1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 19:52:54 +01:00
llvm-mirror/test/Bitcode/upgrade-vecreduce-intrinsics.ll
Sander de Smalen e1e23467af Change semantics of fadd/fmul vector reductions.
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
2019-06-11 08:22:10 +00:00

65 lines
2.9 KiB
LLVM

; RUN: opt -S < %s | FileCheck %s
; RUN: llvm-dis < %s.bc | FileCheck %s
define float @fadd_acc(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fadd_acc
; CHECK: %res = call float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float %acc, <4 x float> %in)
%res = call float @llvm.experimental.vector.reduce.fadd.f32.v4f32(float %acc, <4 x float> %in)
ret float %res
}
define float @fadd_undef(<4 x float> %in) {
; CHECK-LABEL: @fadd_undef
; CHECK: %res = call float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float undef, <4 x float> %in)
%res = call float @llvm.experimental.vector.reduce.fadd.f32.v4f32(float undef, <4 x float> %in)
ret float %res
}
define float @fadd_fast_acc(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fadd_fast_acc
; CHECK: %res = call fast float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float 0.000000e+00, <4 x float> %in)
%res = call fast float @llvm.experimental.vector.reduce.fadd.f32.v4f32(float %acc, <4 x float> %in)
ret float %res
}
define float @fadd_fast_undef(<4 x float> %in) {
; CHECK-LABEL: @fadd_fast_undef
; CHECK: %res = call fast float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float 0.000000e+00, <4 x float> %in)
%res = call fast float @llvm.experimental.vector.reduce.fadd.f32.v4f32(float undef, <4 x float> %in)
ret float %res
}
define float @fmul_acc(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fmul_acc
; CHECK: %res = call float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float %acc, <4 x float> %in)
%res = call float @llvm.experimental.vector.reduce.fmul.f32.v4f32(float %acc, <4 x float> %in)
ret float %res
}
define float @fmul_undef(<4 x float> %in) {
; CHECK-LABEL: @fmul_undef
; CHECK: %res = call float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float undef, <4 x float> %in)
%res = call float @llvm.experimental.vector.reduce.fmul.f32.v4f32(float undef, <4 x float> %in)
ret float %res
}
define float @fmul_fast_acc(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fmul_fast_acc
; CHECK: %res = call fast float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float 1.000000e+00, <4 x float> %in)
%res = call fast float @llvm.experimental.vector.reduce.fmul.f32.v4f32(float %acc, <4 x float> %in)
ret float %res
}
define float @fmul_fast_undef(<4 x float> %in) {
; CHECK-LABEL: @fmul_fast_undef
; CHECK: %res = call fast float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float 1.000000e+00, <4 x float> %in)
%res = call fast float @llvm.experimental.vector.reduce.fmul.f32.v4f32(float undef, <4 x float> %in)
ret float %res
}
declare float @llvm.experimental.vector.reduce.fadd.f32.v4f32(float, <4 x float>)
; CHECK: declare float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float, <4 x float>)
declare float @llvm.experimental.vector.reduce.fmul.f32.v4f32(float, <4 x float>)
; CHECK: declare float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float, <4 x float>)