Skip to content

Commit

Permalink
Revert "[DAG] Support store merging of vector constant stores"
Browse files Browse the repository at this point in the history 
This reverts commit 660b740.  Crash reported in the review thread post commit.  Reverting while investigating.
  • Loading branch information
@preames
preames committed Aug 10, 2023
1 parent d43634c commit 0696a53
Show file tree
Hide file tree
Showing 4 changed files with 174 additions and 108 deletions.
13 changes: 1 addition & 12 deletions llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -698,11 +698,6 @@ namespace {
case ISD::Constant:
case ISD::ConstantFP:
return StoreSource::Constant;
case ISD::BUILD_VECTOR:
if (ISD::isBuildVectorOfConstantSDNodes(StoreVal.getNode()) ||
ISD::isBuildVectorOfConstantFPSDNodes(StoreVal.getNode()))
return StoreSource::Constant;
return StoreSource::Unknown;
case ISD::EXTRACT_VECTOR_ELT:
case ISD::EXTRACT_SUBVECTOR:
return StoreSource::Extract;
Expand Down Expand Up @@ -19500,10 +19495,6 @@ bool DAGCombiner::mergeStoresOfConstantsOrVecElts(
// If fp truncation is necessary give up for now.
if (MemVT.getSizeInBits() != ElementSizeBits)
return false;
} else if (ISD::isBuildVectorOfConstantSDNodes(Val.getNode()) ||
ISD::isBuildVectorOfConstantFPSDNodes(Val.getNode())) {
// Not yet handled
return false;
} else {
llvm_unreachable("Invalid constant element type");
}
Expand Down Expand Up @@ -19634,7 +19625,7 @@ void DAGCombiner::getStoreMergeCandidates(
case StoreSource::Constant:
if (NoTypeMatch)
return false;
if (getStoreSource(OtherBC) != StoreSource::Constant)
if (!isIntOrFPConstant(OtherBC))
return false;
break;
case StoreSource::Extract:
Expand Down Expand Up @@ -19856,8 +19847,6 @@ bool DAGCombiner::tryStoreMergeOfConstants(
IsElementZero = C->isZero();
else if (ConstantFPSDNode *C = dyn_cast<ConstantFPSDNode>(StoredVal))
IsElementZero = C->getConstantFPValue()->isNullValue();
else if (ISD::isBuildVectorAllZeros(StoredVal.getNode()))
IsElementZero = true;
if (IsElementZero) {
if (NonZero && FirstZeroAfterNonZero == NumConsecutiveStores)
FirstZeroAfterNonZero = i;
Expand Down
178 changes: 158 additions & 20 deletions llvm/test/CodeGen/RISCV/rvv/memset-inline.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -544,31 +544,53 @@ define void @bzero_32(ptr %a) nounwind {
define void @bzero_64(ptr %a) nounwind {
; RV32-LABEL: bzero_64:
; RV32: # %bb.0:
; RV32-NEXT: li a1, 64
; RV32-NEXT: vsetvli zero, a1, e8, m4, ta, ma
; RV32-NEXT: addi a1, a0, 48
; RV32-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; RV32-NEXT: vmv.v.i v8, 0
; RV32-NEXT: vse8.v v8, (a1)
; RV32-NEXT: addi a1, a0, 32
; RV32-NEXT: vse8.v v8, (a1)
; RV32-NEXT: addi a1, a0, 16
; RV32-NEXT: vse8.v v8, (a1)
; RV32-NEXT: vse8.v v8, (a0)
; RV32-NEXT: ret
;
; RV64-LABEL: bzero_64:
; RV64: # %bb.0:
; RV64-NEXT: li a1, 64
; RV64-NEXT: vsetvli zero, a1, e8, m4, ta, ma
; RV64-NEXT: addi a1, a0, 48
; RV64-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; RV64-NEXT: vmv.v.i v8, 0
; RV64-NEXT: vse8.v v8, (a1)
; RV64-NEXT: addi a1, a0, 32
; RV64-NEXT: vse8.v v8, (a1)
; RV64-NEXT: addi a1, a0, 16
; RV64-NEXT: vse8.v v8, (a1)
; RV64-NEXT: vse8.v v8, (a0)
; RV64-NEXT: ret
;
; RV32-FAST-LABEL: bzero_64:
; RV32-FAST: # %bb.0:
; RV32-FAST-NEXT: vsetivli zero, 8, e64, m4, ta, ma
; RV32-FAST-NEXT: addi a1, a0, 48
; RV32-FAST-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-FAST-NEXT: vmv.v.i v8, 0
; RV32-FAST-NEXT: vse64.v v8, (a1)
; RV32-FAST-NEXT: addi a1, a0, 32
; RV32-FAST-NEXT: vse64.v v8, (a1)
; RV32-FAST-NEXT: addi a1, a0, 16
; RV32-FAST-NEXT: vse64.v v8, (a1)
; RV32-FAST-NEXT: vse64.v v8, (a0)
; RV32-FAST-NEXT: ret
;
; RV64-FAST-LABEL: bzero_64:
; RV64-FAST: # %bb.0:
; RV64-FAST-NEXT: vsetivli zero, 8, e64, m4, ta, ma
; RV64-FAST-NEXT: addi a1, a0, 48
; RV64-FAST-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV64-FAST-NEXT: vmv.v.i v8, 0
; RV64-FAST-NEXT: vse64.v v8, (a1)
