[llvm-bugs] [Bug 37403] New: Missed optimization: fmax(a+n, b+n)

[via llvm-bugs]

https://bugs.llvm.org/show_bug.cgi?id=37403

            Bug ID: 37403
           Summary: Missed optimization: fmax(a+n, b+n)
           Product: libraries
           Version: 6.0
          Hardware: PC
                OS: Linux
            Status: NEW
          Severity: enhancement
          Priority: P
         Component: Scalar Optimizations
          Assignee: unassignedbugs at nondot.org
          Reporter: m-takahiro at jp.fujitsu.com
                CC: llvm-bugs at lists.llvm.org

I compiled the following code by clang (tags/RELEASE_600/final 327104).
Option is '-Ofast -march=native'.

#include <math.h>
double foo(double a, double b, const double n) {
  return fmax(a + n, b + n);
}

Generated IRs is as follows.

; Function Attrs: nounwind readnone uwtable
define double @foo(double, double, double) local_unnamed_addr #0 {
  %4 = fadd fast double %2, %0
  %5 = fadd fast double %2, %1
  %6 = tail call fast double @llvm.maxnum.f64(double %4, double %5)
  ret double %6
}

I think the above IRs can be simplified like the following IR when
'-ffast-math' is enabled.

; Function Attrs: nounwind readnone uwtable
define double @foo1(double, double, double) local_unnamed_addr #0 {
  %3 = tail call fast double @llvm.maxnum.f64(double %0, double %1)
  %4 = fadd fast double %2, %3
  ret double %4
}

The same occurs about fmin.

#include <math.h>
double foo(double a, double b, const double n) {
  return fmin(a + n, b + n);
}

 -->

; Function Attrs: nounwind readnone uwtable
define double @foo(double, double, double) local_unnamed_addr #0 {
  %4 = fadd fast double %2, %0
  %5 = fadd fast double %2, %1
  %6 = tail call fast double @llvm.minnum.f64(double %4, double %5)
  ret double %6
}

-- 
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20180510/fb823c63/attachment-0001.html>