RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 03:02:36 +01:00
Code Issues Projects Releases Wiki Activity

[SelectionDAG] Remove an early-out from computeKnownBits for smin/smax

Browse Source 
Even if we know nothing about LHS, it can still be useful to know that
smax(LHS, RHS) >= RHS and smin(LHS, RHS) <= RHS.

Differential Revision: https://reviews.llvm.org/D87145
This commit is contained in:
Jay Foad 2020-09-03 19:22:33 +01:00
parent 79bc4c8e7b
commit af89a9efaf
2 changed files with 2 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View File

@ -3416,7 +3416,6 @@ KnownBits SelectionDAG::computeKnownBits(SDValue Op, const APInt &DemandedElts,
}
Known = computeKnownBits(Op.getOperand(0), DemandedElts, Depth + 1);
if (Known.isUnknown()) break; // Early-out
Known2 = computeKnownBits(Op.getOperand(1), DemandedElts, Depth + 1);
if (IsMax)
Known = KnownBits::smax(Known, Known2);

12
test/CodeGen/X86/known-bits-vector.ll
View File

@ -435,11 +435,7 @@ define <4 x float> @knownbits_smax_smin_shuffle_uitofp(<4 x i32> %a0) {
; X32-NEXT: vpminsd {{\.LCPI.*}}, %xmm0, %xmm0
; X32-NEXT: vpmaxsd {{\.LCPI.*}}, %xmm0, %xmm0
; X32-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,3,3]
; X32-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X32-NEXT: vpsrld $16, %xmm0, %xmm0
; X32-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X32-NEXT: vsubps {{\.LCPI.*}}, %xmm0, %xmm0
; X32-NEXT: vaddps %xmm0, %xmm1, %xmm0
; X32-NEXT: vcvtdq2ps %xmm0, %xmm0
; X32-NEXT: retl
;
; X64-LABEL: knownbits_smax_smin_shuffle_uitofp:
@ -447,11 +443,7 @@ define <4 x float> @knownbits_smax_smin_shuffle_uitofp(<4 x i32> %a0) {
; X64-NEXT: vpminsd {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vpmaxsd {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,3,3]
; X64-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X64-NEXT: vpsrld $16, %xmm0, %xmm0
; X64-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X64-NEXT: vsubps {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vaddps %xmm0, %xmm1, %xmm0
; X64-NEXT: vcvtdq2ps %xmm0, %xmm0
; X64-NEXT: retq
%1 = call <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32> %a0, <4 x i32> <i32 0, i32 -65535, i32 -65535, i32 0>)
%2 = call <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32> %1, <4 x i32> <i32 65535, i32 -1, i32 -1, i32 131071>)