[llvm] [AMDGPU] Handle memcpy()-like ops in LowerBufferFatPointers (PR #126621)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Feb 10 15:04:16 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Krzysztof Drewniak (krzysz00)
<details>
<summary>Changes</summary>
Since LowerBufferFatPointers runs before codegenprepare, which normally handles unsupported memcpy()s,, and since you can't have a `noalias {ptr addrspace(8), i32}` becasue it crashes later passes, manually expand memcpy()s involving buffer fat pointers to loops.
Additionally, though they're unlikely to be used, this commit adds support for memset().
This commit doesn't implement writing direct-to-LDS loads as the intrinsics, but leaves the option in the future.
[AMDGPU][LowerBufferFatPointers] Support memcpy(), memset()
---
Patch is 318.81 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/126621.diff
2 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/AMDGPULowerBufferFatPointers.cpp (+98-24)
- (added) llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-mem-transfer.ll (+1730)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerBufferFatPointers.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerBufferFatPointers.cpp
index ccb874e6a934e70..e4120ee79bd4b8c 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerBufferFatPointers.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerBufferFatPointers.cpp
@@ -45,16 +45,16 @@
//
// This pass proceeds in three main phases:
//
-// ## Rewriting loads and stores of p7
+// ## Rewriting loads and stores of p7 and memcpy()-like handling
//
// The first phase is to rewrite away all loads and stors of `ptr addrspace(7)`,
// including aggregates containing such pointers, to ones that use `i160`. This
-// is handled by `StoreFatPtrsAsIntsVisitor` , which visits loads, stores, and
-// allocas and, if the loaded or stored type contains `ptr addrspace(7)`,
-// rewrites that type to one where the p7s are replaced by i160s, copying other
-// parts of aggregates as needed. In the case of a store, each pointer is
-// `ptrtoint`d to i160 before storing, and load integers are `inttoptr`d back.
-// This same transformation is applied to vectors of pointers.
+// is handled by `StoreFatPtrsAsIntsAndExpandMemcpyVisitor` , which visits
+// loads, stores, and allocas and, if the loaded or stored type contains `ptr
+// addrspace(7)`, rewrites that type to one where the p7s are replaced by i160s,
+// copying other parts of aggregates as needed. In the case of a store, each
+// pointer is `ptrtoint`d to i160 before storing, and load integers are
+// `inttoptr`d back. This same transformation is applied to vectors of pointers.
//
// Such a transformation allows the later phases of the pass to not need
// to handle buffer fat pointers moving to and from memory, where we load
@@ -66,6 +66,10 @@
// Atomics operations on `ptr addrspace(7)` values are not suppported, as the
// hardware does not include a 160-bit atomic.
//
+// In order to save on O(N) work and to ensure that the contents type
+// legalizer correctly splits up wide loads, also unconditionally lower
+// memcpy-like intrinsics into loops here.
+//
// ## Buffer contents type legalization
//
// The underlying buffer intrinsics only support types up to 128 bits long,
@@ -231,20 +235,24 @@
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/InstVisitor.h"
#include "llvm/IR/Instructions.h"
+#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/IntrinsicsAMDGPU.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Operator.h"
#include "llvm/IR/PatternMatch.h"
#include "llvm/IR/ReplaceConstant.h"
+#include "llvm/IR/ValueHandle.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
+#include "llvm/Support/AMDGPUAddrSpace.h"
#include "llvm/Support/Alignment.h"
#include "llvm/Support/AtomicOrdering.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Transforms/Utils/Cloning.h"
#include "llvm/Transforms/Utils/Local.h"
+#include "llvm/Transforms/Utils/LowerMemIntrinsics.h"
#include "llvm/Transforms/Utils/ValueMapper.h"
#define DEBUG_TYPE "amdgpu-lower-buffer-fat-pointers"
@@ -431,14 +439,16 @@ namespace {
/// marshalling costs when reading or storing these values, but since placing
/// such pointers into memory is an uncommon operation at best, we feel that
/// this cost is acceptable for better performance in the common case.
