llvm-for-llvmta/test/CodeGen/X86/avx512vbmi2-intrinsics.ll

712 lines
42 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512vbmi2 --show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X86
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vbmi2 --show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X64
define <32 x i16> @test_mask_expand_load_w_512(i8* %addr, <32 x i16> %data, i32 %mask) {
; X86-LABEL: test_mask_expand_load_w_512:
; 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: vpexpandw (%eax), %zmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_load_w_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpexpandw (%rdi), %zmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i8* %addr to i16*
%2 = bitcast i32 %mask to <32 x i1>
%3 = call <32 x i16> @llvm.masked.expandload.v32i16(i16* %1, <32 x i1> %2, <32 x i16> %data)
ret <32 x i16> %3
}
define <32 x i16> @test_maskz_expand_load_w_512(i8* %addr, i32 %mask) {
; X86-LABEL: test_maskz_expand_load_w_512:
; 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: vpexpandw (%eax), %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xc9,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_load_w_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpexpandw (%rdi), %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xc9,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i8* %addr to i16*
%2 = bitcast i32 %mask to <32 x i1>
%3 = call <32 x i16> @llvm.masked.expandload.v32i16(i16* %1, <32 x i1> %2, <32 x i16> zeroinitializer)
ret <32 x i16> %3
}
define <32 x i16> @test_expand_load_w_512(i8* %addr, <32 x i16> %data) {
; X86-LABEL: test_expand_load_w_512:
; 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: vpexpandw (%eax), %zmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_expand_load_w_512:
; X64: # %bb.0:
; X64-NEXT: kxnord %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfd,0x46,0xc8]
; X64-NEXT: vpexpandw (%rdi), %zmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i8* %addr to i16*
%2 = call <32 x i16> @llvm.masked.expandload.v32i16(i16* %1, <32 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <32 x i16> %data)
ret <32 x i16> %2
}
define <32 x i16> @test_expand_w_512(<32 x i16> %data) {
; CHECK-LABEL: test_expand_w_512:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%1 = call <32 x i16> @llvm.x86.avx512.mask.expand.v32i16(<32 x i16> %data, <32 x i16> undef, <32 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
ret <32 x i16> %1
}
define <32 x i16> @test_mask_expand_w_512(<32 x i16> %data, <32 x i16> %passthru, i32 %mask) {
; X86-LABEL: test_mask_expand_w_512:
; X86: # %bb.0:
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpexpandw %zmm0, %zmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x62,0xc8]
; X86-NEXT: vmovdqa64 %zmm1, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_w_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandw %zmm0, %zmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x62,0xc8]
; X64-NEXT: vmovdqa64 %zmm1, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i32 %mask to <32 x i1>
%2 = call <32 x i16> @llvm.x86.avx512.mask.expand.v32i16(<32 x i16> %data, <32 x i16> %passthru, <32 x i1> %1)
ret <32 x i16> %2
}
define <32 x i16> @test_maskz_expand_w_512(<32 x i16> %data, i32 %mask) {
; X86-LABEL: test_maskz_expand_w_512:
; X86: # %bb.0:
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpexpandw %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xc9,0x62,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_w_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandw %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xc9,0x62,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i32 %mask to <32 x i1>
%2 = call <32 x i16> @llvm.x86.avx512.mask.expand.v32i16(<32 x i16> %data, <32 x i16> zeroinitializer, <32 x i1> %1)
ret <32 x i16> %2
}
define <64 x i8> @test_mask_expand_load_b_512(i8* %addr, <64 x i8> %data, i64 %mask) {
; X86-LABEL: test_mask_expand_load_b_512:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovq {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpexpandb (%eax), %zmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_load_b_512:
; X64: # %bb.0:
; X64-NEXT: kmovq %rsi, %k1 # encoding: [0xc4,0xe1,0xfb,0x92,0xce]
; X64-NEXT: vpexpandb (%rdi), %zmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i64 %mask to <64 x i1>
%2 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* %addr, <64 x i1> %1, <64 x i8> %data)
ret <64 x i8> %2
}
define <64 x i8> @test_maskz_expand_load_b_512(i8* %addr, i64 %mask) {
