Skip to content
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

[AutoBump] Merge with bddd8eae (Jun 10) (64) #327

Merged
merged 6 commits into from
Sep 11, 2024
Merged

[AutoBump] Merge with bddd8eae (Jun 10) (64) #327

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
5c268cf
[Clang] Extend EmitPseudoVariable to support debug records (#94956)
SLTozer Jun 10, 2024
d319fc4
[mlir][ArmSME] Add option to only enable streaming mode for scalable …
MacDue Jun 10, 2024
18ec885
[RFC][AMDGPU] Remove old llvm.amdgcn.buffer.* and tbuffer intrinsics …
jayfoad Jun 10, 2024
bc022b4
[AMDGPU] Support SIProgramInfo MCExpr for comments and remarks (#94350)
JanekvO Jun 10, 2024
bddd8ea
Revert "[scudo] Apply filling when realloc shrinks and re-grows a blo…
fabio-d Jun 10, 2024
ce1bf2b
[AutoBump] Merge with bddd8eae (Jun 10)
jorickert Sep 5, 2024
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
32 changes: 10 additions & 22 deletions clang/lib/CodeGen/CGDebugInfo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5766,28 +5766,16 @@ void CGDebugInfo::EmitPseudoVariable(CGBuilderTy &Builder,
// it is loaded upon use, so we identify such pattern here.
if (llvm::LoadInst *Load = dyn_cast<llvm::LoadInst>(Value)) {
llvm::Value *Var = Load->getPointerOperand();
if (llvm::Metadata *MDValue = llvm::ValueAsMetadata::getIfExists(Var)) {
if (llvm::Value *DbgValue = llvm::MetadataAsValue::getIfExists(
CGM.getLLVMContext(), MDValue)) {
for (llvm::User *U : DbgValue->users()) {
if (llvm::CallInst *DbgDeclare = dyn_cast<llvm::CallInst>(U)) {
if (DbgDeclare->getCalledFunction()->getIntrinsicID() ==
llvm::Intrinsic::dbg_declare &&
DbgDeclare->getArgOperand(0) == DbgValue) {
// There can be implicit type cast applied on a variable if it is
// an opaque ptr, in this case its debug info may not match the
// actual type of object being used as in the next instruction, so
// we will need to emit a pseudo variable for type-casted value.
llvm::DILocalVariable *MDNode = cast<llvm::DILocalVariable>(
cast<llvm::MetadataAsValue>(DbgDeclare->getOperand(1))
->getMetadata());
if (MDNode->getType() == Type)
return;
}
}
}
}
}
// There can be implicit type cast applied on a variable if it is an opaque
// ptr, in this case its debug info may not match the actual type of object
// being used as in the next instruction, so we will need to emit a pseudo
// variable for type-casted value.
auto DeclareTypeMatches = [&](auto *DbgDeclare) {
return DbgDeclare->getVariable()->getType() == Type;
};
if (any_of(llvm::findDbgDeclares(Var), DeclareTypeMatches) ||
any_of(llvm::findDVRDeclares(Var), DeclareTypeMatches))
return;
}

// Find the correct location to insert a sequence of instructions to
Expand Down
14 changes: 0 additions & 14 deletions compiler-rt/lib/scudo/standalone/combined.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -565,20 +565,6 @@ class Allocator {
storeSecondaryAllocationStackMaybe(Options, OldPtr, NewSize);
}
}

// If we have reduced the size, set the extra bytes to the fill value
// so that we are ready to grow it again in the future.
if (NewSize < OldSize) {
const FillContentsMode FillContents =
TSDRegistry.getDisableMemInit() ? NoFill
: Options.getFillContentsMode();
if (FillContents != NoFill) {
memset(reinterpret_cast<char *>(OldTaggedPtr) + NewSize,
FillContents == ZeroFill ? 0 : PatternFillByte,
OldSize - NewSize);
}
}

return OldTaggedPtr;
}
}
Expand Down
23 changes: 5 additions & 18 deletions compiler-rt/lib/scudo/standalone/tests/combined_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -447,32 +447,19 @@ SCUDO_TYPED_TEST(ScudoCombinedDeathTest, ReallocateSame) {
// returns the same chunk. This requires that all the sizes we iterate on use
// the same block size, but that should be the case for MaxSize - 64 with our
// default class size maps.
constexpr scudo::uptr InitialSize =
constexpr scudo::uptr ReallocSize =
TypeParam::Primary::SizeClassMap::MaxSize - 64;
void *P = Allocator->allocate(ReallocSize, Origin);
const char Marker = 'A';
Allocator->setFillContents(scudo::PatternOrZeroFill);

void *P = Allocator->allocate(InitialSize, Origin);
scudo::uptr CurrentSize = InitialSize;
memset(P, Marker, ReallocSize);
for (scudo::sptr Delta = -32; Delta < 32; Delta += 8) {
memset(P, Marker, CurrentSize);
const scudo::uptr NewSize =
static_cast<scudo::uptr>(static_cast<scudo::sptr>(InitialSize) + Delta);
static_cast<scudo::uptr>(static_cast<scudo::sptr>(ReallocSize) + Delta);
void *NewP = Allocator->reallocate(P, NewSize);
EXPECT_EQ(NewP, P);

