@@ -285,6 +289,20 @@ void
NVPTXTargetCodeGenInfo::addNVVMMetadata(llvm::GlobalValue *GV,
bool NVPTXTargetCodeGenInfo::shouldEmitStaticExternCAliases() const {
return false;
}
+
+llvm::Constant *
+NVPTXTargetCodeGenInfo::getNullPointer(const CodeGen::CodeGenModule &CGM,
+
@@ -418,8 +418,10 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final :
public TargetInfo {
// value ~0.
uint64_t getNullPointerValue(LangAS AS) const override {
// FIXME: Also should handle region.
-return (AS == LangAS::opencl_local || AS == LangAS::opencl_pr
https://github.com/Naghasan created
https://github.com/llvm/llvm-project/pull/94934
Define __PTX_VERSION__ macro to indicate the used PTX version.
Usually each new PTX version brings a new sm version and the associated
instructions. However, some of these instructions can also be made avialabl
Naghasan wrote:
@Artem-B could you have a look ? I think you are the most relevant for this,
thanks. (Sorry I can't manage assignment)
https://github.com/llvm/llvm-project/pull/94934
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://list
Naghasan wrote:
ping
https://github.com/llvm/llvm-project/pull/94934
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
Naghasan wrote:
Thanks for setting the reviewer
> Can you please include rationale for why this this name e.g. why not
> __NVPTX_VERSION__?
`NVPTX` is the name of the LLVM backend, `PTX` is the name of assembly which
have a version hence `__PTX_VERSION__`. Happy to use a better name, but it i
https://github.com/Naghasan edited
https://github.com/llvm/llvm-project/pull/94934
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
Naghasan wrote:
Still I forgot to answer this point as well...
> Are there ever point releases that might mea +ptx78 should actually expand to
> 780 rather than 78?
not sure what you exactly mean with your question. I guess we can mirror the
cuda arch macro so, major * 100 + minor * 10, no op
@@ -91,6 +97,88 @@ SPIRVTargetMachine::SPIRVTargetMachine(const Target &T,
const Triple &TT,
setRequiresStructuredCFG(false);
}
+enum AddressSpace {
+ Function = storageClassToAddressSpace(SPIRV::StorageClass::Function),
+ CrossWorkgroup =
+ storageClassToAddressSpac
@@ -91,6 +97,88 @@ SPIRVTargetMachine::SPIRVTargetMachine(const Target &T,
const Triple &TT,
setRequiresStructuredCFG(false);
}
+enum AddressSpace {
+ Function = storageClassToAddressSpace(SPIRV::StorageClass::Function),
+ CrossWorkgroup =
+ storageClassToAddressSpac
@@ -92,6 +98,63 @@ SPIRVTargetMachine::SPIRVTargetMachine(const Target &T,
const Triple &TT,
setRequiresStructuredCFG(false);
}
+enum AddressSpace {
+ Function = storageClassToAddressSpace(SPIRV::StorageClass::Function),
+ CrossWorkgroup =
+ storageClassToAddressSpac
@@ -92,6 +98,63 @@ SPIRVTargetMachine::SPIRVTargetMachine(const Target &T,
const Triple &TT,
setRequiresStructuredCFG(false);
}
+enum AddressSpace {
+ Function = storageClassToAddressSpace(SPIRV::StorageClass::Function),
+ CrossWorkgroup =
+ storageClassToAddressSpac
@@ -91,6 +97,88 @@ SPIRVTargetMachine::SPIRVTargetMachine(const Target &T,
const Triple &TT,
setRequiresStructuredCFG(false);
}
+enum AddressSpace {
+ Function = storageClassToAddressSpace(SPIRV::StorageClass::Function),
+ CrossWorkgroup =
+ storageClassToAddressSpac
@@ -91,6 +97,88 @@ SPIRVTargetMachine::SPIRVTargetMachine(const Target &T,
const Triple &TT,
setRequiresStructuredCFG(false);
}
+enum AddressSpace {