; X86-LABEL: test_maskz_expand_load_b_512:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovq {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpexpandb (%eax), %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_load_b_512:
; X64: # %bb.0:
; X64-NEXT: kmovq %rsi, %k1 # encoding: [0xc4,0xe1,0xfb,0x92,0xce]
; X64-NEXT: vpexpandb (%rdi), %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i64 %mask to <64 x i1>
%2 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* %addr, <64 x i1> %1, <64 x i8> zeroinitializer)
ret <64 x i8> %2
}
define <64 x i8> @test_expand_load_b_512(i8* %addr, <64 x i8> %data) {
; X86-LABEL: test_expand_load_b_512:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kxnorq %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfc,0x46,0xc8]
; X86-NEXT: vpexpandb (%eax), %zmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x62,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_expand_load_b_512:
; X64: # %bb.0:
; X64-NEXT: kxnorq %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfc,0x46,0xc8]
; X64-NEXT: vpexpandb (%rdi), %zmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x62,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* %addr, <64 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <64 x i8> %data)
ret <64 x i8> %1
}
define <64 x i8> @test_expand_b_512(<64 x i8> %data) {
; CHECK-LABEL: test_expand_b_512:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%1 = call <64 x i8> @llvm.x86.avx512.mask.expand.v64i8(<64 x i8> %data, <64 x i8> undef, <64 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
ret <64 x i8> %1
}
define <64 x i8> @test_mask_expand_b_512(<64 x i8> %data, <64 x i8> %passthru, i64 %mask) {
; X86-LABEL: test_mask_expand_b_512:
; X86: # %bb.0:
; X86-NEXT: kmovq {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpexpandb %zmm0, %zmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x62,0xc8]
; X86-NEXT: vmovdqa64 %zmm1, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_b_512:
; X64: # %bb.0:
; X64-NEXT: kmovq %rdi, %k1 # encoding: [0xc4,0xe1,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandb %zmm0, %zmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x62,0xc8]
; X64-NEXT: vmovdqa64 %zmm1, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i64 %mask to <64 x i1>
%2 = call <64 x i8> @llvm.x86.avx512.mask.expand.v64i8(<64 x i8> %data, <64 x i8> %passthru, <64 x i1> %1)
ret <64 x i8> %2
}
define <64 x i8> @test_maskz_expand_b_512(<64 x i8> %data, i64 %mask) {
; X86-LABEL: test_maskz_expand_b_512:
; X86: # %bb.0:
; X86-NEXT: kmovq {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpexpandb %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0x62,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_b_512:
; X64: # %bb.0:
; X64-NEXT: kmovq %rdi, %k1 # encoding: [0xc4,0xe1,0xfb,0x92,0xcf]
; X64-NEXT: vpexpandb %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0x62,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i64 %mask to <64 x i1>
%2 = call <64 x i8> @llvm.x86.avx512.mask.expand.v64i8(<64 x i8> %data, <64 x i8> zeroinitializer, <64 x i1> %1)
ret <64 x i8> %2
}
define void @test_mask_compress_store_w_512(i8* %addr, <32 x i16> %data, i32 %mask) {
; X86-LABEL: test_mask_compress_store_w_512:
; 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: vpcompressw %zmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x63,0x00]
; X86-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_store_w_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vpcompressw %zmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x63,0x07]
; X64-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i8* %addr to i16*
%2 = bitcast i32 %mask to <32 x i1>
call void @llvm.masked.compressstore.v32i16(<32 x i16> %data, i16* %1, <32 x i1> %2)
ret void
}
define void @test_compress_store_w_512(i8* %addr, <32 x i16> %data) {
; X86-LABEL: test_compress_store_w_512:
; 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: vpcompressw %zmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x63,0x00]
; X86-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_compress_store_w_512:
; X64: # %bb.0:
; X64-NEXT: kxnord %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfd,0x46,0xc8]
; X64-NEXT: vpcompressw %zmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x63,0x07]
; X64-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i8* %addr to i16*
call void @llvm.masked.compressstore.v32i16(<32 x i16> %data, i16* %1, <32 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