-class StoreFatPtrsAsIntsVisitor
- : public InstVisitor<StoreFatPtrsAsIntsVisitor, bool> {
+class StoreFatPtrsAsIntsAndExpandMemcpyVisitor
+ : public InstVisitor<StoreFatPtrsAsIntsAndExpandMemcpyVisitor, bool> {
BufferFatPtrToIntTypeMap *TypeMap;
ValueToValueMapTy ConvertedForStore;
IRBuilder<> IRB;
+ const TargetMachine *TM;
+
// Convert all the buffer fat pointers within the input value to inttegers
// so that it can be stored in memory.
Value *fatPtrsToInts(Value *V, Type *From, Type *To, const Twine &Name);
@@ -448,8 +458,10 @@ class StoreFatPtrsAsIntsVisitor
Value *intsToFatPtrs(Value *V, Type *From, Type *To, const Twine &Name);
public:
- StoreFatPtrsAsIntsVisitor(BufferFatPtrToIntTypeMap *TypeMap, LLVMContext &Ctx)
- : TypeMap(TypeMap), IRB(Ctx) {}
+ StoreFatPtrsAsIntsAndExpandMemcpyVisitor(BufferFatPtrToIntTypeMap *TypeMap,
+ LLVMContext &Ctx,
+ const TargetMachine *TM)
+ : TypeMap(TypeMap), IRB(Ctx), TM(TM) {}
bool processFunction(Function &F);
bool visitInstruction(Instruction &I) { return false; }
@@ -457,11 +469,16 @@ class StoreFatPtrsAsIntsVisitor
bool visitLoadInst(LoadInst &LI);
bool visitStoreInst(StoreInst &SI);
bool visitGetElementPtrInst(GetElementPtrInst &I);
+
+ bool visitMemCpyInst(MemCpyInst &MCI);
+ bool visitMemMoveInst(MemMoveInst &MMI);
+ bool visitMemSetInst(MemSetInst &MSI);
+ bool visitMemSetPatternInst(MemSetPatternInst &MSPI);
};
} // namespace
-Value *StoreFatPtrsAsIntsVisitor::fatPtrsToInts(Value *V, Type *From, Type *To,
- const Twine &Name) {
+Value *StoreFatPtrsAsIntsAndExpandMemcpyVisitor::fatPtrsToInts(
+ Value *V, Type *From, Type *To, const Twine &Name) {
if (From == To)
return V;
ValueToValueMapTy::iterator Find = ConvertedForStore.find(V);
@@ -498,8 +515,8 @@ Value *StoreFatPtrsAsIntsVisitor::fatPtrsToInts(Value *V, Type *From, Type *To,
return Ret;
}
-Value *StoreFatPtrsAsIntsVisitor::intsToFatPtrs(Value *V, Type *From, Type *To,
- const Twine &Name) {
+Value *StoreFatPtrsAsIntsAndExpandMemcpyVisitor::intsToFatPtrs(
+ Value *V, Type *From, Type *To, const Twine &Name) {
if (From == To)
return V;
if (isBufferFatPtrOrVector(To)) {
@@ -531,18 +548,25 @@ Value *StoreFatPtrsAsIntsVisitor::intsToFatPtrs(Value *V, Type *From, Type *To,
return Ret;
}
-bool StoreFatPtrsAsIntsVisitor::processFunction(Function &F) {
+bool StoreFatPtrsAsIntsAndExpandMemcpyVisitor::processFunction(Function &F) {
bool Changed = false;
- // The visitors will mutate GEPs and allocas, but will push loads and stores
- // to the worklist to avoid invalidation.
+ // Process memcpy-like instructions after the main iteration because they can
+ // invalidate iterators.
