mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 05:01:59 +01:00
070e2e6ea8
Summary:
This isn't an important optimization at all... We're already doing:
pow(x, 0.0) -> 1.0
My patch merely teaches instcombine that -0.0 does the same.
However, doing this fixes an AMAZING bug! Compile this program:
extern "C" double pow(double, double);
double boom(double base) {
return pow(base, -0.0);
}
With:
clang++ ~/Desktop/fast-math.cpp -ffast-math -O2 -S
And clang will crash with a signal. Wow, fast math is so fast it ICEs the
compiler! Arguably, the generated math is infinitely fast.
What's actually happening is that we recurse infinitely in getPow. In debug we
hit its assertion:
assert(Exp != 0 && "Incorrect exponent 0 not handled");
We avoid this entire mess if we instead recognize that an exponent of positive
and negative zero yield 1.0.
A separate commit, r371221, fixed the same problem. This only contains the added
tests.
<rdar://problem/54598300>
Reviewers: scanon
Subscribers: hiraditya, jkorous, dexonsmith, ributzka, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D67248
llvm-svn: 371224
61 lines
2.2 KiB
LLVM
61 lines
2.2 KiB
LLVM
; RUN: opt < %s -instcombine -S | FileCheck %s
|
|
|
|
; CHECK-LABEL: @zero(
|
|
; CHECK-NEXT: ret double 1.000000e+00
|
|
define double @zero(double %value) {
|
|
%res = call double @llvm.pow.f64(double %value, double 0.000000e+00)
|
|
ret double %res
|
|
}
|
|
|
|
; CHECK-LABEL: @minus_zero(
|
|
; CHECK-NEXT: ret double 1.000000e+00
|
|
define double @minus_zero(double %value) {
|
|
%res = call double @llvm.pow.f64(double %value, double -0.000000e+00)
|
|
ret double %res
|
|
}
|
|
|
|
; CHECK-LABEL: @fast_zero(
|
|
; CHECK-NEXT: ret double 1.000000e+00
|
|
define double @fast_zero(double %value) {
|
|
%res = call fast double @llvm.pow.f64(double %value, double 0.000000e+00)
|
|
ret double %res
|
|
}
|
|
|
|
; CHECK-LABEL: @fast_minus_zero(
|
|
; CHECK-NEXT: ret double 1.000000e+00
|
|
define double @fast_minus_zero(double %value) {
|
|
%res = call fast double @llvm.pow.f64(double %value, double -0.000000e+00)
|
|
ret double %res
|
|
}
|
|
|
|
; CHECK-LABEL: @vec_zero(
|
|
; CHECK-NEXT: ret <2 x double> <double 1.000000e+00, double 1.000000e+00>
|
|
define <2 x double> @vec_zero(<2 x double> %value) {
|
|
%res = call <2 x double> @llvm.pow.v2f64(<2 x double> %value, <2 x double> <double 0.000000e+00, double 0.000000e+00>)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
; CHECK-LABEL: @vec_minus_zero(
|
|
; CHECK-NEXT: ret <2 x double> <double 1.000000e+00, double 1.000000e+00>
|
|
define <2 x double> @vec_minus_zero(<2 x double> %value) {
|
|
%res = call <2 x double> @llvm.pow.v2f64(<2 x double> %value, <2 x double> <double -0.000000e+00, double -0.000000e+00>)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
; CHECK-LABEL: @vec_fast_zero(
|
|
; CHECK-NEXT: ret <2 x double> <double 1.000000e+00, double 1.000000e+00>
|
|
define <2 x double> @vec_fast_zero(<2 x double> %value) {
|
|
%res = call fast <2 x double> @llvm.pow.v2f64(<2 x double> %value, <2 x double> <double 0.000000e+00, double 0.000000e+00>)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
; CHECK-LABEL: @vec_fast_minus_zero(
|
|
; CHECK-NEXT: ret <2 x double> <double 1.000000e+00, double 1.000000e+00>
|
|
define <2 x double> @vec_fast_minus_zero(<2 x double> %value) {
|
|
%res = call fast <2 x double> @llvm.pow.v2f64(<2 x double> %value, <2 x double> <double -0.000000e+00, double -0.000000e+00>)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
declare double @llvm.pow.f64(double, double)
|
|
declare <2 x double> @llvm.pow.v2f64(<2 x double>, <2 x double>)
|