[X86] Add tests for full vector loads to fold-load-unops.ll.

We should be able to fold a full vector load into a scalar intrinsic. Since it's legal to narrow a load.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@318015 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/test/CodeGen/X86/fold-load-unops.ll b/test/CodeGen/X86/fold-load-unops.ll
index 0ae14b4..04689b0 100644 (file)
--- a/test/CodeGen/X86/fold-load-unops.ll
+++ b/test/CodeGen/X86/fold-load-unops.ll
@@ -98,6 +98,23 @@ define float @rcpss_size(float* %a) optsize {
     ret float %ext
 }
 
+define <4 x float> @rcpss_full_size(<4 x float>* %a) optsize {
+; SSE-LABEL: rcpss_full_size:
+; SSE:       # BB#0:
+; SSE-NEXT:    movaps (%rdi), %xmm0
+; SSE-NEXT:    rcpss %xmm0, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: rcpss_full_size:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovaps (%rdi), %xmm0
+; AVX-NEXT:    vrcpss %xmm0, %xmm0, %xmm0
+; AVX-NEXT:    retq
+    %ld = load <4 x float>, <4 x float>* %a
+    %res = tail call <4 x float> @llvm.x86.sse.rcp.ss(<4 x float> %ld)
+    ret <4 x float> %res
+}
+
 define float @rsqrtss_size(float* %a) optsize {
 ; SSE-LABEL: rsqrtss_size:
 ; SSE:       # BB#0:
@@ -115,6 +132,23 @@ define float @rsqrtss_size(float* %a) optsize {
     ret float %ext
 }
 
+define <4 x float> @rsqrtss_full_size(<4 x float>* %a) optsize {
+; SSE-LABEL: rsqrtss_full_size:
+; SSE:       # BB#0:
+; SSE-NEXT:    movaps (%rdi), %xmm0
+; SSE-NEXT:    rsqrtss %xmm0, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: rsqrtss_full_size:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovaps (%rdi), %xmm0
+; AVX-NEXT:    vrsqrtss %xmm0, %xmm0, %xmm0
+; AVX-NEXT:    retq
+    %ld = load <4 x float>, <4 x float>* %a
+    %res = tail call <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float> %ld)
+    ret <4 x float> %res
+}
+
 define float @sqrtss_size(float* %a) optsize{
 ; SSE-LABEL: sqrtss_size:
 ; SSE:       # BB#0:
@@ -132,6 +166,23 @@ define float @sqrtss_size(float* %a) optsize{
     ret float %ext
 }
 
+define <4 x float> @sqrtss_full_size(<4 x float>* %a) optsize{
+; SSE-LABEL: sqrtss_full_size:
+; SSE:       # BB#0:
+; SSE-NEXT:    movaps (%rdi), %xmm0
+; SSE-NEXT:    sqrtss %xmm0, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: sqrtss_full_size:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovaps (%rdi), %xmm0
+; AVX-NEXT:    vsqrtss %xmm0, %xmm0, %xmm0
+; AVX-NEXT:    retq
+    %ld = load <4 x float>, <4 x float>* %a
+    %res = tail call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %ld)
+    ret <4 x float> %res
+}
+
 define double @sqrtsd_size(double* %a) optsize {
 ; SSE-LABEL: sqrtsd_size:
 ; SSE:       # BB#0:
@@ -149,6 +200,23 @@ define double @sqrtsd_size(double* %a) optsize {
     ret double %ext
 }
 
+define <2 x double> @sqrtsd_full_size(<2 x double>* %a) optsize {
+; SSE-LABEL: sqrtsd_full_size:
+; SSE:       # BB#0:
+; SSE-NEXT:    movapd (%rdi), %xmm0
+; SSE-NEXT:    sqrtsd %xmm0, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: sqrtsd_full_size:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovapd (%rdi), %xmm0
+; AVX-NEXT:    vsqrtsd %xmm0, %xmm0, %xmm0
+; AVX-NEXT:    retq
+    %ld = load <2 x double>, <2 x double>* %a
+    %res = tail call <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double> %ld)
+    ret <2 x double> %res
+}
+
 declare <4 x float> @llvm.x86.sse.rcp.ss(<4 x float>) nounwind readnone
 declare <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float>) nounwind readnone
 declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>) nounwind readnone