+ Function = storageClassToAddressSpace(SPIRV::StorageClass::Function),
+ CrossWorkgroup =
+ storageClassToAddressSpac
@@ -91,6 +97,88 @@ SPIRVTargetMachine::SPIRVTargetMachine(const Target &T,
const Triple &TT,
setRequiresStructuredCFG(false);
}
+enum AddressSpace {
+ Function = storageClassToAddressSpace(SPIRV::StorageClass::Function),
+ CrossWorkgroup =
+ storageClassToAddressSpac
@@ -35,8 +35,10 @@ static constexpr Builtin::Info BuiltinInfos[] = {
static_assert(std::size(BuiltinInfos) == NumBuiltins);
llvm::SmallVector
-SPIRVTargetInfo::getTargetBuiltins() const {
- return {{&BuiltinStrings, BuiltinInfos}};
+BaseSPIRTargetInfo::getTargetBuiltins() con
https://github.com/Naghasan updated
https://github.com/llvm/llvm-project/pull/137805
>From 020a804188b13ef881dcf1cbd81a5e11e4803d62 Mon Sep 17 00:00:00 2001
From: Victor Lomuller
Date: Mon, 28 Apr 2025 16:20:09 +0100
Subject: [PATCH 1/2] [clang][SPIRV] Add builtin for OpGenericCastToPtrExplicit
@@ -33,8 +46,114 @@ static bool CheckAllArgsHaveSameType(Sema *S, CallExpr
*TheCall) {
return false;
}
-bool SemaSPIRV::CheckSPIRVBuiltinFunctionCall(unsigned BuiltinID,
+static std::optional
+processConstant32BitIntArgument(Sema &SemaRef, CallExpr *Call, int Argument) {
+
@@ -97,10 +97,10 @@ static Value *EmitTargetArchBuiltinExpr(CodeGenFunction
*CGF,
case llvm::Triple::riscv64:
return CGF->EmitRISCVBuiltinExpr(BuiltinID, E, ReturnValue);
case llvm::Triple::spirv:
Naghasan wrote:
nope, I fixed it
https://github.com/l
https://github.com/Naghasan created
https://github.com/llvm/llvm-project/pull/137805
The patch introduce __builtin_spirv_generic_cast_to_ptr_explicit which is
lowered to the llvm.spv.generic.cast.to.ptr.explicit intrinsic.
The patch also introduces a new header defining its SPIR-V friendly equ
Naghasan wrote:
Sorry I can't assign reviewers, @JonChesterfield @jhuber6 as you are involved
in gpuintrin.h, I'd welcome feedbacks here (feel free to ping other relevant
persons)
For the SPIR-V side of thing @VyacheslavLevytskyy @farzonl I appreciate your
feedbacks as well :)
FYI @tahoner
https://github.com/Naghasan updated
https://github.com/llvm/llvm-project/pull/137805
>From 90725e8f74295bfd9169e03e73af54c2cf4616ea Mon Sep 17 00:00:00 2001
From: Victor Lomuller
Date: Mon, 28 Apr 2025 16:20:09 +0100
Subject: [PATCH] [clang][SPIRV] Add builtin for OpGenericCastToPtrExplicit and
https://github.com/Naghasan updated
https://github.com/llvm/llvm-project/pull/137805
>From 020a804188b13ef881dcf1cbd81a5e11e4803d62 Mon Sep 17 00:00:00 2001
From: Victor Lomuller
Date: Mon, 28 Apr 2025 16:20:09 +0100
Subject: [PATCH] [clang][SPIRV] Add builtin for OpGenericCastToPtrExplicit and
@@ -35,8 +35,10 @@ static constexpr Builtin::Info BuiltinInfos[] = {
static_assert(std::size(BuiltinInfos) == NumBuiltins);
llvm::SmallVector
-SPIRVTargetInfo::getTargetBuiltins() const {
- return {{&BuiltinStrings, BuiltinInfos}};
+BaseSPIRTargetInfo::getTargetBuiltins() con
@@ -35,8 +35,10 @@ static constexpr Builtin::Info BuiltinInfos[] = {
static_assert(std::size(BuiltinInfos) == NumBuiltins);
llvm::SmallVector
-SPIRVTargetInfo::getTargetBuiltins() const {
- return {{&BuiltinStrings, BuiltinInfos}};
+BaseSPIRTargetInfo::getTargetBuiltins() con
@@ -35,8 +35,10 @@ static constexpr Builtin::Info BuiltinInfos[] = {
static_assert(std::size(BuiltinInfos) == NumBuiltins);
llvm::SmallVector
-SPIRVTargetInfo::getTargetBuiltins() const {
- return {{&BuiltinStrings, BuiltinInfos}};
