Merging r261039:

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

diff --git a/test/CodeGen/X86/avx.ll b/test/CodeGen/X86/avx.ll
index cba6d98f5a84207afd527b23f554eb2c62e453a8..341dd867e4ff47d18343180a9423201aa293cedf 100644 (file)
--- a/test/CodeGen/X86/avx.ll
+++ b/test/CodeGen/X86/avx.ll
@@ -32,9 +32,9 @@ define <4 x float> @insertps_from_vector_load(<4 x float> %a, <4 x float>* nocap
 ; On X32, account for the argument's move to registers
 ; X32: movl    4(%esp), %eax
 ; CHECK-NOT: mov
-; CHECK: insertps    $48
+; CHECK: vinsertps    $48, (%{{...}}), {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
 ; CHECK-NEXT: ret
-  %1 = load <4 x float>* %pb, align 16
+  %1 = load <4 x float>, <4 x float>* %pb, align 16
   %2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 48)
   ret <4 x float> %2
 }
@@ -46,9 +46,9 @@ define <4 x float> @insertps_from_vector_load_offset(<4 x float> %a, <4 x float>
 ; X32: movl    4(%esp), %eax
 ; CHECK-NOT: mov
 ;; Try to match a bit more of the instr, since we need the load's offset.
-; CHECK: insertps    $96, 4(%{{...}}), %
+; CHECK: vinsertps    $32, 4(%{{...}}), {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
 ; CHECK-NEXT: ret
-  %1 = load <4 x float>* %pb, align 16
+  %1 = load <4 x float>, <4 x float>* %pb, align 16
   %2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 96)
   ret <4 x float> %2
 }
@@ -60,10 +60,10 @@ define <4 x float> @insertps_from_vector_load_offset_2(<4 x float> %a, <4 x floa
 ; X32: movl    8(%esp), %ecx
 ; CHECK-NOT: mov
 ;; Try to match a bit more of the instr, since we need the load's offset.
-; CHECK: vinsertps    $-64, 12(%{{...}},%{{...}}), %
+; CHECK: vinsertps    $0, 12(%{{...}},%{{...}}), {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
 ; CHECK-NEXT: ret
-  %1 = getelementptr inbounds <4 x float>* %pb, i64 %index
-  %2 = load <4 x float>* %1, align 16
+  %1 = getelementptr inbounds <4 x float>, <4 x float>* %pb, i64 %index
+  %2 = load <4 x float>, <4 x float>* %1, align 16
   %3 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %2, i32 192)
   ret <4 x float> %3
 }
@@ -76,8 +76,8 @@ define <4 x float> @insertps_from_broadcast_loadf32(<4 x float> %a, float* nocap
 ; CHECK-NOT: mov
 ; CHECK: insertps    $48
 ; CHECK-NEXT: ret
-  %1 = getelementptr inbounds float* %fb, i64 %index
-  %2 = load float* %1, align 4
+  %1 = getelementptr inbounds float, float* %fb, i64 %index
+  %2 = load float, float* %1, align 4
   %3 = insertelement <4 x float> undef, float %2, i32 0
   %4 = insertelement <4 x float> %3, float %2, i32 1
   %5 = insertelement <4 x float> %4, float %2, i32 2
@@ -93,7 +93,7 @@ define <4 x float> @insertps_from_broadcast_loadv4f32(<4 x float> %a, <4 x float
 ; CHECK-NOT: mov
 ; CHECK: insertps    $48
 ; CHECK-NEXT: ret
-  %1 = load <4 x float>* %b, align 4
+  %1 = load <4 x float>, <4 x float>* %b, align 4
   %2 = extractelement <4 x float> %1, i32 0
   %3 = insertelement <4 x float> undef, float %2, i32 0
   %4 = insertelement <4 x float> %3, float %2, i32 1
@@ -119,8 +119,8 @@ define <4 x float> @insertps_from_broadcast_multiple_use(<4 x float> %a, <4 x fl
 ; CHECK: vaddps
 ; CHECK: vaddps
 ; CHECK-NEXT: ret
-  %1 = getelementptr inbounds float* %fb, i64 %index
-  %2 = load float* %1, align 4
+  %1 = getelementptr inbounds float, float* %fb, i64 %index
+  %2 = load float, float* %1, align 4
   %3 = insertelement <4 x float> undef, float %2, i32 0
   %4 = insertelement <4 x float> %3, float %2, i32 1
   %5 = insertelement <4 x float> %4, float %2, i32 2