Files
clang-p2996/llvm/test/CodeGen/PowerPC/vec_int_to_double_shuffle.ll
Kai Luo 666ee849f0 [PowerPC] Fix shift amount of xxsldwi when performing vector int_to_double
POC
```
// main.c
#include <stdio.h>
#include <altivec.h>
extern vector double foo(vector int s);
int main() {
  vector int s = {0, 1, 0, 4};
  vector double vd;
  vd = foo(s);
  printf("%lf %lf\n", vd[0], vd[1]);
  return 0;
}
// poc.c
vector double foo(vector int s) {
  int x1 = s[1];
  int x3 = s[3];
  double d1 = x1;
  double d3 = x3;
  vector double x = { d1, d3 };
  return x;
}
```
Compiled with `poc.c main.c -mcpu=pwr8 -O3` on BE machine.
Current clang gives
```
4.000000 1.000000
```
while xlc gives
```
1.000000 4.000000
```
Xlc's output should be correct.

Reviewed By: shchenz, #powerpc

Differential Revision: https://reviews.llvm.org/D107428
2021-08-06 06:01:29 +00:00

40 lines
1.3 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mcpu=pwr8 -mtriple=powerpc64le-unknown-unknown \
; RUN: -verify-machineinstrs < %s | FileCheck --check-prefix=CHECK-LE %s
; RUN: llc -mcpu=pwr8 -mtriple=powerpc64-unknown-unknown \
; RUN: -verify-machineinstrs < %s | FileCheck --check-prefix=CHECK-BE %s
define <2 x double> @foo(<4 x i32> %s) {
; CHECK-LE-LABEL: foo:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xvcvsxwdp 34, 34
; CHECK-LE-NEXT: blr
;
; CHECK-BE-LABEL: foo:
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: xxsldwi 0, 34, 34, 1
; CHECK-BE-NEXT: xvcvsxwdp 34, 0
; CHECK-BE-NEXT: blr
entry:
%0 = shufflevector <4 x i32> %s, <4 x i32> undef, <2 x i32> <i32 1, i32 3>
%1 = sitofp <2 x i32> %0 to <2 x double>
ret <2 x double> %1
}
define <2 x double> @bar(<4 x i32> %s) {
; CHECK-LE-LABEL: bar:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: xvcvuxwdp 34, 34
; CHECK-LE-NEXT: blr
;
; CHECK-BE-LABEL: bar:
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: xxsldwi 0, 34, 34, 1
; CHECK-BE-NEXT: xvcvuxwdp 34, 0
; CHECK-BE-NEXT: blr
entry:
%0 = shufflevector <4 x i32> %s, <4 x i32> undef, <2 x i32> <i32 1, i32 3>
%1 = uitofp <2 x i32> %0 to <2 x double>
ret <2 x double> %1
}