ret void
}
define <32 x i16> @test_mask_compress_w_512(<32 x i16> %data, <32 x i16> %passthru, i32 %mask) {
; X86-LABEL: test_mask_compress_w_512:
; X86: # %bb.0:
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpcompressw %zmm0, %zmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x63,0xc1]
; X86-NEXT: vmovdqa64 %zmm1, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_w_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressw %zmm0, %zmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x49,0x63,0xc1]
; X64-NEXT: vmovdqa64 %zmm1, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i32 %mask to <32 x i1>
%2 = call <32 x i16> @llvm.x86.avx512.mask.compress.v32i16(<32 x i16> %data, <32 x i16> %passthru, <32 x i1> %1)
ret <32 x i16> %2
}
define <32 x i16> @test_maskz_compress_w_512(<32 x i16> %data, i32 %mask) {
; X86-LABEL: test_maskz_compress_w_512:
; X86: # %bb.0:
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpcompressw %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xc9,0x63,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_compress_w_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressw %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xc9,0x63,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i32 %mask to <32 x i1>
%2 = call <32 x i16> @llvm.x86.avx512.mask.compress.v32i16(<32 x i16> %data, <32 x i16> zeroinitializer, <32 x i1> %1)
ret <32 x i16> %2
}
define <32 x i16> @test_compress_w_512(<32 x i16> %data) {
; CHECK-LABEL: test_compress_w_512:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%1 = call <32 x i16> @llvm.x86.avx512.mask.compress.v32i16(<32 x i16> %data, <32 x i16> undef, <32 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
ret <32 x i16> %1
}
define void @test_mask_compress_store_b_512(i8* %addr, <64 x i8> %data, i64 %mask) {
; X86-LABEL: test_mask_compress_store_b_512:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kmovq {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT: vpcompressb %zmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x63,0x00]
; X86-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_store_b_512:
; X64: # %bb.0:
; X64-NEXT: kmovq %rsi, %k1 # encoding: [0xc4,0xe1,0xfb,0x92,0xce]
; X64-NEXT: vpcompressb %zmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x63,0x07]
; X64-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i64 %mask to <64 x i1>
call void @llvm.masked.compressstore.v64i8(<64 x i8> %data, i8* %addr, <64 x i1> %1)
ret void
}
define void @test_compress_store_b_512(i8* %addr, <64 x i8> %data) {
; X86-LABEL: test_compress_store_b_512:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: kxnorq %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfc,0x46,0xc8]
; X86-NEXT: vpcompressb %zmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x63,0x00]
; X86-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_compress_store_b_512:
; X64: # %bb.0:
; X64-NEXT: kxnorq %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfc,0x46,0xc8]
; X64-NEXT: vpcompressb %zmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x63,0x07]
; X64-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT: retq # encoding: [0xc3]
call void @llvm.masked.compressstore.v64i8(<64 x i8> %data, i8* %addr, <64 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
ret void
}
define <64 x i8> @test_mask_compress_b_512(<64 x i8> %data, <64 x i8> %passthru, i64 %mask) {
; X86-LABEL: test_mask_compress_b_512:
; X86: # %bb.0:
; X86-NEXT: kmovq {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpcompressb %zmm0, %zmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x63,0xc1]
; X86-NEXT: vmovdqa64 %zmm1, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_b_512:
; X64: # %bb.0:
; X64-NEXT: kmovq %rdi, %k1 # encoding: [0xc4,0xe1,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressb %zmm0, %zmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x63,0xc1]
; X64-NEXT: vmovdqa64 %zmm1, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i64 %mask to <64 x i1>
%2 = call <64 x i8> @llvm.x86.avx512.mask.compress.v64i8(<64 x i8> %data, <64 x i8> %passthru, <64 x i1> %1)
ret <64 x i8> %2
}
define <64 x i8> @test_maskz_compress_b_512(<64 x i8> %data, i64 %mask) {
; X86-LABEL: test_maskz_compress_b_512:
; X86: # %bb.0:
; X86-NEXT: kmovq {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpcompressb %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0x63,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_compress_b_512:
; X64: # %bb.0:
; X64-NEXT: kmovq %rdi, %k1 # encoding: [0xc4,0xe1,0xfb,0x92,0xcf]