+ SmallVector<WeakTrackingVH> CanBecomeLoops;
for (Instruction &I : make_early_inc_range(instructions(F))) {
- Changed |= visit(I);
+ if (isa<MemTransferInst, MemSetInst, MemSetPatternInst>(I))
+ CanBecomeLoops.push_back(&I);
+ else
+ Changed |= visit(I);
+ }
+ for (WeakTrackingVH VH : make_early_inc_range(CanBecomeLoops)) {
+ Changed |= visit(cast<Instruction>(VH));
}
ConvertedForStore.clear();
return Changed;
}
-bool StoreFatPtrsAsIntsVisitor::visitAllocaInst(AllocaInst &I) {
+bool StoreFatPtrsAsIntsAndExpandMemcpyVisitor::visitAllocaInst(AllocaInst &I) {
Type *Ty = I.getAllocatedType();
Type *NewTy = TypeMap->remapType(Ty);
if (Ty == NewTy)
@@ -551,7 +575,8 @@ bool StoreFatPtrsAsIntsVisitor::visitAllocaInst(AllocaInst &I) {
return true;
}
-bool StoreFatPtrsAsIntsVisitor::visitGetElementPtrInst(GetElementPtrInst &I) {
+bool StoreFatPtrsAsIntsAndExpandMemcpyVisitor::visitGetElementPtrInst(
+ GetElementPtrInst &I) {
Type *Ty = I.getSourceElementType();
Type *NewTy = TypeMap->remapType(Ty);
if (Ty == NewTy)
@@ -563,7 +588,7 @@ bool StoreFatPtrsAsIntsVisitor::visitGetElementPtrInst(GetElementPtrInst &I) {
return true;
}
-bool StoreFatPtrsAsIntsVisitor::visitLoadInst(LoadInst &LI) {
+bool StoreFatPtrsAsIntsAndExpandMemcpyVisitor::visitLoadInst(LoadInst &LI) {
Type *Ty = LI.getType();
Type *IntTy = TypeMap->remapType(Ty);
if (Ty == IntTy)
@@ -581,7 +606,7 @@ bool StoreFatPtrsAsIntsVisitor::visitLoadInst(LoadInst &LI) {
return true;
}
-bool StoreFatPtrsAsIntsVisitor::visitStoreInst(StoreInst &SI) {
+bool StoreFatPtrsAsIntsAndExpandMemcpyVisitor::visitStoreInst(StoreInst &SI) {
Value *V = SI.getValueOperand();
Type *Ty = V->getType();
Type *IntTy = TypeMap->remapType(Ty);
@@ -597,6 +622,47 @@ bool StoreFatPtrsAsIntsVisitor::visitStoreInst(StoreInst &SI) {
return true;
}
+bool StoreFatPtrsAsIntsAndExpandMemcpyVisitor::visitMemCpyInst(
+ MemCpyInst &MCI) {
+ // TODO: Allow memcpy.p7.p3 as a synonym for the direct-to-LDS copy, which'll
+ // need loop expansion here.
+ if (MCI.getSourceAddressSpace() != AMDGPUAS::BUFFER_FAT_POINTER &&
+ MCI.getDestAddressSpace() != AMDGPUAS::BUFFER_FAT_POINTER)
+ return false;
+ llvm::expandMemCpyAsLoop(&MCI,
+ TM->getTargetTransformInfo(*MCI.getFunction()));
+ MCI.eraseFromParent();
+ return true;
+}
+
+bool StoreFatPtrsAsIntsAndExpandMemcpyVisitor::visitMemMoveInst(
+ MemMoveInst &MMI) {
+ if (MMI.getSourceAddressSpace() != AMDGPUAS::BUFFER_FAT_POINTER &&
+ MMI.getDestAddressSpace() != AMDGPUAS::BUFFER_FAT_POINTER)
+ return false;
+ report_fatal_error(
+ "memmove() on buffer descriptors is not implemented because pointer "
+ "comparison on buffer descriptors isn't implemented\n");
+}
+
+bool StoreFatPtrsAsIntsAndExpandMemcpyVisitor::visitMemSetInst(
+ MemSetInst &MSI) {
+ if (MSI.getDestAddressSpace() != AMDGPUAS::BUFFER_FAT_POINTER)
+ return false;
+ llvm::expandMemSetAsLoop(&MSI);
+ MSI.eraseFromParent();
+ return true;
+}
+
+bool StoreFatPtrsAsIntsAndExpandMemcpyVisitor::visitMemSetPatternInst(
+ MemSetPatternInst &MSPI) {
+ if (MSPI.getDestAddressSpace() != AMDGPUAS::BUFFER_FAT_POINTER)
+ return false;
+ llvm::expandMemSetPatternAsLoop(&MSPI);
+ MSPI.eraseFromParent();
+ return true;
+}
+
namespace {
/// Convert loads/stores of types that the buffer intrinsics can't handle into
/// one ore more such loads/stores that consist of legal types.
