From c12ac0c984b295fb9b7f6723d428f306314c96dd Mon Sep 17 00:00:00 2001 From: Craig Topper Date: Mon, 11 Jun 2018 06:20:24 +0000 Subject: [PATCH] [X86] Add test files for upgrade of vbmi2 expand load and compress store intrinsics that was done in r334381. llvm-svn: 334386 --- .../X86/avx512vbmi2-intrinsics-upgrade.ll | 281 +++++++++++++ .../X86/avx512vbmi2vl-intrinsics-upgrade.ll | 370 ++++++++++++++++++ 2 files changed, 651 insertions(+) create mode 100644 llvm/test/CodeGen/X86/avx512vbmi2-intrinsics-upgrade.ll create mode 100644 llvm/test/CodeGen/X86/avx512vbmi2vl-intrinsics-upgrade.ll diff --git a/llvm/test/CodeGen/X86/avx512vbmi2-intrinsics-upgrade.ll b/llvm/test/CodeGen/X86/avx512vbmi2-intrinsics-upgrade.ll new file mode 100644 index 000000000000..e1b112924185 --- /dev/null +++ b/llvm/test/CodeGen/X86/avx512vbmi2-intrinsics-upgrade.ll @@ -0,0 +1,281 @@ +; 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] + %res = call <32 x i16> @llvm.x86.avx512.mask.expand.load.w.512(i8* %addr, <32 x i16> %data, i32 %mask) + ret <32 x i16> %res +} + +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] + %res = call <32 x i16> @llvm.x86.avx512.mask.expand.load.w.512(i8* %addr, <32 x i16> zeroinitializer, i32 %mask) + ret <32 x i16> %res +} + +declare <32 x i16> @llvm.x86.avx512.mask.expand.load.w.512(i8* %addr, <32 x i16> %data, i32 %mask) + +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] + %res = call <32 x i16> @llvm.x86.avx512.mask.expand.load.w.512(i8* %addr, <32 x i16> %data, i32 -1) + ret <32 x i16> %res +} + +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] + %res = call <64 x i8> @llvm.x86.avx512.mask.expand.load.b.512(i8* %addr, <64 x i8> %data, i64 %mask) + ret <64 x i8> %res +} + +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] + %res = call <64 x i8> @llvm.x86.avx512.mask.expand.load.b.512(i8* %addr, <64 x i8> zeroinitializer, i64 %mask) + ret <64 x i8> %res +} + +declare <64 x i8> @llvm.x86.avx512.mask.expand.load.b.512(i8* %addr, <64 x i8> %data, i64 %mask) + +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] + %res = call <64 x i8> @llvm.x86.avx512.mask.expand.load.b.512(i8* %addr, <64 x i8> %data, i64 -1) + ret <64 x i8> %res +} + +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] + call void @llvm.x86.avx512.mask.compress.store.w.512(i8* %addr, <32 x i16> %data, i32 %mask) + ret void +} + +declare void @llvm.x86.avx512.mask.compress.store.w.512(i8* %addr, <32 x i16> %data, i32 %mask) + +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] + %res = call <32 x i16> @llvm.x86.avx512.mask.compress.w.512(<32 x i16> %data, <32 x i16> %passthru, i32 %mask) + ret <32 x i16> %res +} + +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] + %res = call <32 x i16> @llvm.x86.avx512.mask.compress.w.512(<32 x i16> %data, <32 x i16> zeroinitializer, i32 %mask) + ret <32 x i16> %res +} + +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] + %res = call <32 x i16> @llvm.x86.avx512.mask.compress.w.512(<32 x i16> %data, <32 x i16> undef, i32 -1) + ret <32 x i16> %res +} + +declare <32 x i16> @llvm.x86.avx512.mask.compress.w.512(<32 x i16> %data, <32 x i16> %src0, i32 %mask) + +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] + call void @llvm.x86.avx512.mask.compress.store.w.512(i8* %addr, <32 x i16> %data, i32 -1) + ret void +} + +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] + call void @llvm.x86.avx512.mask.compress.store.b.512(i8* %addr, <64 x i8> %data, i64 %mask) + ret void +} + +declare void @llvm.x86.avx512.mask.compress.store.b.512(i8* %addr, <64 x i8> %data, i64 %mask) + +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: kmovd {{[0-9]+}}(%esp), %k0 # encoding: [0xc4,0xe1,0xf9,0x90,0x44,0x24,0x04] +; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08] +; X86-NEXT: kunpckdq %k0, %k1, %k1 # encoding: [0xc4,0xe1,0xf4,0x4b,0xc8] +; 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] + %res = call <64 x i8> @llvm.x86.avx512.mask.compress.b.512(<64 x i8> %data, <64 x i8> %passthru, i64 %mask) + ret <64 x i8> %res +} + +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: kmovd {{[0-9]+}}(%esp), %k0 # encoding: [0xc4,0xe1,0xf9,0x90,0x44,0x24,0x04] +; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08] +; X86-NEXT: kunpckdq %k0, %k1, %k1 # encoding: [0xc4,0xe1,0xf4,0x4b,0xc8] +; 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] + %res = call <64 x i8> @llvm.x86.avx512.mask.compress.b.512(<64 x i8> %data, <64 x i8> zeroinitializer, i64 %mask) + ret <64 x i8> %res +} + +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] + %res = call <64 x i8> @llvm.x86.avx512.mask.compress.b.512(<64 x i8> %data, <64 x i8> undef, i64 -1) + ret <64 x i8> %res +} + +declare <64 x i8> @llvm.x86.avx512.mask.compress.b.512(<64 x i8> %data, <64 x i8> %src0, i64 %mask) + +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.x86.avx512.mask.compress.store.b.512(i8* %addr, <64 x i8> %data, i64 -1) + ret void +} diff --git a/llvm/test/CodeGen/X86/avx512vbmi2vl-intrinsics-upgrade.ll b/llvm/test/CodeGen/X86/avx512vbmi2vl-intrinsics-upgrade.ll new file mode 100644 index 000000000000..d26f1648e111 --- /dev/null +++ b/llvm/test/CodeGen/X86/avx512vbmi2vl-intrinsics-upgrade.ll @@ -0,0 +1,370 @@ +; 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 +} + +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 +} + +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 +} + +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 +} + +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 +} + +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 +} + +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 +} + +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 +}