; X64-NEXT: vpcompressb %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0x63,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = bitcast i64 %mask to <64 x i1>
%2 = call <64 x i8> @llvm.x86.avx512.mask.compress.v64i8(<64 x i8> %data, <64 x i8> zeroinitializer, <64 x i1> %1)
ret <64 x i8> %2
}
define <64 x i8> @test_compress_b_512(<64 x i8> %data) {
; CHECK-LABEL: test_compress_b_512:
; CHECK: # %bb.0:
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%1 = call <64 x i8> @llvm.x86.avx512.mask.compress.v64i8(<64 x i8> %data, <64 x i8> undef, <64 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
ret <64 x i8> %1
}
define <16 x i32> @test_int_x86_avx512_mask_vpshld_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x3, i16 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_d_512:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpshldd $22, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x49,0x71,0xd1,0x16]
; X86-NEXT: vpshldd $23, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0x7d,0x48,0x71,0xc1,0x17]
; X86-NEXT: vpaddd %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0x6d,0x48,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_d_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldd $22, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x49,0x71,0xd1,0x16]
; X64-NEXT: vpshldd $23, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0x7d,0x48,0x71,0xc1,0x17]
; X64-NEXT: vpaddd %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0x6d,0x48,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> <i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22>)
%2 = bitcast i16 %x4 to <16 x i1>
%3 = select <16 x i1> %2, <16 x i32> %1, <16 x i32> %x3
%4 = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> <i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23>)
%res2 = add <16 x i32> %3, %4
ret <16 x i32> %res2
}
define <8 x i64> @test_int_x86_avx512_mask_vpshld_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_q_512:
; 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: vpshldq $22, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0x71,0xd1,0x16]
; X86-NEXT: vpshldq $23, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0xfd,0x48,0x71,0xc1,0x17]
; X86-NEXT: vpaddq %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0xed,0x48,0xd4,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_q_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldq $22, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0x71,0xd1,0x16]
; X64-NEXT: vpshldq $23, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0xfd,0x48,0x71,0xc1,0x17]
; X64-NEXT: vpaddq %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0xed,0x48,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <8 x i64> @llvm.fshl.v8i64(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> <i64 22, i64 22, i64 22, i64 22, i64 22, i64 22, i64 22, i64 22>)
%2 = bitcast i8 %x4 to <8 x i1>
%3 = select <8 x i1> %2, <8 x i64> %1, <8 x i64> %x3
%4 = call <8 x i64> @llvm.fshl.v8i64(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> <i64 23, i64 23, i64 23, i64 23, i64 23, i64 23, i64 23, i64 23>)
%res2 = add <8 x i64> %3, %4
ret <8 x i64> %res2
}
define <32 x i16> @test_int_x86_avx512_mask_vpshld_w_512(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x3, i32 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_w_512:
; X86: # %bb.0:
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpshldw $6, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0x70,0xd1,0x06]
; X86-NEXT: vpshldw $7, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0xfd,0x48,0x70,0xc1,0x07]
; X86-NEXT: vpaddw %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0x6d,0x48,0xfd,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_w_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshldw $6, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0x70,0xd1,0x06]
; X64-NEXT: vpshldw $7, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0xfd,0x48,0x70,0xc1,0x07]
; X64-NEXT: vpaddw %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0x6d,0x48,0xfd,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> <i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6>)
%2 = bitcast i32 %x4 to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %x3
%4 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>)
%res2 = add <32 x i16> %3, %4
ret <32 x i16> %res2
}