@@ -1127,6 +1193,7 @@ bool LegalizeBufferContentTypesVisitor::visitStoreInst(StoreInst &SI) {
bool LegalizeBufferContentTypesVisitor::processFunction(Function &F) {
bool Changed = false;
+ // Note, memory transfer intrinsics won't
for (Instruction &I : make_early_inc_range(instructions(F))) {
Changed |= visit(I);
}
@@ -2072,6 +2139,12 @@ static bool isRemovablePointerIntrinsic(Intrinsic::ID IID) {
case Intrinsic::invariant_end:
case Intrinsic::launder_invariant_group:
case Intrinsic::strip_invariant_group:
+ case Intrinsic::memcpy:
+ case Intrinsic::memcpy_inline:
+ case Intrinsic::memmove:
+ case Intrinsic::memset:
+ case Intrinsic::memset_inline:
+ case Intrinsic::experimental_memset_pattern:
return true;
}
}
@@ -2322,7 +2395,8 @@ bool AMDGPULowerBufferFatPointers::run(Module &M, const TargetMachine &TM) {
/*RemoveDeadConstants=*/false, /*IncludeSelf=*/true);
}
- StoreFatPtrsAsIntsVisitor MemOpsRewrite(&IntTM, M.getContext());
+ StoreFatPtrsAsIntsAndExpandMemcpyVisitor MemOpsRewrite(&IntTM, M.getContext(),
+ &TM);
LegalizeBufferContentTypesVisitor BufferContentsTypeRewrite(DL,
M.getContext());
for (Function &F : M.functions()) {
diff --git a/llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-mem-transfer.ll b/llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-mem-transfer.ll
new file mode 100644
index 000000000000000..e6c2d1907068f52
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-mem-transfer.ll
@@ -0,0 +1,1730 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S -mcpu=gfx900 -amdgpu-lower-buffer-fat-pointers < %s | FileCheck %s
+; RUN: opt -S -mcpu=gfx900 -passes=amdgpu-lower-buffer-fat-pointers < %s | FileCheck %s
+
+target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-p7:160:256:256:32-p8:128:128-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5-G1-ni:7:8"
+target triple = "amdgcn--"
+
+;; memcpy
+
+declare void @llvm.memcpy.p7.p7.i32(ptr addrspace(7), ptr addrspace(7), i32, i1)
+declare void @llvm.memcpy.p1.p7.i32(ptr addrspace(1), ptr addrspace(7), i32, i1)
+declare void @llvm.memcpy.p7.p1.i32(ptr addrspace(7), ptr addrspace(1), i32, i1)
+declare void @llvm.memcpy.p7.p7.i64(ptr addrspace(7), ptr addrspace(7), i64, i1)
+declare void @llvm.memcpy.p3.p7.i32(ptr addrspace(3), ptr addrspace(7), i32, i1)
+
+define void @memcpy_known(ptr addrspace(7) inreg %src, ptr addrspace(7) inreg %dst) {
+; CHECK-LABEL: define void @memcpy_known(
+; CHECK-SAME: { ptr addrspace(8), i32 } inreg [[SRC:%.*]], { ptr addrspace(8), i32 } inreg [[DST:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: [[DST_RSRC:%.*]] = extractvalue { ptr addrspace(8), i32 } [[DST]], 0
+; CHECK-NEXT: [[DST_OFF:%.*]] = extractvalue { ptr addrspace(8), i32 } [[DST]], 1
+; CHECK-NEXT: [[SRC_RSRC:%.*]] = extractvalue { ptr addrspace(8), i32 } [[SRC]], 0
+; CHECK-NEXT: [[SRC_OFF:%.*]] = extractvalue { ptr addrspace(8), i32 } [[SRC]], 1
+; CHECK-NEXT: br label %[[LOAD_STORE_LOOP:.*]]
+; CHECK: [[LOAD_STORE_LOOP]]:
