fixed to test only the feature, not the feature and a CPU

[oota-llvm.git] / test / CodeGen / X86 / fold-vex.ll

diff --git a/test/CodeGen/X86/fold-vex.ll b/test/CodeGen/X86/fold-vex.ll
index 60e500b419ed651d91feb25c735ff6070a61c58d..006db6effdf631904a7b2953fed78cc8b9baaa8c 100644 (file)
--- a/test/CodeGen/X86/fold-vex.ll
+++ b/test/CodeGen/X86/fold-vex.ll
@@ -1,16 +1,31 @@
-; RUN: llc < %s -mcpu=corei7-avx -march=x86-64 | FileCheck %s
+; Use CPU parameters to ensure that a CPU-specific attribute is not overriding the AVX definition.
 
-;CHECK: @test
-; No need to load from memory. The operand will be loaded as part of th AND instr.
-;CHECK-NOT: vmovaps
-;CHECK: vandps
-;CHECK: ret
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown                  -mattr=+avx | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=corei7-avx             | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=btver2                 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown                  -mattr=-avx | FileCheck %s --check-prefix=SSE
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=corei7-avx -mattr=-avx | FileCheck %s --check-prefix=SSE
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=btver2     -mattr=-avx | FileCheck %s --check-prefix=SSE
 
-define void @test1(<8 x i32>* %p0, <8 x i32> %in1) nounwind {
-entry:
-  %in0 = load <8 x i32>* %p0, align 2
-  %a = and <8 x i32> %in0, %in1
-  store <8 x i32> %a, <8 x i32>* undef
-  ret void
+; No need to load unaligned operand from memory using an explicit instruction with AVX.
+; The operand should be folded into the AND instr.
+
+; With SSE, folding memory operands into math/logic ops requires 16-byte alignment
+; unless specially configured on some CPUs such as AMD Family 10H.
+
+define <4 x i32> @test1(<4 x i32>* %p0, <4 x i32> %in1) nounwind {
+  %in0 = load <4 x i32>, <4 x i32>* %p0, align 2
+  %a = and <4 x i32> %in0, %in1
+  ret <4 x i32> %a
+
+; CHECK-LABEL: @test1
+; CHECK-NOT:   vmovups
+; CHECK:       vandps (%rdi), %xmm0, %xmm0
+; CHECK-NEXT:  ret
+
+; SSE-LABEL: @test1
+; SSE:       movups (%rdi), %xmm1
+; SSE-NEXT:  andps %xmm1, %xmm0
+; SSE-NEXT:  ret
 }