add X86 load folding tests for unary math ops

X86 load folding is fragile; eg, the tests here
don't work without AVX even though they should. This
is because we have a mix of tablegen patterns that have
been added over time, and we have a load folding table
used by the peephole optimizer that has to be kept in
sync with the ever-changing ISA and tablegen defs.

llvm-svn: 229870

diff --git a/llvm/test/CodeGen/X86/fold-load-unops.ll b/llvm/test/CodeGen/X86/fold-load-unops.ll
new file mode 100644 (file)
index 0000000..0b2e6c7
--- /dev/null
+++ b/llvm/test/CodeGen/X86/fold-load-unops.ll
@@ -0,0 +1,57 @@
+; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+avx < %s | FileCheck %s
+
+; Verify that we're folding the load into the math instruction.
+
+; FIXME: The folding should also happen without the avx attribute; 
+; ie, when generating SSE (non-VEX-prefixed) instructions.
+
+define float @rcpss(float* %a) {
+; CHECK-LABEL: rcpss:
+; CHECK:       vrcpss (%rdi), %xmm0, %xmm0
+
+    %ld = load float* %a
+    %ins = insertelement <4 x float> undef, float %ld, i32 0
+    %res = tail call <4 x float> @llvm.x86.sse.rcp.ss(<4 x float> %ins)
+    %ext = extractelement <4 x float> %res, i32 0
+    ret float %ext
+}
+
+define float @rsqrtss(float* %a) {
+; CHECK-LABEL: rsqrtss:
+; CHECK:       vrsqrtss (%rdi), %xmm0, %xmm0
+
+    %ld = load float* %a
+    %ins = insertelement <4 x float> undef, float %ld, i32 0
+    %res = tail call <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float> %ins)
+    %ext = extractelement <4 x float> %res, i32 0
+    ret float %ext
+}
+
+define float @sqrtss(float* %a) {
+; CHECK-LABEL: sqrtss:
+; CHECK:       vsqrtss (%rdi), %xmm0, %xmm0
+
+    %ld = load float* %a
+    %ins = insertelement <4 x float> undef, float %ld, i32 0
+    %res = tail call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %ins)
+    %ext = extractelement <4 x float> %res, i32 0
+    ret float %ext
+}
+
+define double @sqrtsd(double* %a) {
+; CHECK-LABEL: sqrtsd:
+; CHECK:       vsqrtsd (%rdi), %xmm0, %xmm0
+
+    %ld = load double* %a
+    %ins = insertelement <2 x double> undef, double %ld, i32 0
+    %res = tail call <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double> %ins)
+    %ext = extractelement <2 x double> %res, i32 0
+    ret double %ext
+}
+
+
+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
+declare <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double>) nounwind readnone
+