mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +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
324 lines
9.9 KiB
LLVM
324 lines
9.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple powerpc64le -verify-machineinstrs \
|
|
; RUN: | FileCheck -check-prefix=VSX %s
|
|
; RUN: llc < %s -mtriple powerpc64le -verify-machineinstrs -mattr=-vsx \
|
|
; RUN: | FileCheck -check-prefix=NO-VSX %s
|
|
|
|
define double @test_mul_sub_f64(double %a, double %b, double %c) {
|
|
; VSX-LABEL: test_mul_sub_f64:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsnegdp 0, 2
|
|
; VSX-NEXT: xsmaddadp 1, 0, 3
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_mul_sub_f64:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fneg 0, 2
|
|
; NO-VSX-NEXT: fmadd 1, 0, 3, 1
|
|
; NO-VSX-NEXT: blr
|
|
entry:
|
|
%0 = fmul contract reassoc double %b, %c
|
|
%1 = fsub contract reassoc double %a, %0
|
|
ret double %1
|
|
}
|
|
|
|
define double @test_2mul_sub_f64(double %a, double %b, double %c, double %d) {
|
|
; VSX-LABEL: test_2mul_sub_f64:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsmuldp 0, 3, 4
|
|
; VSX-NEXT: xsmsubadp 0, 1, 2
|
|
; VSX-NEXT: fmr 1, 0
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_2mul_sub_f64:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fmul 0, 3, 4
|
|
; NO-VSX-NEXT: fmsub 1, 1, 2, 0
|
|
; NO-VSX-NEXT: blr
|
|
entry:
|
|
%0 = fmul contract reassoc double %a, %b
|
|
%1 = fmul contract reassoc double %c, %d
|
|
%2 = fsub contract reassoc double %0, %1
|
|
ret double %2
|
|
}
|
|
|
|
define double @test_neg_fma_f64(double %a, double %b, double %c) {
|
|
; VSX-LABEL: test_neg_fma_f64:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsnegdp 0, 1
|
|
; VSX-NEXT: xsmaddadp 3, 0, 2
|
|
; VSX-NEXT: fmr 1, 3
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_neg_fma_f64:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fneg 0, 1
|
|
; NO-VSX-NEXT: fmadd 1, 0, 2, 3
|
|
; NO-VSX-NEXT: blr
|
|
entry:
|
|
%0 = fsub contract reassoc double -0.0, %a
|
|
%1 = call contract reassoc double @llvm.fma.f64(double %0, double %b,
|
|
double %c)
|
|
ret double %1
|
|
}
|
|
|
|
define float @test_mul_sub_f32(float %a, float %b, float %c) {
|
|
; VSX-LABEL: test_mul_sub_f32:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsnegdp 0, 2
|
|
; VSX-NEXT: xsmaddasp 1, 0, 3
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_mul_sub_f32:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fneg 0, 2
|
|
; NO-VSX-NEXT: fmadds 1, 0, 3, 1
|
|
; NO-VSX-NEXT: blr
|
|
entry:
|
|
%0 = fmul contract reassoc float %b, %c
|
|
%1 = fsub contract reassoc float %a, %0
|
|
ret float %1
|
|
}
|
|
|
|
define float @test_2mul_sub_f32(float %a, float %b, float %c, float %d) {
|
|
; VSX-LABEL: test_2mul_sub_f32:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsmulsp 0, 3, 4
|
|
; VSX-NEXT: xsmsubasp 0, 1, 2
|
|
; VSX-NEXT: fmr 1, 0
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_2mul_sub_f32:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fmuls 0, 3, 4
|
|
; NO-VSX-NEXT: fmsubs 1, 1, 2, 0
|
|
; NO-VSX-NEXT: blr
|
|
entry:
|
|
%0 = fmul contract reassoc float %a, %b
|
|
%1 = fmul contract reassoc float %c, %d
|
|
%2 = fsub contract reassoc float %0, %1
|
|
ret float %2
|
|
}
|
|
|
|
define float @test_neg_fma_f32(float %a, float %b, float %c) {
|
|
; VSX-LABEL: test_neg_fma_f32:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsnegdp 0, 1
|
|
