: vpshldvd %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xa9,0x71,0xc2]
; X64-NEXT: vpaddd %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xfe,0xc0]
; X64-NEXT: vpaddd %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <8 x i32>, <8 x i32>* %x2p
%res = call <8 x i32> @llvm.x86.avx512.mask.vpshldv.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.vpshldv.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x4, i8 -1)
%res2 = call <8 x i32> @llvm.x86.avx512.maskz.vpshldv.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x4, i8 %x3)
%res3 = add <8 x i32> %res, %res1
%res4 = add <8 x i32> %res2, %res3
ret <8 x i32> %res4
}
declare <4 x i32> @llvm.x86.avx512.mask.vpshldv.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
declare <4 x i32> @llvm.x86.avx512.maskz.vpshldv.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <4 x i32>@test_int_x86_avx512_mask_vpshldv_d_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32>* %x2p, <4 x i32> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_d_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT: vpshldvd (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x09,0x71,0x18]
; X86-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X86-NEXT: vpshldvd %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0x75,0x08,0x71,0xe2]
; X86-NEXT: vpshldvd %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0x89,0x71,0xc2]
; X86-NEXT: vpaddd %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xfe,0xc0]
; X86-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_d_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT: vpshldvd (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x09,0x71,0x1f]
; X64-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X64-NEXT: vpshldvd %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0x75,0x08,0x71,0xe2]
; X64-NEXT: vpshldvd %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0x89,0x71,0xc2]
; X64-NEXT: vpaddd %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xfe,0xc0]
; X64-NEXT: vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <4 x i32>, <4 x i32>* %x2p
%res = call <4 x i32> @llvm.x86.avx512.mask.vpshldv.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.vpshldv.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x4, i8 -1)
%res2 = call <4 x i32> @llvm.x86.avx512.maskz.vpshldv.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x4, i8 %x3)
%res3 = add <4 x i32> %res, %res1
%res4 = add <4 x i32> %res2, %res3
ret <4 x i32> %res4
}
declare <4 x i64> @llvm.x86.avx512.mask.vpshldv.q.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
declare <4 x i64> @llvm.x86.avx512.maskz.vpshldv.q.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_vpshldv_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64>* %x2p, <4 x i64> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_q_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT: vpshldvq (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x71,0x18]
; X86-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X86-NEXT: vpshldvq %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0xf5,0x28,0x71,0xe2]
; X86-NEXT: vpshldvq %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x71,0xc2]
; X86-NEXT: vpaddq %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xd4,0xc0]
; X86-NEXT: vpaddq %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xd4,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_q_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT: vpshldvq (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x71,0x1f]
; X64-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X64-NEXT: vpshldvq %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0xf5,0x28,0x71,0xe2]
; X64-NEXT: vpshldvq %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x71,0xc2]
; X64-NEXT: vpaddq %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xd4,0xc0]
; X64-NEXT: vpaddq %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <4 x i64>, <4 x i64>* %x2p
%res = call <4 x i64> @llvm.x86.avx512.mask.vpshldv.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %x3)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.vpshldv.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x4, i8 -1)
%res2 = call <4 x i64> @llvm.x86.avx512.maskz.vpshldv.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x4, i8 %x3)
%res3 = add <4 x i64> %res, %res1
%res4 = add <4 x i64> %res2, %res3
ret <4 x i64> %res4
}
declare <2 x i64> @llvm.x86.avx512.mask.vpshldv.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
declare <2 x i64> @llvm.x86.avx512.maskz.vpshldv.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
define <2 x i64>@test_int_x86_avx512_mask_vpshldv_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64>* %x2p, <2 x i64> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_q_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT: vpshldvq (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x71,0x18]
; X86-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X86-NEXT: vpshldvq %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0xf5,0x08,0x71,0xe2]
; X86-NEXT: vpshldvq %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x71,0xc2]
