From 61bb9eeae651b68a990557d3e6d25033451f0f0b Mon Sep 17 00:00:00 2001
From: Craig Topper <craig.topper@intel.com>
Date: Thu, 28 Sep 2017 18:45:29 +0000
Subject: [PATCH] [AVX512] Add avx512bw command lines to 128-bit idiv tests.

The multiply lowering on some of the tests can take advantage of the vpmovwb to simplify the truncate.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@314448 91177308-0d34-0410-b5e6-96231b3b80d8
---
 test/CodeGen/X86/vector-idiv-sdiv-128.ll | 78 ++++++++++++++++--------
 test/CodeGen/X86/vector-idiv-udiv-128.ll | 69 +++++++++++++--------
 2 files changed, 96 insertions(+), 51 deletions(-)

diff --git a/test/CodeGen/X86/vector-idiv-sdiv-128.ll b/test/CodeGen/X86/vector-idiv-sdiv-128.ll
index 87cf2026d1e..51c47ac8e3c 100644
--- a/test/CodeGen/X86/vector-idiv-sdiv-128.ll
+++ b/test/CodeGen/X86/vector-idiv-sdiv-128.ll
@@ -2,7 +2,8 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE --check-prefix=SSE41
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2 --check-prefix=AVX2NOBW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX --check-prefix=AVX2 --check-prefix=AVX512BW
 
 ;
 ; sdiv by 7
@@ -585,32 +586,55 @@ define <16 x i8> @test_rem7_16i8(<16 x i8> %a) nounwind {
 ; AVX1-NEXT:    vpsubb %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: test_rem7_16i8:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vpmovsxbw %xmm0, %ymm1
-; AVX2-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vpsrlw $8, %ymm1, %ymm1
-; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm2
-; AVX2-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
-; AVX2-NEXT:    vpaddb %xmm0, %xmm1, %xmm1
-; AVX2-NEXT:    vpsrlw $2, %xmm1, %xmm2
-; AVX2-NEXT:    vpand {{.*}}(%rip), %xmm2, %xmm2
-; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32]
-; AVX2-NEXT:    vpxor %xmm3, %xmm2, %xmm2
-; AVX2-NEXT:    vpsubb %xmm3, %xmm2, %xmm2
-; AVX2-NEXT:    vpsrlw $7, %xmm1, %xmm1
-; AVX2-NEXT:    vpand {{.*}}(%rip), %xmm1, %xmm1
-; AVX2-NEXT:    vpaddb %xmm1, %xmm2, %xmm1
-; AVX2-NEXT:    vpmovsxbw %xmm1, %ymm1
-; AVX2-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm2
-; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
-; AVX2-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
-; AVX2-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
-; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
-; AVX2-NEXT:    vpsubb %xmm1, %xmm0, %xmm0
-; AVX2-NEXT:    vzeroupper
-; AVX2-NEXT:    retq
+; AVX2NOBW-LABEL: test_rem7_16i8:
+; AVX2NOBW:       # BB#0:
+; AVX2NOBW-NEXT:    vpmovsxbw %xmm0, %ymm1
+; AVX2NOBW-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
+; AVX2NOBW-NEXT:    vpsrlw $8, %ymm1, %ymm1
+; AVX2NOBW-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX2NOBW-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
+; AVX2NOBW-NEXT:    vpaddb %xmm0, %xmm1, %xmm1
+; AVX2NOBW-NEXT:    vpsrlw $2, %xmm1, %xmm2
+; AVX2NOBW-NEXT:    vpand {{.*}}(%rip), %xmm2, %xmm2
+; AVX2NOBW-NEXT:    vmovdqa {{.*#+}} xmm3 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32]
+; AVX2NOBW-NEXT:    vpxor %xmm3, %xmm2, %xmm2
+; AVX2NOBW-NEXT:    vpsubb %xmm3, %xmm2, %xmm2
+; AVX2NOBW-NEXT:    vpsrlw $7, %xmm1, %xmm1
+; AVX2NOBW-NEXT:    vpand {{.*}}(%rip), %xmm1, %xmm1
+; AVX2NOBW-NEXT:    vpaddb %xmm1, %xmm2, %xmm1
+; AVX2NOBW-NEXT:    vpmovsxbw %xmm1, %ymm1
+; AVX2NOBW-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
+; AVX2NOBW-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX2NOBW-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
+; AVX2NOBW-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
+; AVX2NOBW-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
+; AVX2NOBW-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
+; AVX2NOBW-NEXT:    vpsubb %xmm1, %xmm0, %xmm0
+; AVX2NOBW-NEXT:    vzeroupper
+; AVX2NOBW-NEXT:    retq
+;
+; AVX512BW-LABEL: test_rem7_16i8:
+; AVX512BW:       # BB#0:
+; AVX512BW-NEXT:    vpmovsxbw %xmm0, %ymm1
+; AVX512BW-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
+; AVX512BW-NEXT:    vpsrlw $8, %ymm1, %ymm1
+; AVX512BW-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX512BW-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpaddb %xmm0, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpsrlw $2, %xmm1, %xmm2
+; AVX512BW-NEXT:    vpand {{.*}}(%rip), %xmm2, %xmm2
+; AVX512BW-NEXT:    vmovdqa {{.*#+}} xmm3 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32]
+; AVX512BW-NEXT:    vpxor %xmm3, %xmm2, %xmm2
+; AVX512BW-NEXT:    vpsubb %xmm3, %xmm2, %xmm2
+; AVX512BW-NEXT:    vpsrlw $7, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpand {{.*}}(%rip), %xmm1, %xmm1
+; AVX512BW-NEXT:    vpaddb %xmm1, %xmm2, %xmm1
+; AVX512BW-NEXT:    vpmovsxbw %xmm1, %ymm1
+; AVX512BW-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
+; AVX512BW-NEXT:    vpmovwb %zmm1, %ymm1
+; AVX512BW-NEXT:    vpsubb %xmm1, %xmm0, %xmm0
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
   %res = srem <16 x i8> %a, <i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7>
   ret <16 x i8> %res
 }
diff --git a/test/CodeGen/X86/vector-idiv-udiv-128.ll b/test/CodeGen/X86/vector-idiv-udiv-128.ll
index 8138442b3ea..dbf7144d0af 100644
--- a/test/CodeGen/X86/vector-idiv-udiv-128.ll
+++ b/test/CodeGen/X86/vector-idiv-udiv-128.ll
@@ -2,7 +2,8 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE --check-prefix=SSE41
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2 --check-prefix=AVX2NOBW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX --check-prefix=AVX2 --check-prefix=AVX512BW
 