; VSX-NEXT: xsmaddasp 3, 0, 2
|
|
; VSX-NEXT: fmr 1, 3
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_neg_fma_f32:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fneg 0, 1
|
|
; NO-VSX-NEXT: fmadds 1, 0, 2, 3
|
|
; NO-VSX-NEXT: blr
|
|
entry:
|
|
%0 = fsub contract reassoc float -0.0, %a
|
|
%1 = call contract reassoc float @llvm.fma.f32(float %0, float %b, float %c)
|
|
ret float %1
|
|
}
|
|
|
|
define <2 x double> @test_neg_fma_v2f64(<2 x double> %a, <2 x double> %b,
|
|
; VSX-LABEL: test_neg_fma_v2f64:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xvnegdp 0, 34
|
|
; VSX-NEXT: xvmaddadp 36, 0, 35
|
|
; VSX-NEXT: vmr 2, 4
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_neg_fma_v2f64:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fneg 0, 2
|
|
; NO-VSX-NEXT: fneg 1, 1
|
|
; NO-VSX-NEXT: fmadd 1, 1, 3, 5
|
|
; NO-VSX-NEXT: fmadd 2, 0, 4, 6
|
|
; NO-VSX-NEXT: blr
|
|
<2 x double> %c) {
|
|
entry:
|
|
%0 = fsub contract reassoc <2 x double> <double -0.0, double -0.0>, %a
|
|
%1 = call contract reassoc <2 x double> @llvm.fma.v2f64(<2 x double> %0,
|
|
<2 x double> %b,
|
|
<2 x double> %c)
|
|
ret <2 x double> %1
|
|
}
|
|
|
|
define <4 x float> @test_neg_fma_v4f32(<4 x float> %a, <4 x float> %b,
|
|
; VSX-LABEL: test_neg_fma_v4f32:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xvnegsp 0, 34
|
|
; VSX-NEXT: xvmaddasp 36, 0, 35
|
|
; VSX-NEXT: vmr 2, 4
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_neg_fma_v4f32:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: vspltisb 5, -1
|
|
; NO-VSX-NEXT: vslw 5, 5, 5
|
|
; NO-VSX-NEXT: vsubfp 2, 5, 2
|
|
; NO-VSX-NEXT: vmaddfp 2, 2, 3, 4
|
|
; NO-VSX-NEXT: blr
|
|
<4 x float> %c) {
|
|
entry:
|
|
%0 = fsub contract reassoc <4 x float> <float -0.0, float -0.0, float -0.0,
|
|
float -0.0>, %a
|
|
%1 = call contract reassoc <4 x float> @llvm.fma.v4f32(<4 x float> %0,
|
|
<4 x float> %b,
|
|
<4 x float> %c)
|
|
ret <4 x float> %1
|
|
}
|
|
|
|
define double @test_fast_mul_sub_f64(double %a, double %b, double %c) {
|
|
; VSX-LABEL: test_fast_mul_sub_f64:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsnmsubadp 1, 2, 3
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_fast_mul_sub_f64:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fnmsub 1, 2, 3, 1
|
|
; NO-VSX-NEXT: blr
|
|
entry:
|
|
%0 = fmul contract reassoc nsz double %b, %c
|
|
%1 = fsub contract reassoc nsz double %a, %0
|
|
ret double %1
|
|
}
|
|
|
|
define double @test_fast_2mul_sub_f64(double %a, double %b, double %c,
|
|
; VSX-LABEL: test_fast_2mul_sub_f64:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsmuldp 0, 3, 4
|
|
; VSX-NEXT: xsmsubadp 0, 1, 2
|
|
; VSX-NEXT: fmr 1, 0
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_fast_2mul_sub_f64:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fmul 0, 3, 4
|
|
; NO-VSX-NEXT: fmsub 1, 1, 2, 0
|
|
; NO-VSX-NEXT: blr
|
|
double %d) {
|
|
entry:
|
|
%0 = fmul contract reassoc double %a, %b
|
|
%1 = fmul contract reassoc double %c, %d
|
|
%2 = fsub contract reassoc double %0, %1
|
|
ret double %2
|
|
}
|
|
|
|
define double @test_fast_neg_fma_f64(double %a, double %b, double %c) {
|
|
; VSX-LABEL: test_fast_neg_fma_f64:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsnmsubadp 3, 1, 2
|
|
; VSX-NEXT: fmr 1, 3
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_fast_neg_fma_f64:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fnmsub 1, 1, 2, 3
|
|
