maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[x86] enable machine combiner reassociations for 128-bit vector single/double adds 

llvm-svn: 244403
This commit is contained in:
Sanjay Patel 2015-08-08 19:08:20 +00:00
parent df005cbe19
commit e0178262d4
2 changed files with 48 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Target/X86/X86InstrInfo.cpp
View File

@ -6371,8 +6371,12 @@ static bool isAssociativeAndCommutative(const MachineInstr &Inst) {
case X86::IMUL32rr:
case X86::IMUL64rr:
return true;
case X86::ADDPDrr:
case X86::ADDPSrr:
case X86::ADDSDrr:
case X86::ADDSSrr:
case X86::VADDPDrr:
case X86::VADDPSrr:
case X86::VADDSDrr:
case X86::VADDSSrr:
case X86::MULSDrr:

44
llvm/test/CodeGen/X86/machine-combiner.ll
View File

@ -210,3 +210,47 @@ define double @reassociate_muls_double(double %x0, double %x1, double %x2, doubl
ret double %t2
}
; Verify that SSE and AVX 128-bit vector single-precison adds are reassociated.
define <4 x float> @reassociate_adds_v4f32(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, <4 x float> %x3) {
; SSE-LABEL: reassociate_adds_v4f32:
; SSE: # BB#0:
; SSE-NEXT: mulps %xmm1, %xmm0
; SSE-NEXT: addps %xmm3, %xmm2
; SSE-NEXT: addps %xmm2, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: reassociate_adds_v4f32:
; AVX: # BB#0:
; AVX-NEXT: vmulps %xmm1, %xmm0, %xmm0
; AVX-NEXT: vaddps %xmm3, %xmm2, %xmm1
; AVX-NEXT: vaddps %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%t0 = fmul <4 x float> %x0, %x1
%t1 = fadd <4 x float> %x2, %t0
%t2 = fadd <4 x float> %x3, %t1
ret <4 x float> %t2
}
; Verify that SSE and AVX 128-bit vector double-precison adds are reassociated.
define <2 x double> @reassociate_adds_v2f64(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, <2 x double> %x3) {
; SSE-LABEL: reassociate_adds_v2f64:
; SSE: # BB#0:
; SSE-NEXT: mulpd %xmm1, %xmm0
; SSE-NEXT: addpd %xmm3, %xmm2
; SSE-NEXT: addpd %xmm2, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: reassociate_adds_v2f64:
; AVX: # BB#0:
; AVX-NEXT: vmulpd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vaddpd %xmm3, %xmm2, %xmm1
; AVX-NEXT: vaddpd %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%t0 = fmul <2 x double> %x0, %x1
%t1 = fadd <2 x double> %x2, %t0
%t2 = fadd <2 x double> %x3, %t1
ret <2 x double> %t2
}