mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +01:00
e1e23467af
This patch changes how LLVM handles the accumulator/start value in the reduction, by never ignoring it regardless of the presence of fast-math flags on callsites. This change introduces the following new intrinsics to replace the existing ones: llvm.experimental.vector.reduce.fadd -> llvm.experimental.vector.reduce.v2.fadd llvm.experimental.vector.reduce.fmul -> llvm.experimental.vector.reduce.v2.fmul and adds functionality to auto-upgrade existing LLVM IR and bitcode. Reviewers: RKSimon, greened, dmgreen, nikic, simoll, aemerson Reviewed By: nikic Differential Revision: https://reviews.llvm.org/D60261 llvm-svn: 363035
35 lines
1.9 KiB
LLVM
35 lines
1.9 KiB
LLVM
; RUN: not opt -S < %s 2>&1 | FileCheck %s
|
|
|
|
; CHECK: Intrinsic has incorrect argument type!
|
|
; CHECK-NEXT: float (double, <2 x double>)* @llvm.experimental.vector.reduce.v2.fadd.f32.f64.v2f64
|
|
define float @fadd_invalid_scalar_res(double %acc, <2 x double> %in) {
|
|
%res = call float @llvm.experimental.vector.reduce.v2.fadd.f32.f64.v2f64(double %acc, <2 x double> %in)
|
|
ret float %res
|
|
}
|
|
|
|
; CHECK: Intrinsic has incorrect argument type!
|
|
; CHECK-NEXT: double (float, <2 x double>)* @llvm.experimental.vector.reduce.v2.fadd.f64.f32.v2f64
|
|
define double @fadd_invalid_scalar_start(float %acc, <2 x double> %in) {
|
|
%res = call double @llvm.experimental.vector.reduce.v2.fadd.f64.f32.v2f64(float %acc, <2 x double> %in)
|
|
ret double %res
|
|
}
|
|
|
|
; CHECK: Intrinsic has incorrect argument type!
|
|
; CHECK-NEXT: <2 x double> (double, <2 x double>)* @llvm.experimental.vector.reduce.v2.fadd.v2f64.f64.v2f64
|
|
define <2 x double> @fadd_invalid_vector_res(double %acc, <2 x double> %in) {
|
|
%res = call <2 x double> @llvm.experimental.vector.reduce.v2.fadd.v2f64.f64.v2f64(double %acc, <2 x double> %in)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
; CHECK: Intrinsic has incorrect argument type!
|
|
; CHECK-NEXT: double (<2 x double>, <2 x double>)* @llvm.experimental.vector.reduce.v2.fadd.f64.v2f64.v2f64
|
|
define double @fadd_invalid_vector_start(<2 x double> %in, <2 x double> %acc) {
|
|
%res = call double @llvm.experimental.vector.reduce.v2.fadd.f64.v2f64.v2f64(<2 x double> %acc, <2 x double> %in)
|
|
ret double %res
|
|
}
|
|
|
|
declare float @llvm.experimental.vector.reduce.v2.fadd.f32.f64.v2f64(double %acc, <2 x double> %in)
|
|
declare double @llvm.experimental.vector.reduce.v2.fadd.f64.f32.v2f64(float %acc, <2 x double> %in)
|
|
declare double @llvm.experimental.vector.reduce.v2.fadd.f64.v2f64.v2f64(<2 x double> %acc, <2 x double> %in)
|
|
declare <2 x double> @llvm.experimental.vector.reduce.v2.fadd.v2f64.f64.v2f64(double %acc, <2 x double> %in)
|