[x86] fix test specifications and auto-generate checks

llvm-svn: 289492

diff --git a/llvm/test/CodeGen/X86/SwizzleShuff.ll b/llvm/test/CodeGen/X86/SwizzleShuff.ll
index e4c35c5..05dc607 100644 (file)
--- a/llvm/test/CodeGen/X86/SwizzleShuff.ll
+++ b/llvm/test/CodeGen/X86/SwizzleShuff.ll
@@ -1,11 +1,14 @@
-; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx -x86-experimental-vector-widening-legalization | FileCheck %s
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx -x86-experimental-vector-widening-legalization | FileCheck %s
 
 ; Check that we perform a scalar XOR on i32.
 
-; CHECK: pull_bitcast
-; CHECK: xorl
-; CHECK: ret
-define void @pull_bitcast (<4 x i8>* %pA, <4 x i8>* %pB) {
+define void @pull_bitcast(<4 x i8>* %pA, <4 x i8>* %pB) {
+; CHECK-LABEL: pull_bitcast:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    movl (%rsi), %eax
+; CHECK-NEXT:    xorl %eax, (%rdi)
+; CHECK-NEXT:    retq
   %A = load <4 x i8>, <4 x i8>* %pA
   %B = load <4 x i8>, <4 x i8>* %pB
   %C = xor <4 x i8> %A, %B
@@ -13,15 +16,16 @@ define void @pull_bitcast (<4 x i8>* %pA, <4 x i8>* %pB) {
   ret void
 }
 
-; CHECK: multi_use_swizzle
-; CHECK: pshufd
-; CHECK-NEXT: pshufd
-; CHECK-NEXT: pblendw
-; CHECK-NEXT: pshufd
-; CHECK-NEXT: pshufd
-; CHECK-NEXT: pxor
-; CHECK-NEXT: ret
-define <4 x i32> @multi_use_swizzle (<4 x i32>* %pA, <4 x i32>* %pB) {
+define <4 x i32> @multi_use_swizzle(<4 x i32>* %pA, <4 x i32>* %pB) {
+; CHECK-LABEL: multi_use_swizzle:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vpshufd {{.*#+}} xmm0 = mem[0,1,1,2]
+; CHECK-NEXT:    vpshufd {{.*#+}} xmm1 = mem[1,1,2,3]
+; CHECK-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
+; CHECK-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,3,2,2]
+; CHECK-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,1,0,2]
+; CHECK-NEXT:    vpxor %xmm0, %xmm1, %xmm0
+; CHECK-NEXT:    retq
   %A = load <4 x i32>, <4 x i32>* %pA
   %B = load <4 x i32>, <4 x i32>* %pB
   %S = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> <i32 1, i32 1, i32 5, i32 6>
@@ -31,10 +35,15 @@ define <4 x i32> @multi_use_swizzle (<4 x i32>* %pA, <4 x i32>* %pB) {
   ret <4 x i32> %R
 }
 
-; CHECK: pull_bitcast2
-; CHECK: xorl
-; CHECK: ret
-define <4 x i8> @pull_bitcast2 (<4 x i8>* %pA, <4 x i8>* %pB, <4 x i8>* %pC) {
+define <4 x i8> @pull_bitcast2(<4 x i8>* %pA, <4 x i8>* %pB, <4 x i8>* %pC) {
+; CHECK-LABEL: pull_bitcast2:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    movl (%rdi), %eax
+; CHECK-NEXT:    movl %eax, (%rdx)
+; CHECK-NEXT:    xorl (%rsi), %eax
+; CHECK-NEXT:    vmovd %eax, %xmm0
+; CHECK-NEXT:    movl %eax, (%rdi)
+; CHECK-NEXT:    retq
   %A = load <4 x i8>, <4 x i8>* %pA
   store <4 x i8> %A, <4 x i8>* %pC
   %B = load <4 x i8>, <4 x i8>* %pB
@@ -43,12 +52,11 @@ define <4 x i8> @pull_bitcast2 (<4 x i8>* %pA, <4 x i8>* %pB, <4 x i8>* %pC) {
   ret <4 x i8> %C
 }
 
-
-
-; CHECK: reverse_1
-; CHECK-NOT: pshufd
-; CHECK: ret
-define <4 x i32> @reverse_1 (<4 x i32>* %pA, <4 x i32>* %pB) {
+define <4 x i32> @reverse_1(<4 x i32>* %pA, <4 x i32>* %pB) {
+; CHECK-LABEL: reverse_1:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vmovaps (%rdi), %xmm0
+; CHECK-NEXT:    retq
   %A = load <4 x i32>, <4 x i32>* %pA
   %B = load <4 x i32>, <4 x i32>* %pB
   %S = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
@@ -56,14 +64,15 @@ define <4 x i32> @reverse_1 (<4 x i32>* %pA, <4 x i32>* %pB) {
   ret <4 x i32> %S1
 }
 
-
-; CHECK: no_reverse_shuff
-; CHECK: pshufd
-; CHECK: ret
-define <4 x i32> @no_reverse_shuff (<4 x i32>* %pA, <4 x i32>* %pB) {
+define <4 x i32> @no_reverse_shuff(<4 x i32>* %pA, <4 x i32>* %pB) {
+; CHECK-LABEL: no_reverse_shuff:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vpshufd {{.*#+}} xmm0 = mem[2,3,2,3]
+; CHECK-NEXT:    retq
   %A = load <4 x i32>, <4 x i32>* %pA
   %B = load <4 x i32>, <4 x i32>* %pB
   %S = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
   %S1 = shufflevector <4 x i32> %S, <4 x i32> undef, <4 x i32> <i32 3, i32 2, i32 3, i32 2>
   ret <4 x i32> %S1
 }
+