Use Twin instead of std::to_string.

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

diff --git a/test/CodeGen/X86/avx-load-store.ll b/test/CodeGen/X86/avx-load-store.ll
index 0afaff830df09f1f33a6310dbfdfcb540dd63cc4..d7eceb7cce664e2b607e1a97b28a09319bcd87cb 100644 (file)
--- a/test/CodeGen/X86/avx-load-store.ll
+++ b/test/CodeGen/X86/avx-load-store.ll
@@ -10,10 +10,10 @@
 define void @test_256_load(double* nocapture %d, float* nocapture %f, <4 x i64>* nocapture %i) nounwind uwtable ssp {
 entry:
   %0 = bitcast double* %d to <4 x double>*
-  %tmp1.i = load <4 x double>* %0, align 32
+  %tmp1.i = load <4 x double>, <4 x double>* %0, align 32
   %1 = bitcast float* %f to <8 x float>*
-  %tmp1.i17 = load <8 x float>* %1, align 32
-  %tmp1.i16 = load <4 x i64>* %i, align 32
+  %tmp1.i17 = load <8 x float>, <8 x float>* %1, align 32
+  %tmp1.i16 = load <4 x i64>, <4 x i64>* %i, align 32
   tail call void @dummy(<4 x double> %tmp1.i, <8 x float> %tmp1.i17, <4 x i64> %tmp1.i16) nounwind
   store <4 x double> %tmp1.i, <4 x double>* %0, align 32
   store <8 x float> %tmp1.i17, <8 x float>* %1, align 32
@@ -29,9 +29,8 @@ declare void @dummy(<4 x double>, <8 x float>, <4 x i64>)
 
 ; CHECK: mov00
 define <8 x float> @mov00(<8 x float> %v, float * %ptr) nounwind {
-  %val = load float* %ptr
-; CHECK: vinsertps
-; CHECK: vinsertf128
+  %val = load float, float* %ptr
+; CHECK: vmovss (%
   %i0 = insertelement <8 x float> zeroinitializer, float %val, i32 0
   ret <8 x float> %i0
 ; CHECK: ret
@@ -39,9 +38,8 @@ define <8 x float> @mov00(<8 x float> %v, float * %ptr) nounwind {
 
 ; CHECK: mov01
 define <4 x double> @mov01(<4 x double> %v, double * %ptr) nounwind {
-  %val = load double* %ptr
-; CHECK: vmovlpd
-; CHECK: vinsertf128
+  %val = load double, double* %ptr
+; CHECK: vmovsd (%
   %i0 = insertelement <4 x double> zeroinitializer, double %val, i32 0
   ret <4 x double> %i0
 ; CHECK: ret
@@ -81,7 +79,7 @@ define void @storev32i8_01(<32 x i8> %a) nounwind {
 ; CHECK: _double_save
 ; CHECK-NOT: vinsertf128 $1
 ; CHECK-NOT: vinsertf128 $0
-; CHECK: vmovups %xmm
+; CHECK: vmovaps %xmm
 ; CHECK: vmovaps %xmm
 define void @double_save(<4 x i32> %A, <4 x i32> %B, <8 x i32>* %P) nounwind ssp {
 entry:
@@ -90,7 +88,7 @@ entry:
   ret void
 }
 
-declare void @llvm.x86.avx.maskstore.ps.256(i8*, <8 x float>, <8 x float>) nounwind
+declare void @llvm.x86.avx.maskstore.ps.256(i8*, <8 x i32>, <8 x float>) nounwind
 
 ; CHECK_O0: _f_f
 ; CHECK-O0: vmovss LCPI
@@ -107,7 +105,7 @@ cif_mask_mixed:                                   ; preds = %allocas
   br i1 undef, label %cif_mixed_test_all, label %cif_mixed_test_any_check
 
 cif_mixed_test_all:                               ; preds = %cif_mask_mixed
-  call void @llvm.x86.avx.maskstore.ps.256(i8* undef, <8 x float> <float 0xFFFFFFFFE0000000, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00>, <8 x float> undef) nounwind
+  call void @llvm.x86.avx.maskstore.ps.256(i8* undef, <8 x i32> <i32 -1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>, <8 x float> undef) nounwind
   unreachable
 
 cif_mixed_test_any_check:                         ; preds = %cif_mask_mixed
@@ -122,8 +120,30 @@ cif_mixed_test_any_check:                         ; preds = %cif_mask_mixed
 ; CHECK: vmovups
 ; CHECK: vmovups
 define void @add8i32(<8 x i32>* %ret, <8 x i32>* %bp) nounwind {
-  %b = load <8 x i32>* %bp, align 1
+  %b = load <8 x i32>, <8 x i32>* %bp, align 1
   %x = add <8 x i32> zeroinitializer, %b
   store <8 x i32> %x, <8 x i32>* %ret, align 1
   ret void
 }
+
+; CHECK: add4i64a64
+; CHECK: vmovaps ({{.*}}), %ymm{{.*}}
+; CHECK: vmovaps %ymm{{.*}}, ({{.*}})
+define void @add4i64a64(<4 x i64>* %ret, <4 x i64>* %bp) nounwind {
+  %b = load <4 x i64>, <4 x i64>* %bp, align 64
+  %x = add <4 x i64> zeroinitializer, %b
+  store <4 x i64> %x, <4 x i64>* %ret, align 64
+  ret void
+}
+
+; CHECK: add4i64a16
+; CHECK: vmovaps {{.*}}({{.*}}), %xmm{{.*}}
+; CHECK: vmovaps {{.*}}({{.*}}), %xmm{{.*}}
+; CHECK: vmovaps %xmm{{.*}}, {{.*}}({{.*}})
+; CHECK: vmovaps %xmm{{.*}}, {{.*}}({{.*}})
+define void @add4i64a16(<4 x i64>* %ret, <4 x i64>* %bp) nounwind {
+  %b = load <4 x i64>, <4 x i64>* %bp, align 16
+  %x = add <4 x i64> zeroinitializer, %b
+  store <4 x i64> %x, <4 x i64>* %ret, align 16
+  ret void
+}