// Verify that existing contents have been preserved.
for (scudo::uptr I = 0; I < scudo::Min(CurrentSize, NewSize); I++)
for (scudo::uptr I = 0; I < ReallocSize - 32; I++)
EXPECT_EQ((reinterpret_cast<char *>(NewP))[I], Marker);

// Verify that new bytes are set according to FillContentsMode.
for (scudo::uptr I = CurrentSize; I < NewSize; I++) {
EXPECT_EQ((reinterpret_cast<unsigned char *>(NewP))[I],
scudo::PatternFillByte);
}

checkMemoryTaggingMaybe(Allocator, NewP, NewSize, 0);
CurrentSize = NewSize;
}
Allocator->deallocate(P, Origin);
}
Expand Down
2 changes: 1 addition & 1 deletion llvm/docs/TableGen/BackGuide.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -761,7 +761,7 @@ over time. The output looks like this.

-------------------- Global Variables (5) --------------------

AMDGPUBufferIntrinsics = [int_amdgcn_buffer_load_format, ...
AMDGPUBufferIntrinsics = [int_amdgcn_s_buffer_load, ...
AMDGPUImageDimAtomicIntrinsics = [int_amdgcn_image_atomic_swap_1d, ...
...
-------------------- Classes (758) --------------------
Expand Down
110 changes: 3 additions & 107 deletions llvm/include/llvm/IR/IntrinsicsAMDGPU.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1083,18 +1083,6 @@ def int_amdgcn_make_buffer_rsrc : DefaultAttrsIntrinsic <

defset list<AMDGPURsrcIntrinsic> AMDGPUBufferIntrinsics = {

class AMDGPUBufferLoad<LLVMType data_ty = llvm_any_ty> : DefaultAttrsIntrinsic <
[data_ty],
[llvm_v4i32_ty, // rsrc(SGPR)
llvm_i32_ty, // vindex(VGPR)
llvm_i32_ty, // offset(SGPR/VGPR/imm)
llvm_i1_ty, // glc(imm)
llvm_i1_ty], // slc(imm)
[IntrReadMem, ImmArg<ArgIndex<3>>, ImmArg<ArgIndex<4>>], "", [SDNPMemOperand]>,
AMDGPURsrcIntrinsic<0>;
def int_amdgcn_buffer_load_format : AMDGPUBufferLoad<llvm_anyfloat_ty>;
def int_amdgcn_buffer_load : AMDGPUBufferLoad;

// Generate a buffer_load instruction that may be optimized to s_buffer_load if
// the offset argument is uniform.
def int_amdgcn_s_buffer_load : DefaultAttrsIntrinsic <
Expand All @@ -1111,25 +1099,12 @@ def int_amdgcn_s_buffer_load : DefaultAttrsIntrinsic <
[IntrNoMem, ImmArg<ArgIndex<2>>]>,
AMDGPURsrcIntrinsic<0>;

class AMDGPUBufferStore<LLVMType data_ty = llvm_any_ty> : DefaultAttrsIntrinsic <
[],
[data_ty, // vdata(VGPR)
llvm_v4i32_ty, // rsrc(SGPR)
llvm_i32_ty, // vindex(VGPR)
llvm_i32_ty, // offset(SGPR/VGPR/imm)
llvm_i1_ty, // glc(imm)
llvm_i1_ty], // slc(imm)
[IntrWriteMem, ImmArg<ArgIndex<4>>, ImmArg<ArgIndex<5>>], "", [SDNPMemOperand]>,
AMDGPURsrcIntrinsic<1>;
def int_amdgcn_buffer_store_format : AMDGPUBufferStore<llvm_anyfloat_ty>;
def int_amdgcn_buffer_store : AMDGPUBufferStore;

// New buffer intrinsics with separate raw and struct variants. The raw
// Buffer intrinsics with separate raw and struct variants. The raw
// variant never has an index. The struct variant always has an index, even if
// it is const 0. A struct intrinsic with constant 0 index is different to the
// corresponding raw intrinsic on gfx9+ because the behavior of bound checking
// and swizzling changes depending on whether idxen is set in the instruction.
// These new instrinsics also keep the offset and soffset arguments separate as
// These instrinsics also keep the offset and soffset arguments separate as
// they behave differently in bounds checking and swizzling.