; NO-VSX-NEXT: blr
|
|
entry:
|
|
%0 = fsub reassoc double -0.0, %a
|
|
%1 = call reassoc nsz double @llvm.fma.f64(double %0, double %b, double %c)
|
|
ret double %1
|
|
}
|
|
|
|
define float @test_fast_mul_sub_f32(float %a, float %b, float %c) {
|
|
; VSX-LABEL: test_fast_mul_sub_f32:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsnmsubasp 1, 2, 3
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_fast_mul_sub_f32:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fnmsubs 1, 2, 3, 1
|
|
; NO-VSX-NEXT: blr
|
|
entry:
|
|
%0 = fmul contract reassoc float %b, %c
|
|
%1 = fsub contract reassoc nsz float %a, %0
|
|
ret float %1
|
|
}
|
|
|
|
define float @test_fast_2mul_sub_f32(float %a, float %b, float %c, float %d) {
|
|
; VSX-LABEL: test_fast_2mul_sub_f32:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsmulsp 0, 3, 4
|
|
; VSX-NEXT: xsmsubasp 0, 1, 2
|
|
; VSX-NEXT: fmr 1, 0
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_fast_2mul_sub_f32:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fmuls 0, 3, 4
|
|
; NO-VSX-NEXT: fmsubs 1, 1, 2, 0
|
|
; NO-VSX-NEXT: blr
|
|
entry:
|
|
%0 = fmul contract reassoc float %a, %b
|
|
%1 = fmul contract reassoc float %c, %d
|
|
%2 = fsub contract reassoc nsz float %0, %1
|
|
ret float %2
|
|
}
|
|
|
|
define float @test_fast_neg_fma_f32(float %a, float %b, float %c) {
|
|
; VSX-LABEL: test_fast_neg_fma_f32:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xsnmsubasp 3, 1, 2
|
|
; VSX-NEXT: fmr 1, 3
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_fast_neg_fma_f32:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fnmsubs 1, 1, 2, 3
|
|
; NO-VSX-NEXT: blr
|
|
entry:
|
|
%0 = fsub reassoc float -0.0, %a
|
|
%1 = call reassoc nsz float @llvm.fma.f32(float %0, float %b, float %c)
|
|
ret float %1
|
|
}
|
|
|
|
define <2 x double> @test_fast_neg_fma_v2f64(<2 x double> %a, <2 x double> %b,
|
|
; VSX-LABEL: test_fast_neg_fma_v2f64:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xvnmsubadp 36, 34, 35
|
|
; VSX-NEXT: vmr 2, 4
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_fast_neg_fma_v2f64:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: fnmsub 1, 1, 3, 5
|
|
; NO-VSX-NEXT: fnmsub 2, 2, 4, 6
|
|
; NO-VSX-NEXT: blr
|
|
<2 x double> %c) {
|
|
entry:
|
|
%0 = fsub reassoc <2 x double> <double -0.0, double -0.0>, %a
|
|
%1 = call reassoc nsz <2 x double> @llvm.fma.v2f64(<2 x double> %0, <2 x double> %b,
|
|
<2 x double> %c)
|
|
ret <2 x double> %1
|
|
}
|
|
|
|
define <4 x float> @test_fast_neg_fma_v4f32(<4 x float> %a, <4 x float> %b,
|
|
; VSX-LABEL: test_fast_neg_fma_v4f32:
|
|
; VSX: # %bb.0: # %entry
|
|
; VSX-NEXT: xvnmsubasp 36, 34, 35
|
|
; VSX-NEXT: vmr 2, 4
|
|
; VSX-NEXT: blr
|
|
;
|
|
; NO-VSX-LABEL: test_fast_neg_fma_v4f32:
|
|
; NO-VSX: # %bb.0: # %entry
|
|
; NO-VSX-NEXT: vnmsubfp 2, 2, 3, 4
|
|
; NO-VSX-NEXT: blr
|
|
<4 x float> %c) {
|
|
entry:
|
|
%0 = fsub reassoc <4 x float> <float -0.0, float -0.0, float -0.0,
|
|
float -0.0>, %a
|
|
%1 = call reassoc nsz <4 x float> @llvm.fma.v4f32(<4 x float> %0, <4 x float> %b,
|
|
<4 x float> %c)
|
|
ret <4 x float> %1
|
|
}
|
|
|
|
declare float @llvm.fma.f32(float %a, float %b, float %c)
|
|
declare double @llvm.fma.f64(double %a, double %b, double %c)
|
|
declare <4 x float> @llvm.fma.v4f32(<4 x float> %a, <4 x float> %b,
|
|
<4 x float> %c)
|
|
declare <2 x double> @llvm.fma.v2f64(<2 x double> %a, <2 x double> %b,
|
|
<2 x double> %c)
|