1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 11:13:28 +01:00
llvm-mirror/test/CodeGen/AArch64/neon-fma-FMF.ll
Adam Nemet f9970cbc84 [DAGCombine] Support FMF contract in fused multiple-and-sub too
This is a follow-on to r299096 which added support for fmadd.

Subtract does not have the case where with two multiply operands we commute in
order to fuse with the multiply with the fewer uses.

llvm-svn: 299572
2017-04-05 17:58:48 +00:00

54 lines
1.6 KiB
LLVM

; RUN: llc < %s -verify-machineinstrs -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s
define <2 x float> @fma(<2 x float> %A, <2 x float> %B, <2 x float> %C) {
; CHECK-LABEL: fma:
; 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
}
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> @no_fma_2(<2 x float> %A, <2 x float> %B, <2 x float> %C) {
; CHECK-LABEL: no_fma_2:
; CHECK: fmul
; CHECK: fadd
%tmp1 = fmul <2 x float> %A, %B;
%tmp2 = fadd contract <2 x float> %C, %tmp1;
ret <2 x float> %tmp2
}
define <2 x float> @fma_sub(<2 x float> %A, <2 x float> %B, <2 x float> %C) {
; CHECK-LABEL: fma_sub:
; 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
}
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
}
define <2 x float> @no_fma_sub_2(<2 x float> %A, <2 x float> %B, <2 x float> %C) {
; CHECK-LABEL: no_fma_sub_2:
; CHECK: fmul
; CHECK: fsub
%tmp1 = fmul <2 x float> %A, %B;
%tmp2 = fsub contract <2 x float> %C, %tmp1;
ret <2 x float> %tmp2
}