mirror of
https://github.com/capstone-engine/llvm-capstone.git
synced 2025-04-02 21:22:44 +00:00
d052de856d
As noted in the D44909 review, the transform from (fptosi+sitofp) to ftrunc
can produce -0.0 where the original code does not:
#include <stdio.h>
int main(int argc) {
float x;
x = -0.8 * argc;
printf("%f\n", (float)((int)x));
return 0;
}
$ clang -O0 -mavx fp.c ; ./a.out
0.000000
$ clang -O1 -mavx fp.c ; ./a.out
-0.000000
Ideally, we'd use IR/node flags to predicate the transform, but the IR parser
doesn't currently allow fast-math-flags on the cast instructions. So for now,
just use the function attribute that corresponds to clang's "-fno-signed-zeros"
option.
Differential Revision: https://reviews.llvm.org/D48085
llvm-svn: 335761
44 lines
1.2 KiB
LLVM
44 lines
1.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -O0 -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
|
|
|
|
; xscvdpsxds should NOT be emitted, since it saturates the result down to i64.
|
|
; We can't use friz here because it may return -0.0 where the original code doesn't.
|
|
|
|
define float @f_i128_f(float %v) {
|
|
; CHECK-LABEL: f_i128_f:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: mflr 0
|
|
; CHECK-NEXT: std 0, 16(1)
|
|
; CHECK-NEXT: stdu 1, -32(1)
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: .cfi_offset lr, 16
|
|
; CHECK-NEXT: bl __fixsfti
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: bl __floattisf
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: addi 1, 1, 32
|
|
; CHECK-NEXT: ld 0, 16(1)
|
|
; CHECK-NEXT: mtlr 0
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%a = fptosi float %v to i128
|
|
%b = sitofp i128 %a to float
|
|
ret float %b
|
|
}
|
|
|
|
; NSZ, so it's safe to friz.
|
|
|
|
define float @f_i128_fi_nsz(float %v) #0 {
|
|
; CHECK-LABEL: f_i128_fi_nsz:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: friz 1, 1
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%a = fptosi float %v to i128
|
|
%b = sitofp i128 %a to float
|
|
ret float %b
|
|
}
|
|
|
|
attributes #0 = { "no-signed-zeros-fp-math"="true" }
|
|
|