; RV64-FAST-NEXT: addi a1, a0, 32
; RV64-FAST-NEXT: vse64.v v8, (a1)
; RV64-FAST-NEXT: addi a1, a0, 16
; RV64-FAST-NEXT: vse64.v v8, (a1)
; RV64-FAST-NEXT: vse64.v v8, (a0)
; RV64-FAST-NEXT: ret
tail call void @llvm.memset.inline.p0.i64(ptr %a, i8 0, i64 64, i1 0)
Expand Down Expand Up @@ -664,15 +686,27 @@ define void @aligned_bzero_32(ptr %a) nounwind {
define void @aligned_bzero_64(ptr %a) nounwind {
; RV32-BOTH-LABEL: aligned_bzero_64:
; RV32-BOTH: # %bb.0:
; RV32-BOTH-NEXT: vsetivli zero, 8, e64, m4, ta, ma
; RV32-BOTH-NEXT: addi a1, a0, 48
; RV32-BOTH-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-BOTH-NEXT: vmv.v.i v8, 0
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 32
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 16
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: vse64.v v8, (a0)
; RV32-BOTH-NEXT: ret
;
; RV64-BOTH-LABEL: aligned_bzero_64:
; RV64-BOTH: # %bb.0:
; RV64-BOTH-NEXT: vsetivli zero, 8, e64, m4, ta, ma
; RV64-BOTH-NEXT: addi a1, a0, 48
; RV64-BOTH-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV64-BOTH-NEXT: vmv.v.i v8, 0
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 32
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 16
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: vse64.v v8, (a0)
; RV64-BOTH-NEXT: ret
tail call void @llvm.memset.inline.p0.i64(ptr align 64 %a, i8 0, i64 64, i1 0)
Expand All @@ -683,16 +717,28 @@ define void @aligned_bzero_66(ptr %a) nounwind {
; RV32-BOTH-LABEL: aligned_bzero_66:
; RV32-BOTH: # %bb.0:
; RV32-BOTH-NEXT: sh zero, 64(a0)
; RV32-BOTH-NEXT: vsetivli zero, 8, e64, m4, ta, ma
; RV32-BOTH-NEXT: addi a1, a0, 48
; RV32-BOTH-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-BOTH-NEXT: vmv.v.i v8, 0
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 32
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 16
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: vse64.v v8, (a0)
; RV32-BOTH-NEXT: ret
;
; RV64-BOTH-LABEL: aligned_bzero_66:
; RV64-BOTH: # %bb.0:
; RV64-BOTH-NEXT: sh zero, 64(a0)
; RV64-BOTH-NEXT: vsetivli zero, 8, e64, m4, ta, ma
; RV64-BOTH-NEXT: addi a1, a0, 48
; RV64-BOTH-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV64-BOTH-NEXT: vmv.v.i v8, 0
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 32
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 16
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: vse64.v v8, (a0)
; RV64-BOTH-NEXT: ret
tail call void @llvm.memset.inline.p0.i64(ptr align 64 %a, i8 0, i64 66, i1 0)
Expand All @@ -708,8 +754,12 @@ define void @aligned_bzero_96(ptr %a) nounwind {
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 64
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: vsetivli zero, 8, e64, m4, ta, ma
; RV32-BOTH-NEXT: vmv.v.i v8, 0
; RV32-BOTH-NEXT: addi a1, a0, 48
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 32
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 16
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: vse64.v v8, (a0)
; RV32-BOTH-NEXT: ret
;
Expand All @@ -721,8 +771,12 @@ define void @aligned_bzero_96(ptr %a) nounwind {
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 64
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: vsetivli zero, 8, e64, m4, ta, ma
; RV64-BOTH-NEXT: vmv.v.i v8, 0
; RV64-BOTH-NEXT: addi a1, a0, 48
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 32
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 16
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: vse64.v v8, (a0)
; RV64-BOTH-NEXT: ret
tail call void @llvm.memset.inline.p0.i64(ptr align 64 %a, i8 0, i64 96, i1 0)
Expand All @@ -732,15 +786,43 @@ define void @aligned_bzero_96(ptr %a) nounwind {
define void @aligned_bzero_128(ptr %a) nounwind {
; RV32-BOTH-LABEL: aligned_bzero_128:
; RV32-BOTH: # %bb.0:
; RV32-BOTH-NEXT: vsetivli zero, 16, e64, m8, ta, ma
; RV32-BOTH-NEXT: addi a1, a0, 112
