Skip to content

[IA] Add support for [de]interleave{3,5,7} #139373

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
May 22, 2025
Merged

[IA] Add support for [de]interleave{3,5,7} #139373

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c45fca8
Precommit tests
lukel97 May 10, 2025
a6b4b02
[IA] Support [de]interleave{3,5,7}
lukel97 May 10, 2025
cbf92d8
Add opt tests
lukel97 May 12, 2025
b9f0574
Update comment to mention other intrinsics
lukel97 May 12, 2025
33652d3
Update comments
lukel97 May 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions llvm/include/llvm/CodeGen/TargetLowering.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3234,7 +3234,7 @@ class TargetLoweringBase {

/// Lower a deinterleave intrinsic to a target specific load intrinsic.
/// Return true on success. Currently only supports
/// llvm.vector.deinterleave2
/// llvm.vector.deinterleave{2,3,5,7}
///
/// \p LI is the accompanying load instruction.
/// \p DeinterleaveValues contains the deinterleaved values.
Expand All @@ -3246,7 +3246,7 @@ class TargetLoweringBase {

/// Lower an interleave intrinsic to a target specific store intrinsic.
/// Return true on success. Currently only supports
/// llvm.vector.interleave2
/// llvm.vector.interleave{2,3,5,7}
///
/// \p SI is the accompanying store instruction
/// \p InterleaveValues contains the interleaved values.
Expand Down
75 changes: 56 additions & 19 deletions llvm/lib/CodeGen/InterleavedAccessPass.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -571,6 +571,25 @@ bool InterleavedAccessImpl::lowerInterleavedStore(
return true;
}

static unsigned getIntrinsicFactor(const IntrinsicInst *II) {
switch (II->getIntrinsicID()) {
case Intrinsic::vector_deinterleave2:
case Intrinsic::vector_interleave2:
return 2;
case Intrinsic::vector_deinterleave3:
case Intrinsic::vector_interleave3:
return 3;
case Intrinsic::vector_deinterleave5:
case Intrinsic::vector_interleave5:
return 5;
case Intrinsic::vector_deinterleave7:
case Intrinsic::vector_interleave7:
return 7;
default:
llvm_unreachable("Unexpected intrinsic");
}
}

// For an (de)interleave tree like this:
//
// A C B D
Expand All @@ -586,7 +605,7 @@ bool InterleavedAccessImpl::lowerInterleavedStore(
// to reorder them by interleaving these values.
static void interleaveLeafValues(MutableArrayRef<Value *> SubLeaves) {
unsigned NumLeaves = SubLeaves.size();
if (NumLeaves == 2)
if (NumLeaves == 2 || !isPowerOf2_64(NumLeaves))
return;

assert(isPowerOf2_32(NumLeaves) && NumLeaves > 1);
Expand All @@ -608,7 +627,10 @@ static void interleaveLeafValues(MutableArrayRef<Value *> SubLeaves) {
static bool
getVectorInterleaveFactor(IntrinsicInst *II, SmallVectorImpl<Value *> &Operands,
SmallVectorImpl<Instruction *> &DeadInsts) {
assert(II->getIntrinsicID() == Intrinsic::vector_interleave2);
assert(II->getIntrinsicID() == Intrinsic::vector_interleave2 ||
II->getIntrinsicID() == Intrinsic::vector_interleave3 ||
II->getIntrinsicID() == Intrinsic::vector_interleave5 ||
II->getIntrinsicID() == Intrinsic::vector_interleave7);

// Visit with BFS
SmallVector<IntrinsicInst *, 8> Queue;
Expand All @@ -620,7 +642,7 @@ getVectorInterleaveFactor(IntrinsicInst *II, SmallVectorImpl<Value *> &Operands,
// All the intermediate intrinsics will be deleted.
DeadInsts.push_back(Current);

for (unsigned I = 0; I < 2; ++I) {
for (unsigned I = 0; I < getIntrinsicFactor(Current); ++I) {
Value *Op = Current->getOperand(I);
if (auto *OpII = dyn_cast<IntrinsicInst>(Op))
if (OpII->getIntrinsicID() == Intrinsic::vector_interleave2) {
Expand All @@ -638,9 +660,10 @@ getVectorInterleaveFactor(IntrinsicInst *II, SmallVectorImpl<Value *> &Operands,
}