 ;
 ; udiv by 7
@@ -556,29 +557,49 @@ define <16 x i8> @test_rem7_16i8(<16 x i8> %a) nounwind {
 ; AVX1-NEXT:    vpsubb %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: test_rem7_16i8:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vpmovzxbw {{.*#+}} ymm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
-; AVX2-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vpsrlw $8, %ymm1, %ymm1
-; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm2
-; AVX2-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
-; AVX2-NEXT:    vpsubb %xmm1, %xmm0, %xmm2
-; AVX2-NEXT:    vpsrlw $1, %xmm2, %xmm2
-; AVX2-NEXT:    vpand {{.*}}(%rip), %xmm2, %xmm2
-; AVX2-NEXT:    vpaddb %xmm1, %xmm2, %xmm1
-; AVX2-NEXT:    vpsrlw $2, %xmm1, %xmm1
-; AVX2-NEXT:    vpand {{.*}}(%rip), %xmm1, %xmm1
-; AVX2-NEXT:    vpmovsxbw %xmm1, %ymm1
-; AVX2-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
-; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm2
-; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
-; AVX2-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
-; AVX2-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
-; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
-; AVX2-NEXT:    vpsubb %xmm1, %xmm0, %xmm0
-; AVX2-NEXT:    vzeroupper
-; AVX2-NEXT:    retq
+; AVX2NOBW-LABEL: test_rem7_16i8:
+; AVX2NOBW:       # BB#0:
+; AVX2NOBW-NEXT:    vpmovzxbw {{.*#+}} ymm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
+; AVX2NOBW-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
+; AVX2NOBW-NEXT:    vpsrlw $8, %ymm1, %ymm1
+; AVX2NOBW-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX2NOBW-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
+; AVX2NOBW-NEXT:    vpsubb %xmm1, %xmm0, %xmm2
+; AVX2NOBW-NEXT:    vpsrlw $1, %xmm2, %xmm2
+; AVX2NOBW-NEXT:    vpand {{.*}}(%rip), %xmm2, %xmm2
+; AVX2NOBW-NEXT:    vpaddb %xmm1, %xmm2, %xmm1
+; AVX2NOBW-NEXT:    vpsrlw $2, %xmm1, %xmm1
+; AVX2NOBW-NEXT:    vpand {{.*}}(%rip), %xmm1, %xmm1
+; AVX2NOBW-NEXT:    vpmovsxbw %xmm1, %ymm1
+; AVX2NOBW-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
+; AVX2NOBW-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX2NOBW-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
+; AVX2NOBW-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
+; AVX2NOBW-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
+; AVX2NOBW-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
+; AVX2NOBW-NEXT:    vpsubb %xmm1, %xmm0, %xmm0
+; AVX2NOBW-NEXT:    vzeroupper
+; AVX2NOBW-NEXT:    retq
+;
+; AVX512BW-LABEL: test_rem7_16i8:
+; AVX512BW:       # BB#0:
+; AVX512BW-NEXT:    vpmovzxbw {{.*#+}} ymm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
+; AVX512BW-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
+; AVX512BW-NEXT:    vpsrlw $8, %ymm1, %ymm1
+; AVX512BW-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX512BW-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpsubb %xmm1, %xmm0, %xmm2
+; AVX512BW-NEXT:    vpsrlw $1, %xmm2, %xmm2
+; AVX512BW-NEXT:    vpand {{.*}}(%rip), %xmm2, %xmm2
+; AVX512BW-NEXT:    vpaddb %xmm1, %xmm2, %xmm1
+; AVX512BW-NEXT:    vpsrlw $2, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpand {{.*}}(%rip), %xmm1, %xmm1
+; AVX512BW-NEXT:    vpmovsxbw %xmm1, %ymm1
+; AVX512BW-NEXT:    vpmullw {{.*}}(%rip), %ymm1, %ymm1
+; AVX512BW-NEXT:    vpmovwb %zmm1, %ymm1
+; AVX512BW-NEXT:    vpsubb %xmm1, %xmm0, %xmm0
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
   %res = urem <16 x i8> %a, <i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7>
   ret <16 x i8> %res
 }
-- 
2.49.0