+; CHECK-NEXT: [[LOOP_INDEX:%.*]] = phi i32 [ 0, [[TMP0:%.*]] ], [ [[TMP4:%.*]], %[[LOAD_STORE_LOOP]] ]
+; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[SRC_OFF]], [[LOOP_INDEX]]
+; CHECK-NEXT: [[DOTOFF_0:%.*]] = call <4 x i32> @llvm.amdgcn.raw.ptr.buffer.load.v4i32(ptr addrspace(8) align 16 [[SRC_RSRC]], i32 [[TMP1]], i32 0, i32 0)
+; CHECK-NEXT: [[DOTEXT_0:%.*]] = shufflevector <4 x i32> [[DOTOFF_0]], <4 x i32> poison, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[DOTPARTS_0:%.*]] = shufflevector <64 x i32> poison, <64 x i32> [[DOTEXT_0]], <64 x i32> <i32 64, i32 65, i32 66, i32 67, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
+; CHECK-NEXT: [[DOTOFF_PTR_16:%.*]] = add nuw i32 [[TMP1]], 16
+; CHECK-NEXT: [[DOTOFF_16:%.*]] = call <4 x i32> @llvm.amdgcn.raw.ptr.buffer.load.v4i32(ptr addrspace(8) align 16 [[SRC_RSRC]], i32 [[DOTOFF_PTR_16]], i32 0, i32 0)
+; CHECK-NEXT: [[DOTEXT_4:%.*]] = shufflevector <4 x i32> [[DOTOFF_16]], <4 x i32> poison, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[DOTPARTS_4:%.*]] = shufflevector <64 x i32> [[DOTPARTS_0]], <64 x i32> [[DOTEXT_4]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 64, i32 65, i32 66, i32 67, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
+; CHECK-NEXT: [[DOTOFF_PTR_32:%.*]] = add nuw i32 [[TMP1]], 32
+; CHECK-NEXT: [[DOTOFF_32:%.*]] = call <4 x i32> @llvm.amdgcn.raw.ptr.buffer.load.v4i32(ptr addrspace(8) align 16 [[SRC_RSRC]], i32 [[DOTOFF_PTR_32]], i32 0, i32 0)
+; CHECK-NEXT: [[DOTEXT_8:%.*]] = shufflevector <4 x i32> [[DOTOFF_32]], <4 x i32> poison, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[DOTPARTS_8:%.*]] = shufflevector <64 x i32> [[DOTPARTS_4]], <64 x i32> [[DOTEXT_8]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 64, i32 65, i32 66, i32 67, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
+; CHECK-NEXT: [[DOTOFF_PTR_48:%.*]] = add nuw i32 [[TMP1]], 48
+; CHECK-NEXT: [[DOTOFF_48:%.*]] = call <4 x i32> @llvm.amdgcn.raw.ptr.buffer.load.v4i32(ptr addrspace(8) align 16 [[SRC_RSRC]], i32 [[DOTOFF_PTR_48]], i32 0, i32 0)
+; CHECK-NEXT: [[DOTEXT_12:%.*]] = shufflevector <4 x i32> [[DOTOFF_48]], <4 x i32> poison, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[DOTPARTS_12:%.*]] = shufflevector <64 x i32> [[DOTPARTS_8]], <64 x i32> [[DOTEXT_12]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 64, i32 65, i32 66, i32 67, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
+; CHECK-NEXT: [[DOTOFF_PTR_64:%.*]] = add nuw i32 [[TMP1]], 64
+; CHECK-NEXT: [[DOTOFF_64:%.*]] = call <4 x i32> @llvm.amdgcn.raw.ptr.buffer.load.v4i32(ptr addrspace(8) align 16 [[SRC_RSRC]], i32 [[DOTOFF_PTR_64]], i32 0, i32 0)
+; CHECK-NEXT: [[DOTEXT_16:%.*]] = shufflevector <4 x i32> [[DOTOFF_64]], <4 x i32> poison, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 pois...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/126621
More information about the llvm-commits
mailing list