transform fadd chains to increase parallelism

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

diff --git a/test/CodeGen/X86/fp-fast.ll b/test/CodeGen/X86/fp-fast.ll
index 479f60d91f1d56331dbfdaef8bfbbb70590b3c0d..eb2ebd9119a90c355be3b1cfdcee43bbb9846fde 100644 (file)
--- a/test/CodeGen/X86/fp-fast.ll
+++ b/test/CodeGen/X86/fp-fast.ll
@@ -113,3 +113,46 @@ define float @test11(float %a) {
   %t2 = fadd float %a, %t1
   ret float %t2
 }
+
+; Verify that the first two adds are independent; the destination registers
+; are used as source registers for the third add.
+
+define float @reassociate_adds1(float %a, float %b, float %c, float %d) {
+; CHECK-LABEL: reassociate_adds1:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    vaddss %xmm2, %xmm3, %xmm1
+; CHECK-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    retq
+  %add0 = fadd float %a, %b
+  %add1 = fadd float %add0, %c
+  %add2 = fadd float %add1, %d
+  ret float %add2
+}
+
+define float @reassociate_adds2(float %a, float %b, float %c, float %d) {
+; CHECK-LABEL: reassociate_adds2:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    vaddss %xmm2, %xmm3, %xmm1
+; CHECK-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    retq
+  %add0 = fadd float %a, %b
+  %add1 = fadd float %c, %add0
+  %add2 = fadd float %add1, %d
+  ret float %add2
+}
+
+define float @reassociate_adds3(float %a, float %b, float %c, float %d) {
+; CHECK-LABEL: reassociate_adds3:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    vaddss %xmm2, %xmm3, %xmm1
+; CHECK-NEXT:    vaddss %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    retq
+  %add0 = fadd float %a, %b
+  %add1 = fadd float %add0, %c
+  %add2 = fadd float %d, %add1
+  ret float %add2
+}
+