; RV32-BOTH-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-BOTH-NEXT: vmv.v.i v8, 0
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 96
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 80
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 64
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 48
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 32
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 16
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: vse64.v v8, (a0)
; RV32-BOTH-NEXT: ret
;
; RV64-BOTH-LABEL: aligned_bzero_128:
; RV64-BOTH: # %bb.0:
; RV64-BOTH-NEXT: vsetivli zero, 16, e64, m8, ta, ma
; RV64-BOTH-NEXT: addi a1, a0, 112
; RV64-BOTH-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV64-BOTH-NEXT: vmv.v.i v8, 0
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 96
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 80
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 64
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 48
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 32
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 16
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: vse64.v v8, (a0)
; RV64-BOTH-NEXT: ret
tail call void @llvm.memset.inline.p0.i64(ptr align 64 %a, i8 0, i64 128, i1 0)
Expand All @@ -750,19 +832,75 @@ define void @aligned_bzero_128(ptr %a) nounwind {
define void @aligned_bzero_256(ptr %a) nounwind {
; RV32-BOTH-LABEL: aligned_bzero_256:
; RV32-BOTH: # %bb.0:
; RV32-BOTH-NEXT: addi a1, a0, 128
; RV32-BOTH-NEXT: vsetivli zero, 16, e64, m8, ta, ma
; RV32-BOTH-NEXT: addi a1, a0, 240
; RV32-BOTH-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-BOTH-NEXT: vmv.v.i v8, 0
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 224
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 208
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 192
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 176
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 160
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 144
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 128
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 112
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 96
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 80
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 64
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 48
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 32
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: addi a1, a0, 16
; RV32-BOTH-NEXT: vse64.v v8, (a1)
; RV32-BOTH-NEXT: vse64.v v8, (a0)
; RV32-BOTH-NEXT: ret
;
; RV64-BOTH-LABEL: aligned_bzero_256:
; RV64-BOTH: # %bb.0:
; RV64-BOTH-NEXT: addi a1, a0, 128
; RV64-BOTH-NEXT: vsetivli zero, 16, e64, m8, ta, ma
; RV64-BOTH-NEXT: addi a1, a0, 240
; RV64-BOTH-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV64-BOTH-NEXT: vmv.v.i v8, 0
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 224
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 208
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 192
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 176
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 160
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 144
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 128
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 112
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 96
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 80
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 64
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 48
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 32
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: addi a1, a0, 16
; RV64-BOTH-NEXT: vse64.v v8, (a1)
; RV64-BOTH-NEXT: vse64.v v8, (a0)
; RV64-BOTH-NEXT: ret
tail call void @llvm.memset.inline.p0.i64(ptr align 64 %a, i8 0, i64 256, i1 0)
Expand Down
Loading

0 comments on commit 0696a53

Please sign in to comment.