; X86-NEXT: vpaddq %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xd4,0xc0]
; X86-NEXT: vpaddq %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xd4,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_q_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT: vpshldvq (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x71,0x1f]
; X64-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X64-NEXT: vpshldvq %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0xf5,0x08,0x71,0xe2]
; X64-NEXT: vpshldvq %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x71,0xc2]
; X64-NEXT: vpaddq %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xd4,0xc0]
; X64-NEXT: vpaddq %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <2 x i64>, <2 x i64>* %x2p
%res = call <2 x i64> @llvm.x86.avx512.mask.vpshldv.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.vpshldv.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x4, i8 -1)
%res2 = call <2 x i64> @llvm.x86.avx512.maskz.vpshldv.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x4, i8 %x3)
%res3 = add <2 x i64> %res, %res1
%res4 = add <2 x i64> %res2, %res3
ret <2 x i64> %res4
}
declare <16 x i16> @llvm.x86.avx512.mask.vpshldv.w.256(<16 x i16>, <16 x i16>, <16 x i16>, i16)
declare <16 x i16> @llvm.x86.avx512.maskz.vpshldv.w.256(<16 x i16>, <16 x i16>, <16 x i16>, i16)
define <16 x i16>@test_int_x86_avx512_mask_vpshldv_w_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16>* %x2p, <16 x i16> %x4, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_w_256:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT: vpshldvw (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x70,0x18]
; X86-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X86-NEXT: vpshldvw %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0xf5,0x28,0x70,0xe2]
; X86-NEXT: vpshldvw %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x70,0xc2]
; X86-NEXT: vpaddw %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xfd,0xc0]
; X86-NEXT: vpaddw %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfd,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_w_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT: vpshldvw (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x70,0x1f]
; X64-NEXT: vmovdqa %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xe0]
; X64-NEXT: vpshldvw %ymm2, %ymm1, %ymm4 # encoding: [0x62,0xf2,0xf5,0x28,0x70,0xe2]
; X64-NEXT: vpshldvw %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x70,0xc2]
; X64-NEXT: vpaddw %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xfd,0xc0]
; X64-NEXT: vpaddw %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfd,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <16 x i16>, <16 x i16>* %x2p
%res = call <16 x i16> @llvm.x86.avx512.mask.vpshldv.w.256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3)
%res1 = call <16 x i16> @llvm.x86.avx512.mask.vpshldv.w.256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x4, i16 -1)
%res2 = call <16 x i16> @llvm.x86.avx512.maskz.vpshldv.w.256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x4, i16 %x3)
%res3 = add <16 x i16> %res, %res1
%res4 = add <16 x i16> %res2, %res3
ret <16 x i16> %res4
}
declare <8 x i16> @llvm.x86.avx512.mask.vpshldv.w.128(<8 x i16>, <8 x i16>, <8 x i16>, i8)
declare <8 x i16> @llvm.x86.avx512.maskz.vpshldv.w.128(<8 x i16>, <8 x i16>, <8 x i16>, i8)
define <8 x i16>@test_int_x86_avx512_mask_vpshldv_w_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16>* %x2p, <8 x i16> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_w_128:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT: vpshldvw (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x70,0x18]
; X86-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X86-NEXT: vpshldvw %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0xf5,0x08,0x70,0xe2]
; X86-NEXT: vpshldvw %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x70,0xc2]
; X86-NEXT: vpaddw %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xfd,0xc0]
; X86-NEXT: vpaddw %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfd,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_w_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT: vpshldvw (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x70,0x1f]
; X64-NEXT: vmovdqa %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xe0]
; X64-NEXT: vpshldvw %xmm2, %xmm1, %xmm4 # encoding: [0x62,0xf2,0xf5,0x08,0x70,0xe2]
; X64-NEXT: vpshldvw %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x70,0xc2]
; X64-NEXT: vpaddw %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xfd,0xc0]
; X64-NEXT: vpaddw %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfd,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <8 x i16>, <8 x i16>* %x2p
%res = call <8 x i16> @llvm.x86.avx512.mask.vpshldv.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3)
%res1 = call <8 x i16> @llvm.x86.avx512.mask.vpshldv.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x4, i8 -1)
%res2 = call <8 x i16> @llvm.x86.avx512.maskz.vpshldv.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x4, i8 %x3)
%res3 = add <8 x i16> %res, %res1
%res4 = add <8 x i16> %res2, %res3
ret <8 x i16> %res4
}