mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 18:54:02 +01:00
4d8c0e830b
According to IR LangRef, the FMF flag: contract Allow floating-point contraction (e.g. fusing a multiply followed by an addition into a fused multiply-and-add). reassoc Allow reassociation transformations for floating-point instructions. This may dramatically change results in floating-point. My understanding is that these two flags shouldn't imply each other, as we might have a SDNode that can be reassociated with others, but not contractble. eg: We may want following fmul/fad/fsub to freely reassoc, but don't want fma being generated here. %F = fmul reassoc double %A, %B ; <double> [#uses=1] %G = fmul reassoc double %C, %D ; <double> [#uses=1] %H = fadd reassoc double %F, %G ; <double> [#uses=1] %I = fsub reassoc double %H, %E ; <double> [#uses=1] Before https://reviews.llvm.org/D45710, `reassoc` flag actually did not imply isContratable either. The current implementation also only check the flag in fadd node, ignoring fmul node, this patch update that as well. Reviewed By: spatel, qiucf Differential Revision: https://reviews.llvm.org/D104247
45 lines
1.4 KiB
LLVM
45 lines
1.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 -mattr=+vsx -disable-ppc-vsx-fma-mutation=false | FileCheck %s
|
|
|
|
declare double @llvm.sqrt.f64(double)
|
|
|
|
; Test several VSX FMA mutation opportunities.
|
|
|
|
; This is reasonable transformation since it eliminates extra register copy.
|
|
define double @foo3_fmf(double %a) nounwind {
|
|
; CHECK-LABEL: foo3_fmf:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: xstsqrtdp 0, 1
|
|
; CHECK-NEXT: bc 12, 2, .LBB0_2
|
|
; CHECK-NEXT: # %bb.1:
|
|
; CHECK-NEXT: xsrsqrtedp 0, 1
|
|
; CHECK-NEXT: addis 3, 2, .LCPI0_0@toc@ha
|
|
; CHECK-NEXT: lfs 3, .LCPI0_0@toc@l(3)
|
|
; CHECK-NEXT: addis 3, 2, .LCPI0_1@toc@ha
|
|
; CHECK-NEXT: lfs 4, .LCPI0_1@toc@l(3)
|
|
; CHECK-NEXT: xsmuldp 2, 1, 0
|
|
; CHECK-NEXT: xsmaddmdp 2, 0, 3
|
|
; CHECK-NEXT: xsmuldp 0, 0, 4
|
|
; CHECK-NEXT: xsmuldp 0, 0, 2
|
|
; CHECK-NEXT: xsmuldp 1, 1, 0
|
|
; CHECK-NEXT: xsmaddadp 3, 1, 0
|
|
; CHECK-NEXT: xsmuldp 0, 1, 4
|
|
; CHECK-NEXT: xsmuldp 1, 0, 3
|
|
; CHECK-NEXT: blr
|
|
; CHECK-NEXT: .LBB0_2:
|
|
; CHECK-NEXT: xssqrtdp 1, 1
|
|
; CHECK-NEXT: blr
|
|
%r = call contract reassoc afn ninf double @llvm.sqrt.f64(double %a)
|
|
ret double %r
|
|
}
|
|
|
|
define double @foo3_safe(double %a) nounwind {
|
|
; CHECK-LABEL: foo3_safe:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: xssqrtdp 1, 1
|
|
; CHECK-NEXT: blr
|
|
%r = call double @llvm.sqrt.f64(double %a)
|
|
ret double %r
|
|
}
|
|
|