From b4a0df9a4a8a3dac612c1f6cde089d190951dc4a Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Thu, 12 Feb 2015 22:47:45 +0000
Subject: [PATCH] Ensure integer domain on general shuffle stack folding tests

llvm-svn: 228972
---
 llvm/test/CodeGen/X86/stack-folding-int-avx1.ll  | 16 ++++++++++++----
 llvm/test/CodeGen/X86/stack-folding-int-avx2.ll  | 16 ++++++++++++----
 llvm/test/CodeGen/X86/stack-folding-int-sse42.ll | 16 ++++++++++++----
 3 files changed, 36 insertions(+), 12 deletions(-)

diff --git a/llvm/test/CodeGen/X86/stack-folding-int-avx1.ll b/llvm/test/CodeGen/X86/stack-folding-int-avx1.ll
index 22d86a7e5f78..cea89283306a 100644
--- a/llvm/test/CodeGen/X86/stack-folding-int-avx1.ll
+++ b/llvm/test/CodeGen/X86/stack-folding-int-avx1.ll
@@ -1078,7 +1078,9 @@ define <4 x i32> @stack_fold_punpckhdq(<4 x i32> %a0, <4 x i32> %a1) {
   ;CHECK:       vpunpckhdq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <4 x i32> %a0, <4 x i32> %a1, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-  ret <4 x i32> %2
+  ; add forces execution domain
+  %3 = add <4 x i32> %2, <i32 1, i32 1, i32 1, i32 1>
+  ret <4 x i32> %3
 }
 
 define <2 x i64> @stack_fold_punpckhqdq(<2 x i64> %a0, <2 x i64> %a1) {
@@ -1086,7 +1088,9 @@ define <2 x i64> @stack_fold_punpckhqdq(<2 x i64> %a0, <2 x i64> %a1) {
   ;CHECK:       vpunpckhqdq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <2 x i64> %a0, <2 x i64> %a1, <2 x i32> <i32 1, i32 3>
-  ret <2 x i64> %2
+  ; add forces execution domain
+  %3 = add <2 x i64> %2, <i64 1, i64 1>
+  ret <2 x i64> %3
 }
 
 define <8 x i16> @stack_fold_punpckhwd(<8 x i16> %a0, <8 x i16> %a1) {
@@ -1110,7 +1114,9 @@ define <4 x i32> @stack_fold_punpckldq(<4 x i32> %a0, <4 x i32> %a1) {
   ;CHECK:       vpunpckldq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <4 x i32> %a0, <4 x i32> %a1, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
-  ret <4 x i32> %2
+  ; add forces execution domain
+  %3 = add <4 x i32> %2, <i32 1, i32 1, i32 1, i32 1>
+  ret <4 x i32> %3
 }
 
 define <2 x i64> @stack_fold_punpcklqdq(<2 x i64> %a0, <2 x i64> %a1) {
@@ -1118,7 +1124,9 @@ define <2 x i64> @stack_fold_punpcklqdq(<2 x i64> %a0, <2 x i64> %a1) {
   ;CHECK:       vpunpcklqdq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <2 x i64> %a0, <2 x i64> %a1, <2 x i32> <i32 0, i32 2>
-  ret <2 x i64> %2
+  ; add forces execution domain
+  %3 = add <2 x i64> %2, <i64 1, i64 1>
+  ret <2 x i64> %3
 }
 
 define <8 x i16> @stack_fold_punpcklwd(<8 x i16> %a0, <8 x i16> %a1) {
diff --git a/llvm/test/CodeGen/X86/stack-folding-int-avx2.ll b/llvm/test/CodeGen/X86/stack-folding-int-avx2.ll
index de3a91db765b..39169e67089b 100644
--- a/llvm/test/CodeGen/X86/stack-folding-int-avx2.ll
+++ b/llvm/test/CodeGen/X86/stack-folding-int-avx2.ll
@@ -1130,7 +1130,9 @@ define <8 x i32> @stack_fold_punpckhdq(<8 x i32> %a0, <8 x i32> %a1) {
   ;CHECK:       vpunpckhdq {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <8 x i32> %a0, <8 x i32> %a1, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
-  ret <8 x i32> %2
+  ; add forces execution domain
+  %3 = add <8 x i32> %2, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+  ret <8 x i32> %3
 }
 
