mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 18:54:02 +01:00
beaa269335
Currently, instruction level fast math flags are not considered when
generating patterns for the machine combiner.
This currently leads to some missed opportunities to generate FMAs in
combination with `#pragma clang fp contract (fast)`.
For example, when building the example below with -O3 for AArch64, no
FMADD is generated. If built with -O2 and the DAGCombiner is used
instead of the MachineCombiner for FMAs, an FMADD is generated.
With this patch, the same code is generated in both cases.
float madd_contract(float a, float b, float c) {
#pragma clang fp contract (fast)
return (a * b) + c;
}
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D84930
57 lines
2.0 KiB
LLVM
57 lines
2.0 KiB
LLVM
; RUN: llc < %s -verify-machineinstrs -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s
|
|
; RUN: llc < %s -O3 -verify-machineinstrs -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s
|
|
|
|
define <2 x float> @fma_1(<2 x float> %A, <2 x float> %B, <2 x float> %C) {
|
|
; CHECK-LABEL: fma_1:
|
|
; CHECK: fmla {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s
|
|
%tmp1 = fmul contract <2 x float> %A, %B;
|
|
%tmp2 = fadd contract <2 x float> %C, %tmp1;
|
|
ret <2 x float> %tmp2
|
|
}
|
|
|
|
; This case will fold as it was only available through unsafe before, now available from
|
|
; the contract on the fadd
|
|
define <2 x float> @fma_2(<2 x float> %A, <2 x float> %B, <2 x float> %C) {
|
|
; CHECK-LABEL: fma_2:
|
|
; CHECK: fmla {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s
|
|
%tmp1 = fmul <2 x float> %A, %B;
|
|
%tmp2 = fadd contract <2 x float> %C, %tmp1;
|
|
ret <2 x float> %tmp2
|
|
}
|
|
|
|
define <2 x float> @no_fma_1(<2 x float> %A, <2 x float> %B, <2 x float> %C) {
|
|
; CHECK-LABEL: no_fma_1:
|
|
; CHECK: fmul
|
|
; CHECK: fadd
|
|
%tmp1 = fmul contract <2 x float> %A, %B;
|
|
%tmp2 = fadd <2 x float> %C, %tmp1;
|
|
ret <2 x float> %tmp2
|
|
}
|
|
|
|
define <2 x float> @fma_sub_1(<2 x float> %A, <2 x float> %B, <2 x float> %C) {
|
|
; CHECK-LABEL: fma_sub_1:
|
|
; CHECK: fmls {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s
|
|
%tmp1 = fmul contract <2 x float> %A, %B;
|
|
%tmp2 = fsub contract <2 x float> %C, %tmp1;
|
|
ret <2 x float> %tmp2
|
|
}
|
|
|
|
; This case will fold as it was only available through unsafe before, now available from
|
|
; the contract on the fsub
|
|
define <2 x float> @fma_sub_2(<2 x float> %A, <2 x float> %B, <2 x float> %C) {
|
|
; CHECK-LABEL: fma_sub_2:
|
|
; CHECK: fmls {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s
|
|
%tmp1 = fmul <2 x float> %A, %B;
|
|
%tmp2 = fsub contract <2 x float> %C, %tmp1;
|
|
ret <2 x float> %tmp2
|
|
}
|
|
|
|
define <2 x float> @no_fma_sub_1(<2 x float> %A, <2 x float> %B, <2 x float> %C) {
|
|
; CHECK-LABEL: no_fma_sub_1:
|
|
; CHECK: fmul
|
|
; CHECK: fsub
|
|
%tmp1 = fmul contract <2 x float> %A, %B;
|
|
%tmp2 = fsub <2 x float> %C, %tmp1;
|
|
ret <2 x float> %tmp2
|
|
}
|