summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen
diff options
context:
space:
mode:
authorSanjay Patel <spatel@rotateright.com>2015-07-09 17:28:37 +0000
committerSanjay Patel <spatel@rotateright.com>2015-07-09 17:28:37 +0000
commite2361d4a184a57fb3e96294918dfbdc9f7cb2d72 (patch)
treece7dfb6f590d5f1c8663dbc95633ad365de63f93 /llvm/test/CodeGen
parent578caf5da7f648e7e60f316779b6f2f7e1cb8e03 (diff)
downloadbcm5719-llvm-e2361d4a184a57fb3e96294918dfbdc9f7cb2d72.tar.gz
bcm5719-llvm-e2361d4a184a57fb3e96294918dfbdc9f7cb2d72.zip
fix an invisible bug when combining repeated FP divisors
This patch fixes bugs that were exposed by the addition of fast-math-flags in the DAG: r237046 ( http://reviews.llvm.org/rL237046 ): 1. When replacing a division node, it's not enough to RAUW. We should call CombineTo() to delete dead nodes and combine again. 2. Because we are changing the DAG, we can't return an empty SDValue after the transform. As the code comments say: Visitation implementation - Implement dag node combining for different node types. The semantics are as follows: Return Value: SDValue.getNode() == 0 - No change was made SDValue.getNode() == N - N was replaced, is dead and has been handled. otherwise - N should be replaced by the returned Operand. The new test case shows no difference with or without this patch, but it will crash if we re-apply r237046 or enable FMF via the current -enable-fmf-dag cl::opt. Differential Revision: http://reviews.llvm.org/D9893 llvm-svn: 241826
Diffstat (limited to 'llvm/test/CodeGen')
-rw-r--r--llvm/test/CodeGen/X86/fdiv-combine.ll17
1 files changed, 17 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/X86/fdiv-combine.ll b/llvm/test/CodeGen/X86/fdiv-combine.ll
index 8adfde7f3f3..34eac62e367 100644
--- a/llvm/test/CodeGen/X86/fdiv-combine.ll
+++ b/llvm/test/CodeGen/X86/fdiv-combine.ll
@@ -27,5 +27,22 @@ define float @div2_arcp(float %x, float %y, float %z) #0 {
ret float %div2
}
+; If the reciprocal is already calculated, we should not
+; generate an extra multiplication by 1.0.
+
+define double @div3_arcp(double %x, double %y, double %z) #0 {
+; CHECK-LABEL: div3_arcp:
+; CHECK: # BB#0:
+; CHECK-NEXT: movsd{{.*#+}} xmm2 = mem[0],zero
+; CHECK-NEXT: divsd %xmm1, %xmm2
+; CHECK-NEXT: mulsd %xmm2, %xmm0
+; CHECK-NEXT: addsd %xmm2, %xmm0
+; CHECK-NEXT: retq
+ %div1 = fdiv fast double 1.0, %y
+ %div2 = fdiv fast double %x, %y
+ %ret = fadd fast double %div2, %div1
+ ret double %ret
+}
+
; FIXME: If the backend understands 'arcp', then this attribute is unnecessary.
attributes #0 = { "unsafe-fp-math"="true" }
OpenPOWER on IntegriCloud