define <16 x i32> @test_int_x86_avx512_mask_vpshrd_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x3, i16 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_d_512:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpshrdd $22, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x49,0x73,0xd1,0x16]
; X86-NEXT: vpshrdd $23, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0x7d,0x48,0x73,0xc1,0x17]
; X86-NEXT: vpaddd %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0x6d,0x48,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_d_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdd $22, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x49,0x73,0xd1,0x16]
; X64-NEXT: vpshrdd $23, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0x7d,0x48,0x73,0xc1,0x17]
; X64-NEXT: vpaddd %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0x6d,0x48,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <16 x i32> @llvm.fshr.v16i32(<16 x i32> %x1, <16 x i32> %x0, <16 x i32> <i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22>)
%2 = bitcast i16 %x4 to <16 x i1>
%3 = select <16 x i1> %2, <16 x i32> %1, <16 x i32> %x3
%4 = call <16 x i32> @llvm.fshr.v16i32(<16 x i32> %x1, <16 x i32> %x0, <16 x i32> <i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23>)
%res2 = add <16 x i32> %3, %4
ret <16 x i32> %res2
}
define <8 x i64> @test_int_x86_avx512_mask_vpshrd_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_q_512:
; 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: vpshrdq $22, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0x73,0xd1,0x16]
; X86-NEXT: vpshrdq $23, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0xfd,0x48,0x73,0xc1,0x17]
; X86-NEXT: vpaddq %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0xed,0x48,0xd4,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_q_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdq $22, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0x73,0xd1,0x16]
; X64-NEXT: vpshrdq $23, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0xfd,0x48,0x73,0xc1,0x17]
; X64-NEXT: vpaddq %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0xed,0x48,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <8 x i64> @llvm.fshr.v8i64(<8 x i64> %x1, <8 x i64> %x0, <8 x i64> <i64 22, i64 22, i64 22, i64 22, i64 22, i64 22, i64 22, i64 22>)
%2 = bitcast i8 %x4 to <8 x i1>
%3 = select <8 x i1> %2, <8 x i64> %1, <8 x i64> %x3
%4 = call <8 x i64> @llvm.fshr.v8i64(<8 x i64> %x1, <8 x i64> %x0, <8 x i64> <i64 23, i64 23, i64 23, i64 23, i64 23, i64 23, i64 23, i64 23>)
%res2 = add <8 x i64> %3, %4
ret <8 x i64> %res2
}
define <32 x i16> @test_int_x86_avx512_mask_vpshrd_w_512(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x3, i32 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_w_512:
; X86: # %bb.0:
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vpshrdw $6, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0x72,0xd1,0x06]
; X86-NEXT: vpshrdw $7, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0xfd,0x48,0x72,0xc1,0x07]
; X86-NEXT: vpaddw %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0x6d,0x48,0xfd,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_w_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vpshrdw $6, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0x72,0xd1,0x06]
; X64-NEXT: vpshrdw $7, %zmm1, %zmm0, %zmm0 # encoding: [0x62,0xf3,0xfd,0x48,0x72,0xc1,0x07]
; X64-NEXT: vpaddw %zmm0, %zmm2, %zmm0 # encoding: [0x62,0xf1,0x6d,0x48,0xfd,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%1 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %x1, <32 x i16> %x0, <32 x i16> <i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6>)
%2 = bitcast i32 %x4 to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %x3
%4 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %x1, <32 x i16> %x0, <32 x i16> <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>)
%res2 = add <32 x i16> %3, %4
ret <32 x i16> %res2
}
define <16 x i32> @test_int_x86_avx512_mask_vpshrdv_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32>* %x2p, <16 x i32> %x4, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_d_512:
; 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: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X86-NEXT: vpshrdvd (%eax), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x49,0x73,0x18]
; X86-NEXT: vpshrdvd %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xc9,0x73,0xc2]
; X86-NEXT: vpaddd %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0x65,0x48,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_d_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X64-NEXT: vpshrdvd (%rdi), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x49,0x73,0x1f]
