RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-29 22:30:33 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[ConstantFolding] Fix wrong folding of intrinsic 'convert.from.fp16'.

Browse Source 
Function 'ConstantFoldScalarCall' (in ConstantFolding.cpp) works under the
wrong assumption that a call to 'convert.from.fp16' returns a value of
type 'float'.
However, intrinsic 'convert.from.fp16' can be overloaded; for example, we
can call 'convert.from.fp16.f64' to convert from half to double; etc.

Before this patch, the following example would have triggered an assertion
failure in opt (with -constprop):

```
define double @foo() {
entry:
  %0 = call double @llvm.convert.from.fp16.f64(i16 0)
  ret double %0
}
```

This patch fixes the problem in ConstantFolding.cpp. When folding a call to
convert.from.fp16, we perform a different kind of conversion based on the call
return type.

Added test 'Transform/ConstProp/convert-from-fp16.ll'.

Differential Revision: http://reviews.llvm.org/D9771

llvm-svn: 237377
This commit is contained in:
Andrea Di Biagio 2015-05-14 18:01:48 +00:00
parent 2b48b0ebda
commit 67c82df819
2 changed files with 99 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/Analysis/ConstantFolding.cpp
View File

@ -1543,8 +1543,8 @@ static Constant *ConstantFoldScalarCall(StringRef Name, unsigned IntrinsicID,
APFloat Val(APFloat::IEEEhalf, Op->getValue());
bool lost = false;
APFloat::opStatus status =
Val.convert(APFloat::IEEEsingle, APFloat::rmNearestTiesToEven, &lost);
APFloat::opStatus status = Val.convert(
Ty->getFltSemantics(), APFloat::rmNearestTiesToEven, &lost);
// Conversion is always precise.
(void)status;

97
test/Transforms/ConstProp/convert-from-fp16.ll Normal file
View File

@ -0,0 +1,97 @@
; RUN: opt -constprop -S < %s | FileCheck %s
; Verify that we don't crash with an assertion failure when constant folding
; a call to intrinsic 'convert.from.fp16' if the return type is not 'float'.
define float @fold_from_fp16_to_fp32() {
; CHECK-LABEL: @fold_from_fp16_to_fp32
; CHECK: ret float 0.000000e+00
entry:
%0 = call float @llvm.convert.from.fp16.f32(i16 0)
ret float %0
}
define double @fold_from_fp16_to_fp64() {
; CHECK-LABEL: @fold_from_fp16_to_fp64
; CHECK: ret double 0.000000e+00
entry:
%0 = call double @llvm.convert.from.fp16.f64(i16 0)
ret double %0
}
define x86_fp80 @fold_from_fp16_to_fp80() {
; CHECK-LABEL: @fold_from_fp16_to_fp80
; CHECK: ret x86_fp80 0xK00000000000000000000
entry:
%0 = call x86_fp80 @llvm.convert.from.fp16.f80(i16 0)
ret x86_fp80 %0
}
define fp128 @fold_from_fp16_to_fp128() {
; CHECK-LABEL: @fold_from_fp16_to_fp128
; CHECK: ret fp128 0xL00000000000000000000000000000000
entry:
%0 = call fp128 @llvm.convert.from.fp16.f128(i16 0)
ret fp128 %0
}
define ppc_fp128 @fold_from_fp16_to_ppcfp128() {
; CHECK-LABEL: @fold_from_fp16_to_ppcfp128
; CHECK: ret ppc_fp128 0xM00000000000000000000000000000000
entry:
%0 = call ppc_fp128 @llvm.convert.from.fp16.ppcf128(i16 0)
ret ppc_fp128 %0
}
define float @fold_from_fp16_to_fp32_b() {
; CHECK-LABEL: @fold_from_fp16_to_fp32_b
; CHECK: ret float 4.000000e+00
entry:
%0 = call i16 @llvm.convert.to.fp16.f64(double 4.0)
%1 = call float @llvm.convert.from.fp16.f32(i16 %0)
ret float %1
}
define double @fold_from_fp16_to_fp64_b() {
; CHECK-LABEL: @fold_from_fp16_to_fp64_b
; CHECK: ret double 4.000000e+00
entry:
%0 = call i16 @llvm.convert.to.fp16.f64(double 4.0)
%1 = call double @llvm.convert.from.fp16.f64(i16 %0)
ret double %1
}
define x86_fp80 @fold_from_fp16_to_fp80_b() {
; CHECK-LABEL: @fold_from_fp16_to_fp80_b
; CHECK: ret x86_fp80 0xK40018000000000000000
entry:
%0 = call i16 @llvm.convert.to.fp16.f64(double 4.0)
%1 = call x86_fp80 @llvm.convert.from.fp16.f80(i16 %0)
ret x86_fp80 %1
}
define fp128 @fold_from_fp16_to_fp128_b() {
; CHECK-LABEL: @fold_from_fp16_to_fp128_b
; CHECK: ret fp128 0xL00000000000000004001000000000000
entry:
%0 = call i16 @llvm.convert.to.fp16.f64(double 4.0)
%1 = call fp128 @llvm.convert.from.fp16.f128(i16 %0)
ret fp128 %1
}
define ppc_fp128 @fold_from_fp16_to_ppcfp128_b() {
; CHECK-LABEL: @fold_from_fp16_to_ppcfp128_b
; CHECK: ret ppc_fp128 0xM40100000000000000000000000000000
entry:
%0 = call i16 @llvm.convert.to.fp16.f64(double 4.0)
%1 = call ppc_fp128 @llvm.convert.from.fp16.ppcf128(i16 %0)
ret ppc_fp128 %1
}
declare i16 @llvm.convert.to.fp16.f64(double)
declare float @llvm.convert.from.fp16.f32(i16)
declare double @llvm.convert.from.fp16.f64(i16)
declare x86_fp80 @llvm.convert.from.fp16.f80(i16)
declare fp128 @llvm.convert.from.fp16.f128(i16)
declare ppc_fp128 @llvm.convert.from.fp16.ppcf128(i16)