const unsigned Factor = Operands.size();
// Currently we only recognize power-of-two factors.
// Currently we only recognize factors of 2, 3, 5 and 7.
// FIXME: should we assert here instead?
if (Factor <= 1 || !isPowerOf2_32(Factor))
if (Factor <= 1 ||
(!isPowerOf2_32(Factor) && Factor != getIntrinsicFactor(II)))
return false;

interleaveLeafValues(Operands);
Expand All @@ -651,9 +674,12 @@ static bool
getVectorDeinterleaveFactor(IntrinsicInst *II,
SmallVectorImpl<Value *> &Results,
SmallVectorImpl<Instruction *> &DeadInsts) {
assert(II->getIntrinsicID() == Intrinsic::vector_deinterleave2);
assert(II->getIntrinsicID() == Intrinsic::vector_deinterleave2 ||
II->getIntrinsicID() == Intrinsic::vector_deinterleave3 ||
II->getIntrinsicID() == Intrinsic::vector_deinterleave5 ||
II->getIntrinsicID() == Intrinsic::vector_deinterleave7);
using namespace PatternMatch;
if (!II->hasNUses(2))
if (!II->hasNUses(getIntrinsicFactor(II)))
return false;

// Visit with BFS
Expand All @@ -662,12 +688,12 @@ getVectorDeinterleaveFactor(IntrinsicInst *II,
while (!Queue.empty()) {
IntrinsicInst *Current = Queue.front();
Queue.erase(Queue.begin());
assert(Current->hasNUses(2));
assert(Current->hasNUses(getIntrinsicFactor(Current)));

// All the intermediate intrinsics will be deleted from the bottom-up.
DeadInsts.insert(DeadInsts.begin(), Current);

ExtractValueInst *LHS = nullptr, *RHS = nullptr;
SmallVector<ExtractValueInst *> EVs(getIntrinsicFactor(Current), nullptr);
for (User *Usr : Current->users()) {
if (!isa<ExtractValueInst>(Usr))
return 0;
Expand All @@ -679,17 +705,15 @@ getVectorDeinterleaveFactor(IntrinsicInst *II,
if (Indices.size() != 1)
return false;

if (Indices[0] == 0 && !LHS)
LHS = EV;
else if (Indices[0] == 1 && !RHS)
RHS = EV;
if (!EVs[Indices[0]])
EVs[Indices[0]] = EV;
else
return false;
}

// We have legal indices. At this point we're either going
// to continue the traversal or push the leaf values into Results.
for (ExtractValueInst *EV : {LHS, RHS}) {
for (ExtractValueInst *EV : EVs) {
// Continue the traversal. We're playing safe here and matching only the
// expression consisting of a perfectly balanced binary tree in which all
// intermediate values are only used once.
Expand All @@ -713,9 +737,10 @@ getVectorDeinterleaveFactor(IntrinsicInst *II,
}

const unsigned Factor = Results.size();
// Currently we only recognize power-of-two factors.
// Currently we only recognize factors of 2, 3, 5 and 7.
// FIXME: should we assert here instead?
if (Factor <= 1 || !isPowerOf2_32(Factor))
if (Factor <= 1 ||
(!isPowerOf2_32(Factor) && Factor != getIntrinsicFactor(II)))
return 0;

interleaveLeafValues(Results);
Expand Down Expand Up @@ -878,11 +903,23 @@ bool InterleavedAccessImpl::runOnFunction(Function &F) {

if (auto *II = dyn_cast<IntrinsicInst>(&I)) {
// At present, we only have intrinsics to represent (de)interleaving
// with a factor of 2.
if (II->getIntrinsicID() == Intrinsic::vector_deinterleave2)
// with a factor of 2,3,5 and 7.
switch (II->getIntrinsicID()) {
case Intrinsic::vector_deinterleave2:
case Intrinsic::vector_deinterleave3:
case Intrinsic::vector_deinterleave5:
case Intrinsic::vector_deinterleave7:
Changed |= lowerDeinterleaveIntrinsic(II, DeadInsts);
else if (II->getIntrinsicID() == Intrinsic::vector_interleave2)
break;
case Intrinsic::vector_interleave2:
case Intrinsic::vector_interleave3:
case Intrinsic::vector_interleave5:
case Intrinsic::vector_interleave7:
Changed |= lowerInterleaveIntrinsic(II, DeadInsts);
break;
default:
break;
}
}
}