; X64-NEXT: vpshrdvd %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xc9,0x73,0xc2]
; X64-NEXT: vpaddd %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0x65,0x48,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <16 x i32>, <16 x i32>* %x2p
%1 = call <16 x i32> @llvm.fshr.v16i32(<16 x i32> %x1, <16 x i32> %x0, <16 x i32> %x2)
%2 = bitcast i16 %x3 to <16 x i1>
%3 = select <16 x i1> %2, <16 x i32> %1, <16 x i32> %x0
%4 = call <16 x i32> @llvm.fshr.v16i32(<16 x i32> %x1, <16 x i32> %x0, <16 x i32> %x4)
%5 = bitcast i16 %x3 to <16 x i1>
%6 = select <16 x i1> %5, <16 x i32> %4, <16 x i32> zeroinitializer
%res3 = add <16 x i32> %3, %6
ret <16 x i32> %res3
}
define <8 x i64> @test_int_x86_avx512_mask_vpshrdv_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64>* %x2p, <8 x i64> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_q_512:
; 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: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X86-NEXT: vpshrdvq (%eax), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x49,0x73,0x18]
; X86-NEXT: vpshrdvq %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xc9,0x73,0xc2]
; X86-NEXT: vpaddq %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0xe5,0x48,0xd4,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_q_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X64-NEXT: vpshrdvq (%rdi), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x49,0x73,0x1f]
; X64-NEXT: vpshrdvq %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xc9,0x73,0xc2]
; X64-NEXT: vpaddq %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0xe5,0x48,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <8 x i64>, <8 x i64>* %x2p
%1 = call <8 x i64> @llvm.fshr.v8i64(<8 x i64> %x1, <8 x i64> %x0, <8 x i64> %x2)
%2 = bitcast i8 %x3 to <8 x i1>
%3 = select <8 x i1> %2, <8 x i64> %1, <8 x i64> %x0
%4 = call <8 x i64> @llvm.fshr.v8i64(<8 x i64> %x1, <8 x i64> %x0, <8 x i64> %x4)
%5 = bitcast i8 %x3 to <8 x i1>
%6 = select <8 x i1> %5, <8 x i64> %4, <8 x i64> zeroinitializer
%res3 = add <8 x i64> %3, %6
ret <8 x i64> %res3
}
define <32 x i16> @test_int_x86_avx512_mask_vpshrdv_w_512(<32 x i16> %x0, <32 x i16> %x1, <32 x i16>* %x2p, <32 x i16> %x4, i32 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_w_512:
; 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: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X86-NEXT: vpshrdvw (%eax), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x49,0x72,0x18]
; X86-NEXT: vpshrdvw %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xc9,0x72,0xc2]
; X86-NEXT: vpaddw %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0x65,0x48,0xfd,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_w_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X64-NEXT: vpshrdvw (%rdi), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x49,0x72,0x1f]
; X64-NEXT: vpshrdvw %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xc9,0x72,0xc2]
; X64-NEXT: vpaddw %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0x65,0x48,0xfd,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <32 x i16>, <32 x i16>* %x2p
%1 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %x1, <32 x i16> %x0, <32 x i16> %x2)
%2 = bitcast i32 %x3 to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %x0
%4 = call <32 x i16> @llvm.fshr.v32i16(<32 x i16> %x1, <32 x i16> %x0, <32 x i16> %x4)
%5 = bitcast i32 %x3 to <32 x i1>
%6 = select <32 x i1> %5, <32 x i16> %4, <32 x i16> zeroinitializer
%res3 = add <32 x i16> %3, %6
ret <32 x i16> %res3
}
define <16 x i32> @test_int_x86_avx512_mask_vpshldv_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32>* %x2p, <16 x i32> %x4, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_d_512:
; 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: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X86-NEXT: vpshldvd (%eax), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x49,0x71,0x18]
; X86-NEXT: vpshldvd %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xc9,0x71,0xc2]
; X86-NEXT: vpaddd %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0x65,0x48,0xfe,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_d_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X64-NEXT: vpshldvd (%rdi), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x49,0x71,0x1f]
; X64-NEXT: vpshldvd %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xc9,0x71,0xc2]
