diff options
author | Hal Finkel <hfinkel@anl.gov> | 2014-11-24 23:45:21 +0000 |
---|---|---|
committer | Hal Finkel <hfinkel@anl.gov> | 2014-11-24 23:45:21 +0000 |
commit | 360f213d039b519ce33c6b553f211e1cc826b976 (patch) | |
tree | 7c749c14b88fce502ee4c501037410d148536931 /llvm/test/CodeGen/PowerPC/fdiv-combine.ll | |
parent | 00d3b279cbdad40d27098754820b5951ff9328d8 (diff) | |
download | bcm5719-llvm-360f213d039b519ce33c6b553f211e1cc826b976.tar.gz bcm5719-llvm-360f213d039b519ce33c6b553f211e1cc826b976.zip |
[PowerPC] Implement combineRepeatedFPDivisors
This does not matter on newer cores (where we can use reciprocal estimates in
fast-math mode anyway), but for older cores this allows us to generate better
fast-math code where we have multiple FDIVs with a common divisor.
llvm-svn: 222710
Diffstat (limited to 'llvm/test/CodeGen/PowerPC/fdiv-combine.ll')
-rw-r--r-- | llvm/test/CodeGen/PowerPC/fdiv-combine.ll | 39 |
1 files changed, 39 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/PowerPC/fdiv-combine.ll b/llvm/test/CodeGen/PowerPC/fdiv-combine.ll new file mode 100644 index 00000000000..d3dc3fe913f --- /dev/null +++ b/llvm/test/CodeGen/PowerPC/fdiv-combine.ll @@ -0,0 +1,39 @@ +; RUN: llc -mcpu=ppc64 < %s | FileCheck %s +target datalayout = "E-m:e-i64:64-n32:64" +target triple = "powerpc64-unknown-linux-gnu" + +; Following test case checks: +; a / D; b / D; c / D; +; => +; recip = 1.0 / D; a * recip; b * recip; c * recip; + +define void @three_fdiv_double(double %D, double %a, double %b, double %c) #0 { +; CHECK-LABEL: three_fdiv_double: +; CHECK: fdiv +; CHECK-NEXT-NOT: fdiv +; CHECK: fmul +; CHECK: fmul +; CHECK: fmul + %div = fdiv double %a, %D + %div1 = fdiv double %b, %D + %div2 = fdiv double %c, %D + tail call void @foo_3d(double %div, double %div1, double %div2) + ret void +} + +define void @two_fdiv_double(double %D, double %a, double %b) #0 { +; CHECK-LABEL: two_fdiv_double: +; CHECK: fdiv +; CHECK: fdiv +; CHECK-NEXT-NOT: fmul + %div = fdiv double %a, %D + %div1 = fdiv double %b, %D + tail call void @foo_2d(double %div, double %div1) + ret void +} + +declare void @foo_3d(double, double, double) +declare void @foo_3_2xd(<2 x double>, <2 x double>, <2 x double>) +declare void @foo_2d(double, double) + +attributes #0 = { "unsafe-fp-math"="true" } |