Expand Down
63 changes: 63 additions & 0 deletions llvm/test/CodeGen/RISCV/rvv/fixed-vectors-deinterleave-load.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -257,6 +257,23 @@ define {<2 x double>, <2 x double>} @vector_deinterleave_load_v2f64_v4f64(ptr %p
ret {<2 x double>, <2 x double>} %res1
}

define { <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor3(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor3:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vlseg3e8.v v6, (a0)
; CHECK-NEXT: ret
%vec = load <24 x i8>, ptr %p
%d0 = call {<8 x i8>, <8 x i8>, <8 x i8>} @llvm.vector.deinterleave3(<24 x i8> %vec)
%t0 = extractvalue {<8 x i8>, <8 x i8>, <8 x i8>} %d0, 0
%t1 = extractvalue {<8 x i8>, <8 x i8>, <8 x i8>} %d0, 1
%t2 = extractvalue {<8 x i8>, <8 x i8>, <8 x i8>} %d0, 2
%res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
%res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 0
%res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 0
ret { <8 x i8>, <8 x i8>, <8 x i8> } %res2
}

define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor4(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor4:
; CHECK: # %bb.0:
Expand All @@ -281,6 +298,52 @@ define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_fact
ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3
}

define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor5(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor5:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vlseg5e8.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <40 x i8>, ptr %p
%d0 = call {<8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>} @llvm.vector.deinterleave5(<40 x i8> %vec)
%t0 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 0
%t1 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 1
%t2 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 2
%t3 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 3
%t4 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 4
%res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
%res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 1
%res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 2
%res3 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res2, <8 x i8> %t3, 3
%res4 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t4, 4
ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res4
}

define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor7(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor7:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vlseg7e8.v v8, (a0)
; CHECK-NEXT: ret
%vec = load <56 x i8>, ptr %p
%d0 = call {<8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>} @llvm.vector.deinterleave7(<56 x i8> %vec)
%t0 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 0
%t1 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 1
%t2 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 2
%t3 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 3
%t4 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 4
%t5 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 5
%t6 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 6
%res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
%res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 1
%res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 2
%res3 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res2, <8 x i8> %t3, 3
%res4 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t4, 4
%res5 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t5, 5
%res6 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t6, 6
ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res6
}

define {<2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>} @vector_deinterleave_load_factor8(ptr %ptr) {
; CHECK-LABEL: vector_deinterleave_load_factor8:
; CHECK: # %bb.0:
Expand Down
33 changes: 33 additions & 0 deletions llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleave-store.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,6 +181,17 @@ define void @vector_interleave_store_v4f64_v2f64(<2 x double> %a, <2 x double> %
ret void
}

define void @vector_interleave_store_factor3(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, ptr %p) {
; CHECK-LABEL: vector_interleave_store_factor3:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vsseg3e32.v v8, (a0)
; CHECK-NEXT: ret
%v = call <12 x i32> @llvm.vector.interleave3(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c)
store <12 x i32> %v, ptr %p
ret void
}

define void @vector_interleave_store_factor4(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, ptr %p) {
; CHECK-LABEL: vector_interleave_store_factor4:
; CHECK: # %bb.0:
Expand All @@ -194,6 +205,28 @@ define void @vector_interleave_store_factor4(<4 x i32> %a, <4 x i32> %b, <4 x i3
ret void
}

define void @vector_interleave_store_factor5(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, <4 x i32> %e, ptr %p) {
; CHECK-LABEL: vector_interleave_store_factor5:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vsseg5e32.v v8, (a0)
; CHECK-NEXT: ret
%v = call <20 x i32> @llvm.vector.interleave5(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, <4 x i32> %e)
store <20 x i32> %v, ptr %p
ret void
}

define void @vector_interleave_store_factor7(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, <4 x i32> %e, <4 x i32> %f, <4 x i32> %g, ptr %p) {
; CHECK-LABEL: vector_interleave_store_factor7:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vsseg7e32.v v8, (a0)
; CHECK-NEXT: ret
%v = call <28 x i32> @llvm.vector.interleave7(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, <4 x i32> %e, <4 x i32> %f, <4 x i32> %g)
store <28 x i32> %v, ptr %p
ret void
}

define void @vector_interleave_store_factor8(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, <4 x i32> %e, <4 x i32> %f, <4 x i32> %g, <4 x i32> %h, ptr %p) {
; CHECK-LABEL: vector_interleave_store_factor8:
; CHECK: # %bb.0:
Expand Down
Loading