; X64-NEXT: vpaddd %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0x65,0x48,0xfe,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <16 x i32>, <16 x i32>* %x2p
%1 = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2)
%2 = bitcast i16 %x3 to <16 x i1>
%3 = select <16 x i1> %2, <16 x i32> %1, <16 x i32> %x0
%4 = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x4)
%5 = bitcast i16 %x3 to <16 x i1>
%6 = select <16 x i1> %5, <16 x i32> %4, <16 x i32> zeroinitializer
%res3 = add <16 x i32> %3, %6
ret <16 x i32> %res3
}
define <8 x i64> @test_int_x86_avx512_mask_vpshldv_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64>* %x2p, <8 x i64> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_q_512:
; 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: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X86-NEXT: vpshldvq (%eax), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x49,0x71,0x18]
; X86-NEXT: vpshldvq %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xc9,0x71,0xc2]
; X86-NEXT: vpaddq %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0xe5,0x48,0xd4,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_q_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X64-NEXT: vpshldvq (%rdi), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x49,0x71,0x1f]
; X64-NEXT: vpshldvq %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xc9,0x71,0xc2]
; X64-NEXT: vpaddq %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0xe5,0x48,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <8 x i64>, <8 x i64>* %x2p
%1 = call <8 x i64> @llvm.fshl.v8i64(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2)
%2 = bitcast i8 %x3 to <8 x i1>
%3 = select <8 x i1> %2, <8 x i64> %1, <8 x i64> %x0
%4 = call <8 x i64> @llvm.fshl.v8i64(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x4)
%5 = bitcast i8 %x3 to <8 x i1>
%6 = select <8 x i1> %5, <8 x i64> %4, <8 x i64> zeroinitializer
%res3 = add <8 x i64> %3, %6
ret <8 x i64> %res3
}
define <32 x i16> @test_int_x86_avx512_mask_vpshldv_w_512(<32 x i16> %x0, <32 x i16> %x1, <32 x i16>* %x2p, <32 x i16> %x4, i32 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_w_512:
; 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: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X86-NEXT: vpshldvw (%eax), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x49,0x70,0x18]
; X86-NEXT: vpshldvw %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xc9,0x70,0xc2]
; X86-NEXT: vpaddw %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0x65,0x48,0xfd,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_w_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT: vmovdqa64 %zmm0, %zmm3 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xd8]
; X64-NEXT: vpshldvw (%rdi), %zmm1, %zmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x49,0x70,0x1f]
; X64-NEXT: vpshldvw %zmm2, %zmm1, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xc9,0x70,0xc2]
; X64-NEXT: vpaddw %zmm0, %zmm3, %zmm0 # encoding: [0x62,0xf1,0x65,0x48,0xfd,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%x2 = load <32 x i16>, <32 x i16>* %x2p
%1 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x2)
%2 = bitcast i32 %x3 to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %x0
%4 = call <32 x i16> @llvm.fshl.v32i16(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x4)
%5 = bitcast i32 %x3 to <32 x i1>
%6 = select <32 x i1> %5, <32 x i16> %4, <32 x i16> zeroinitializer
%res3 = add <32 x i16> %3, %6
ret <32 x i16> %res3
}
declare <16 x i32> @llvm.fshl.v16i32(<16 x i32>, <16 x i32>, <16 x i32>)
declare <8 x i64> @llvm.fshl.v8i64(<8 x i64>, <8 x i64>, <8 x i64>)
declare <32 x i16> @llvm.fshl.v32i16(<32 x i16>, <32 x i16>, <32 x i16>)
declare <16 x i32> @llvm.fshr.v16i32(<16 x i32>, <16 x i32>, <16 x i32>)
declare <8 x i64> @llvm.fshr.v8i64(<8 x i64>, <8 x i64>, <8 x i64>)
declare <32 x i16> @llvm.fshr.v32i16(<32 x i16>, <32 x i16>, <32 x i16>)
declare <32 x i16> @llvm.masked.expandload.v32i16(i16*, <32 x i1>, <32 x i16>)
declare <64 x i8> @llvm.masked.expandload.v64i8(i8*, <64 x i1>, <64 x i8>)
declare void @llvm.masked.compressstore.v32i16(<32 x i16>, i16*, <32 x i1>)
declare void @llvm.masked.compressstore.v64i8(<64 x i8>, i8*, <64 x i1>)
declare <32 x i16> @llvm.x86.avx512.mask.expand.v32i16(<32 x i16>, <32 x i16>, <32 x i1>)
declare <64 x i8> @llvm.x86.avx512.mask.expand.v64i8(<64 x i8>, <64 x i8>, <64 x i1>)
declare <32 x i16> @llvm.x86.avx512.mask.compress.v32i16(<32 x i16>, <32 x i16>, <32 x i1>)
declare <64 x i8> @llvm.x86.avx512.mask.compress.v64i8(<64 x i8>, <64 x i8>, <64 x i1>)