b7d7c448df
The conditions for which Clang emits the `unsafe-fp-math` function
attribute has been modified as part of
`84a9ec2ff1ee97fd7e8ed988f5e7b197aab84a7`.
In the backend code generators `"unsafe-fp-math"="true"` enable floating
point contraction for the whole function.
The intent of the change in `84a9ec2ff1ee97fd7e8ed988f5e7b197aab84a7`
was to prevent backend code generators performing contractions when that
is not expected.
However the change is inaccurate and incomplete because it allows
`unsafe-fp-math` to be set also when only in-statement contraction is
allowed.
Consider the following example
```
float foo(float a, float b, float c) {
float tmp = a * b;
return tmp + c;
}
```
and compile it with the command line
```
clang -fno-math-errno -funsafe-math-optimizations -ffp-contract=on \
-O2 -mavx512f -S -o -
```
The resulting assembly has a `vfmadd213ss` instruction which corresponds
to a fused multiply-add. From the user perspective there shouldn't be
any contraction because the multiplication and the addition are not in
the same statement.
The optimized IR is:
```
define float @test(float noundef %a, float noundef %b, float noundef %c) #0 {
%mul = fmul reassoc nsz arcp afn float %b, %a
%add = fadd reassoc nsz arcp afn float %mul, %c
ret float %add
}
attributes #0 = {
[...]
"no-signed-zeros-fp-math"="true"
"no-trapping-math"="true"
[...]
"unsafe-fp-math"="true"
}
```
The `"unsafe-fp-math"="true"` function attribute allows the backend code
generator to perform `(fadd (fmul a, b), c) -> (fmadd a, b, c)`.
In the current IR representation there is no way to determine the
statement boundaries from the original source code.
Because of this for in-statement only contraction the generated IR
doesn't have instructions with the `contract` fast-math flag and
`llvm.fmuladd` is being used to represent contractions opportunities
that occur within a single statement.
Therefore `"unsafe-fp-math"="true"` can only be emitted when contraction
across statements is allowed.
Moreover the change in `84a9ec2ff1ee97fd7e8ed988f5e7b197aab84a7` doesn't
take into account that the floating point math function attributes can
be refined during IR code generation of a function to handle the cases
where the floating point math options are modified within a compound
statement via pragmas (see `CGFPOptionsRAII`).
For consistency `unsafe-fp-math` needs to be disabled if the contraction
mode for any scope/operation is not `fast`.
Similarly for consistency reason the initialization of `UnsafeFPMath` of
in `TargetOptions` for the backend code generation should take into
account the contraction mode as well.
Reviewed By: zahiraam
Differential Revision: https://reviews.llvm.org/D136786
59 lines
2.3 KiB
C++
59 lines
2.3 KiB
C++
// RUN: %clang_cc1 -triple x86_64-linux-gnu -ffast-math -ffp-contract=fast -emit-llvm -o - %s | FileCheck %s
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -ffast-math -ffp-contract=fast-honor-pragmas -emit-llvm -o - %s | FileCheck %s
|
|
|
|
float test_default(float a, float b, float c) {
|
|
float tmp = a;
|
|
tmp += b;
|
|
tmp += c;
|
|
return tmp;
|
|
}
|
|
|
|
// CHECK: define{{.*}} float @_Z12test_defaultfff(float noundef %a, float noundef %b, float noundef %c) [[FAST_ATTRS:#[0-9]+]]
|
|
// CHECK: fadd fast float {{%.+}}, {{%.+}}
|
|
// CHECK: fadd fast float {{%.+}}, {{%.+}}
|
|
|
|
float test_precise_on_pragma(float a, float b, float c) {
|
|
float tmp = a;
|
|
{
|
|
#pragma float_control(precise, on)
|
|
tmp += b;
|
|
}
|
|
tmp += c;
|
|
return tmp;
|
|
}
|
|
|
|
// CHECK: define{{.*}} float @_Z22test_precise_on_pragmafff(float noundef %a, float noundef %b, float noundef %c) [[PRECISE_ATTRS:#[0-9]+]]
|
|
// CHECK: fadd float {{%.+}}, {{%.+}}
|
|
// CHECK: fadd fast float {{%.+}}, {{%.+}}
|
|
|
|
float test_reassociate_off_pragma(float a, float b, float c) {
|
|
float tmp = a;
|
|
{
|
|
#pragma clang fp reassociate(off)
|
|
tmp += b;
|
|
}
|
|
tmp += c;
|
|
return tmp;
|
|
}
|
|
|
|
// CHECK: define{{.*}} float @_Z27test_reassociate_off_pragmafff(float noundef %a, float noundef %b, float noundef %c) [[NO_UNSAFE_ATTRS:#[0-9]+]]
|
|
// CHECK: fadd nnan ninf nsz arcp contract afn float {{%.+}}, {{%.+}}
|
|
// CHECK: fadd fast float {{%.+}}, {{%.+}}
|
|
|
|
float test_contract_on_pragma(float a, float b, float c) {
|
|
float tmp = a * b;
|
|
{
|
|
#pragma clang fp contract(on)
|
|
tmp += c;
|
|
}
|
|
return tmp;
|
|
}
|
|
|
|
// CHECK: define{{.*}} float @_Z23test_contract_on_pragmafff(float noundef %a, float noundef %b, float noundef %c) [[NO_UNSAFE_ATTRS:#[0-9]+]]
|
|
// CHECK: fmul fast float {{%.+}}, {{%.+}}
|
|
// CHECK: fadd reassoc nnan ninf nsz arcp afn float {{%.+}}, {{%.+}}
|
|
|
|
// CHECK: attributes [[FAST_ATTRS]] = { {{.*}}"no-infs-fp-math"="true" {{.*}}"no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" {{.*}}"unsafe-fp-math"="true"{{.*}} }
|
|
// CHECK: attributes [[PRECISE_ATTRS]] = { {{.*}}"no-infs-fp-math"="false" {{.*}}"no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" {{.*}}"unsafe-fp-math"="false"{{.*}} }
|
|
// CHECK: attributes [[NO_UNSAFE_ATTRS]] = { {{.*}}"no-infs-fp-math"="true" {{.*}}"no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" {{.*}}"unsafe-fp-math"="false"{{.*}} }
|