 define <4 x i64> @stack_fold_punpckhqdq(<4 x i64> %a0, <4 x i64> %a1) {
@@ -1138,7 +1140,9 @@ define <4 x i64> @stack_fold_punpckhqdq(<4 x i64> %a0, <4 x i64> %a1) {
   ;CHECK:       vpunpckhqdq {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <4 x i64> %a0, <4 x i64> %a1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
-  ret <4 x i64> %2
+  ; add forces execution domain
+  %3 = add <4 x i64> %2, <i64 1, i64 1, i64 1, i64 1>
+  ret <4 x i64> %3
 }
 
 define <16 x i16> @stack_fold_punpckhwd(<16 x i16> %a0, <16 x i16> %a1) {
@@ -1162,7 +1166,9 @@ define <8 x i32> @stack_fold_punpckldq(<8 x i32> %a0, <8 x i32> %a1) {
   ;CHECK:       vpunpckldq {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <8 x i32> %a0, <8 x i32> %a1, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
-  ret <8 x i32> %2
+  ; add forces execution domain
+  %3 = add <8 x i32> %2, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+  ret <8 x i32> %3
 }
 
 define <4 x i64> @stack_fold_punpcklqdq(<4 x i64> %a0, <4 x i64> %a1) {
@@ -1170,7 +1176,9 @@ define <4 x i64> @stack_fold_punpcklqdq(<4 x i64> %a0, <4 x i64> %a1) {
   ;CHECK:       vpunpcklqdq {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <4 x i64> %a0, <4 x i64> %a1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-  ret <4 x i64> %2
+  ; add forces execution domain
+  %3 = add <4 x i64> %2, <i64 1, i64 1, i64 1, i64 1>
+  ret <4 x i64> %3
 }
 
 define <16 x i16> @stack_fold_punpcklwd(<16 x i16> %a0, <16 x i16> %a1) {
diff --git a/llvm/test/CodeGen/X86/stack-folding-int-sse42.ll b/llvm/test/CodeGen/X86/stack-folding-int-sse42.ll
index 961b4a4b6b82..ac2bdfa8204d 100644
--- a/llvm/test/CodeGen/X86/stack-folding-int-sse42.ll
+++ b/llvm/test/CodeGen/X86/stack-folding-int-sse42.ll
@@ -1069,7 +1069,9 @@ define <4 x i32> @stack_fold_punpckhdq(<4 x i32> %a0, <4 x i32> %a1) {
   ;CHECK:       punpckhdq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <4 x i32> %a0, <4 x i32> %a1, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-  ret <4 x i32> %2
+  ; add forces execution domain
+  %3 = add <4 x i32> %2, <i32 1, i32 1, i32 1, i32 1>
+  ret <4 x i32> %3
 }
 
 define <2 x i64> @stack_fold_punpckhqdq(<2 x i64> %a0, <2 x i64> %a1) {
@@ -1077,7 +1079,9 @@ define <2 x i64> @stack_fold_punpckhqdq(<2 x i64> %a0, <2 x i64> %a1) {
   ;CHECK:       punpckhqdq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <2 x i64> %a0, <2 x i64> %a1, <2 x i32> <i32 1, i32 3>
-  ret <2 x i64> %2
+  ; add forces execution domain
+  %3 = add <2 x i64> %2, <i64 1, i64 1>
+  ret <2 x i64> %3
 }
 
 define <8 x i16> @stack_fold_punpckhwd(<8 x i16> %a0, <8 x i16> %a1) {
@@ -1101,7 +1105,9 @@ define <4 x i32> @stack_fold_punpckldq(<4 x i32> %a0, <4 x i32> %a1) {
   ;CHECK:       punpckldq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <4 x i32> %a0, <4 x i32> %a1, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
-  ret <4 x i32> %2
+  ; add forces execution domain
+  %3 = add <4 x i32> %2, <i32 1, i32 1, i32 1, i32 1>
+  ret <4 x i32> %3
 }
 
 define <2 x i64> @stack_fold_punpcklqdq(<2 x i64> %a0, <2 x i64> %a1) {
@@ -1109,7 +1115,9 @@ define <2 x i64> @stack_fold_punpcklqdq(<2 x i64> %a0, <2 x i64> %a1) {
   ;CHECK:       punpcklqdq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
   %2 = shufflevector <2 x i64> %a0, <2 x i64> %a1, <2 x i32> <i32 0, i32 2>
-  ret <2 x i64> %2
+  ; add forces execution domain
+  %3 = add <2 x i64> %2, <i64 1, i64 1>
+  ret <2 x i64> %3
 }
 
 define <8 x i16> @stack_fold_punpcklwd(<8 x i16> %a0, <8 x i16> %a1) {