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

[x86] try select simplification for target-specific nodes 

This failed to select (which might be a separate bug) in
X86ISelDAGToDAG because we try to create a select node
that can be simplified away after rL347227.

This change avoids the problem by simplifying the SHRUNKBLEND
node sooner. In the test case, we manage to realize that the
true/false values of the select (SHRUNKBLEND) are the same thing,
so it simplifies away completely.

llvm-svn: 347818
This commit is contained in:
Sanjay Patel 2018-11-28 22:51:04 +00:00
parent b02baf0a7e
commit 2de209313e
2 changed files with 57 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -33674,9 +33674,14 @@ static SDValue combineSelect(SDNode *N, SelectionDAG &DAG,
const X86Subtarget &Subtarget) {
SDLoc DL(N);
SDValue Cond = N->getOperand(0);
// Get the LHS/RHS of the select.
SDValue LHS = N->getOperand(1);
SDValue RHS = N->getOperand(2);
// Try simplification again because we use this function to optimize
// SHRUNKBLEND nodes that are not handled by the generic combiner.
if (SDValue V = DAG.simplifySelect(Cond, LHS, RHS))
return V;
EVT VT = LHS.getValueType();
EVT CondVT = Cond.getValueType();
const TargetLowering &TLI = DAG.getTargetLoweringInfo();

51
llvm/test/CodeGen/X86/vselect.ll
View File

@ -559,3 +559,54 @@ define <2 x i64> @shrunkblend_nonvselectuse(<2 x i1> %cond, <2 x i64> %a, <2 x i
ret <2 x i64> %z
}
; This turns into a SHRUNKBLEND with SSE4 or later, and via
; late shuffle magic, both sides of the blend are the same
; value. If that is not simplified before isel, it can fail
; to match (crash).
define <2 x i32> @simplify_select(i32 %x, <2 x i1> %z) {
; SSE2-LABEL: simplify_select:
; SSE2: # %bb.0:
; SSE2-NEXT: # kill: def $edi killed $edi def $rdi
; SSE2-NEXT: psllq $63, %xmm0
; SSE2-NEXT: psrad $31, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,3,3]
; SSE2-NEXT: movq %rdi, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[0,1,0,1]
; SSE2-NEXT: movdqa %xmm2, %xmm3
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm1[0]
; SSE2-NEXT: pand %xmm0, %xmm2
; SSE2-NEXT: pandn %xmm3, %xmm0
; SSE2-NEXT: por %xmm2, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: simplify_select:
; SSE41: # %bb.0:
; SSE41-NEXT: # kill: def $edi killed $edi def $rdi
; SSE41-NEXT: movq %rdi, %xmm0
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
; SSE41-NEXT: retq
;
; AVX1-LABEL: simplify_select:
; AVX1: # %bb.0:
; AVX1-NEXT: # kill: def $edi killed $edi def $rdi
; AVX1-NEXT: vmovq %rdi, %xmm0
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
; AVX1-NEXT: retq
;
; AVX2-LABEL: simplify_select:
; AVX2: # %bb.0:
; AVX2-NEXT: # kill: def $edi killed $edi def $rdi
; AVX2-NEXT: vmovq %rdi, %xmm0
; AVX2-NEXT: vpbroadcastq %xmm0, %xmm0
; AVX2-NEXT: retq
%a = insertelement <2 x i32> <i32 0, i32 undef>, i32 %x, i32 1
%b = insertelement <2 x i32> <i32 undef, i32 0>, i32 %x, i32 0
%y = or <2 x i32> %a, %b
%p16 = extractelement <2 x i32> %y, i32 1
%p17 = insertelement <2 x i32> undef, i32 %p16, i32 0
%p18 = insertelement <2 x i32> %p17, i32 %x, i32 1
%r = select <2 x i1> %z, <2 x i32> %y, <2 x i32> %p18
ret <2 x i32> %r
}