// The versions of these intrinsics that take <4 x i32> arguments are deprecated
Expand Down Expand Up @@ -1489,41 +1464,7 @@ def int_amdgcn_struct_buffer_atomic_fmax : AMDGPUStructBufferAtomic<llvm_anyfloa
def int_amdgcn_struct_ptr_buffer_atomic_fmin : AMDGPUStructPtrBufferAtomic<llvm_anyfloat_ty>;
def int_amdgcn_struct_ptr_buffer_atomic_fmax : AMDGPUStructPtrBufferAtomic<llvm_anyfloat_ty>;

// Obsolescent tbuffer intrinsics.
def int_amdgcn_tbuffer_load : DefaultAttrsIntrinsic <
[llvm_any_ty], // overloaded for types f32/i32, v2f32/v2i32, v4f32/v4i32
[llvm_v4i32_ty, // rsrc(SGPR)
llvm_i32_ty, // vindex(VGPR)
llvm_i32_ty, // voffset(VGPR)
llvm_i32_ty, // soffset(SGPR)
llvm_i32_ty, // offset(imm)
llvm_i32_ty, // dfmt(imm)
llvm_i32_ty, // nfmt(imm)
llvm_i1_ty, // glc(imm)
llvm_i1_ty], // slc(imm)
[IntrReadMem,
ImmArg<ArgIndex<4>>, ImmArg<ArgIndex<5>>, ImmArg<ArgIndex<6>>,
ImmArg<ArgIndex<7>>, ImmArg<ArgIndex<8>>], "", [SDNPMemOperand]>,
AMDGPURsrcIntrinsic<0>;

def int_amdgcn_tbuffer_store : DefaultAttrsIntrinsic <
[],
[llvm_any_ty, // vdata(VGPR), overloaded for types f32/i32, v2f32/v2i32, v4f32/v4i32
llvm_v4i32_ty, // rsrc(SGPR)
llvm_i32_ty, // vindex(VGPR)
llvm_i32_ty, // voffset(VGPR)
llvm_i32_ty, // soffset(SGPR)
llvm_i32_ty, // offset(imm)
llvm_i32_ty, // dfmt(imm)
llvm_i32_ty, // nfmt(imm)
llvm_i1_ty, // glc(imm)
llvm_i1_ty], // slc(imm)
[IntrWriteMem, ImmArg<ArgIndex<5>>,
ImmArg<ArgIndex<6>>, ImmArg<ArgIndex<7>>,
ImmArg<ArgIndex<8>>, ImmArg<ArgIndex<9>>], "", [SDNPMemOperand]>,
AMDGPURsrcIntrinsic<1>;

// New tbuffer intrinsics, with:
// tbuffer intrinsics, with:
// - raw and struct variants
// - joint format field
// - joint cachepolicy field
Expand Down Expand Up @@ -1670,51 +1611,6 @@ def int_amdgcn_struct_tbuffer_store : DefaultAttrsIntrinsic <
ImmArg<ArgIndex<5>>, ImmArg<ArgIndex<6>>], "", [SDNPMemOperand]>,
AMDGPURsrcIntrinsic<1>;

class AMDGPUBufferAtomic : Intrinsic <
[llvm_anyint_ty],
[LLVMMatchType<0>, // vdata(VGPR)
llvm_v4i32_ty, // rsrc(SGPR)
llvm_i32_ty, // vindex(VGPR)
llvm_i32_ty, // offset(SGPR/VGPR/imm)
llvm_i1_ty], // slc(imm)
[ImmArg<ArgIndex<4>>, IntrWillReturn, IntrNoCallback, IntrNoFree], "", [SDNPMemOperand]>,
AMDGPURsrcIntrinsic<1, 0>;
def int_amdgcn_buffer_atomic_swap : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_add : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_sub : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_smin : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_umin : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_smax : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_umax : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_and : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_or : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_xor : AMDGPUBufferAtomic;
def int_amdgcn_buffer_atomic_cmpswap : Intrinsic<
[llvm_i32_ty],
[llvm_i32_ty, // src(VGPR)
llvm_i32_ty, // cmp(VGPR)
llvm_v4i32_ty, // rsrc(SGPR)
llvm_i32_ty, // vindex(VGPR)
llvm_i32_ty, // offset(SGPR/VGPR/imm)
llvm_i1_ty], // slc(imm)
[ImmArg<ArgIndex<5>>, IntrWillReturn, IntrNoCallback, IntrNoFree], "", [SDNPMemOperand]>,
AMDGPURsrcIntrinsic<2, 0>;

def int_amdgcn_buffer_atomic_csub : AMDGPUBufferAtomic;

class AMDGPUBufferAtomicFP : Intrinsic <
[llvm_anyfloat_ty],
[LLVMMatchType<0>, // vdata(VGPR)
llvm_v4i32_ty, // rsrc(SGPR)
llvm_i32_ty, // vindex(VGPR)
llvm_i32_ty, // offset(SGPR/VGPR/imm)
llvm_i1_ty], // slc(imm)
[ImmArg<ArgIndex<4>>, IntrWillReturn, IntrNoCallback, IntrNoFree], "", [SDNPMemOperand]>,
AMDGPURsrcIntrinsic<1, 0>;

// Legacy form of the intrinsic. raw and struct forms should be preferred.
def int_amdgcn_buffer_atomic_fadd : AMDGPUBufferAtomicFP;

class AMDGPURawBufferLoadLDS : Intrinsic <
[],
[llvm_v4i32_ty, // rsrc(SGPR)
Expand Down
Loading