+BaseSPIRTargetInfo::getTargetBuiltins() con
@@ -5837,12 +5838,13 @@ static void handleBuiltinAliasAttr(Sema &S, Decl *D,
const ParsedAttr &AL) {
bool IsAArch64 = S.Context.getTargetInfo().getTriple().isAArch64();
bool IsARM = S.Context.getTargetInfo().getTriple().isARM();
bool IsRISCV = S.Context.getTargetInfo().g
https://github.com/Naghasan updated
https://github.com/llvm/llvm-project/pull/137805
>From 020a804188b13ef881dcf1cbd81a5e11e4803d62 Mon Sep 17 00:00:00 2001
From: Victor Lomuller
Date: Mon, 28 Apr 2025 16:20:09 +0100
Subject: [PATCH 1/2] [clang][SPIRV] Add builtin for OpGenericCastToPtrExplicit
https://github.com/Naghasan edited
https://github.com/llvm/llvm-project/pull/137805
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -0,0 +1,131 @@
+//===--- SYCL.h -*- C++
-*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM
Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Ap
@@ -0,0 +1,131 @@
+//===--- SYCL.h -*- C++
-*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM
Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Ap
https://github.com/Naghasan updated
https://github.com/llvm/llvm-project/pull/143909
>From 049087b07503add00192211b8ee96bdfebcfeed3 Mon Sep 17 00:00:00 2001
From: Victor Lomuller
Date: Thu, 5 Jun 2025 16:17:10 +0100
Subject: [PATCH] [SPIRV] Add more id and range builtIns
The patch adds intrins
https://github.com/Naghasan ready_for_review
https://github.com/llvm/llvm-project/pull/143909
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/Naghasan created
https://github.com/llvm/llvm-project/pull/143909
The patch adds intrinsics and lowering logic for GlobalSize, GlobalOffset,
SubgroupMaxSize, NumWorkgroups, WorkgroupSize, WorkgroupId, LocalInvocationId,
GlobalInvocationId, SubgroupSize, NumSubgroups, Subgrou
Naghasan wrote:
The advantage of intrinsics is they can be understood better by passes, it also
creates an easier way for passes to introduce them (and less error prone). It's
kinda pedantic TBH and I don't have strong opinions about them (it just feels
cleaner to me). For the frontend side, t
https://github.com/Naghasan converted_to_draft
https://github.com/llvm/llvm-project/pull/143909
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
Naghasan wrote:
Just opened a PR for this https://github.com/llvm/llvm-project/pull/141954
https://github.com/llvm/llvm-project/pull/137805
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-comm
https://github.com/Naghasan created
https://github.com/llvm/llvm-project/pull/141954
Remove unneeded default label which triggers a warning with
-Wcovered-switch-default
>From 5b5bbe5792043881e03db19e9e888bd797052b8e Mon Sep 17 00:00:00 2001
From: Victor Lomuller
Date: Thu, 29 May 2025 15:10:
https://github.com/Naghasan edited
https://github.com/llvm/llvm-project/pull/141954
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/Naghasan edited
https://github.com/llvm/llvm-project/pull/141954
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
Naghasan wrote:
@farzonl @VyacheslavLevytskyy
https://github.com/llvm/llvm-project/pull/141954
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
Naghasan wrote:
Thanks for the background, that helps.
> That said, I'm not completely against having 2 ways to do the same thing in
> the backend if that's really a requirement on your end. Some FE could use
> intrinsics, other the global approach.
Well all could switch to intrinics or none
42 matches
Mail list logo
