@@ -167,6 +167,10 @@ def FeatureCuMode : SubtargetFeature<"cumode",
"Enable CU wavefront execution mode"
>;
+def FeaturePreciseMemory
jwanggit86 wrote:
Thanks for the suggestion. It looks it would work. However, I'm not sure the
extra overhead is worth it
@@ -603,14 +626,69 @@ class SIGfx12CacheControl : public SIGfx11CacheControl {
SIAtomicAddrSpace AddrSpace, SIMemOp Op,
bool IsVolatile,
bool IsNonTemporal) const o
@@ -603,14 +626,69 @@ class SIGfx12CacheControl : public SIGfx11CacheControl {
SIAtomicAddrSpace AddrSpace, SIMemOp Op,
bool IsVolatile,
bool IsNonTemporal) const o
@@ -603,14 +626,69 @@ class SIGfx12CacheControl : public SIGfx11CacheControl {
SIAtomicAddrSpace AddrSpace, SIMemOp Op,
bool IsVolatile,
bool IsNonTemporal) const o
https://github.com/jwanggit86 updated
https://github.com/llvm/llvm-project/pull/79236
>From 9c40b1151b0673430ff53eb121784724a5b090e5 Mon Sep 17 00:00:00 2001
From: Jun Wang
Date: Tue, 23 Jan 2024 19:19:00 -0600
Subject: [PATCH 1/5] [AMDGPU] Emit a waitcnt instruction after each memory
instruct
https://github.com/jwanggit86 updated
https://github.com/llvm/llvm-project/pull/79236
>From 9c40b1151b0673430ff53eb121784724a5b090e5 Mon Sep 17 00:00:00 2001
From: Jun Wang
Date: Tue, 23 Jan 2024 19:19:00 -0600
Subject: [PATCH 1/6] [AMDGPU] Emit a waitcnt instruction after each memory
instruct
@@ -603,14 +626,69 @@ class SIGfx12CacheControl : public SIGfx11CacheControl {
SIAtomicAddrSpace AddrSpace, SIMemOp Op,
bool IsVolatile,
bool IsNonTemporal) const o
@@ -2378,6 +2456,221 @@ bool
SIGfx12CacheControl::enableVolatileAndOrNonTemporal(
return Changed;
}
+bool SIGfx6CacheControl ::handleNonAtomicForPreciseMemory(
+MachineBasicBlock::iterator &MI) {
+ assert(MI->mayLoadOrStore());
+
+ MachineInstr &Inst = *MI;
+ AMDGPU:
@@ -2378,6 +2456,221 @@ bool
SIGfx12CacheControl::enableVolatileAndOrNonTemporal(
return Changed;
}
+bool SIGfx6CacheControl ::handleNonAtomicForPreciseMemory(
+MachineBasicBlock::iterator &MI) {
+ assert(MI->mayLoadOrStore());
+
+ MachineInstr &Inst = *MI;
+ AMDGPU:
https://github.com/jwanggit86 edited
https://github.com/llvm/llvm-project/pull/79236
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -356,6 +356,19 @@ void AMDGPUTargetCodeGenInfo::setFunctionDeclAttributes(
if (NumVGPR != 0)
F->addFnAttr("amdgpu-num-vgpr", llvm::utostr(NumVGPR));
}
+
+ if (const auto *Attr = FD->getAttr()) {
+uint32_t X = Attr->getNumWorkGroupsX();
+uint32_t Y = Attr
https://github.com/jwanggit86 updated
https://github.com/llvm/llvm-project/pull/79035
>From 5c088a59bd36df40bae9a3a712f3994feded359d Mon Sep 17 00:00:00 2001
From: Jun Wang
Date: Mon, 22 Jan 2024 12:43:27 -0600
Subject: [PATCH 1/5] [AMDGPU] Adding the amdgpu-num-work-groups function
attribute
https://github.com/jwanggit86 updated
https://github.com/llvm/llvm-project/pull/79035
>From 5c088a59bd36df40bae9a3a712f3994feded359d Mon Sep 17 00:00:00 2001
From: Jun Wang
Date: Mon, 22 Jan 2024 12:43:27 -0600
Subject: [PATCH 1/6] [AMDGPU] Adding the amdgpu-num-work-groups function
attribute
@@ -1108,3 +1108,8 @@ void
GCNUserSGPRUsageInfo::allocKernargPreloadSGPRs(unsigned NumSGPRs) {
unsigned GCNUserSGPRUsageInfo::getNumFreeUserSGPRs() {
return AMDGPU::getMaxNumUserSGPRs(ST) - NumUsedUserSGPRs;
}
+
+SmallVector
jwanggit86 wrote:
This function
@@ -8069,6 +8069,25 @@ static void handleAMDGPUNumVGPRAttr(Sema &S, Decl *D,
const ParsedAttr &AL) {
D->addAttr(::new (S.Context) AMDGPUNumVGPRAttr(S.Context, AL, NumVGPR));
}
+static void handleAMDGPUNumWorkGroupsAttr(Sema &S, Decl *D,
+
@@ -2031,6 +2031,13 @@ def AMDGPUNumVGPR : InheritableAttr {
let Subjects = SubjectList<[Function], ErrorDiag, "kernel functions">;
}
+def AMDGPUNumWorkGroups : InheritableAttr {
+ let Spellings = [Clang<"amdgpu_num_work_groups", 0>];
+ let Args = [UnsignedArgument<"NumWor
@@ -2705,6 +2705,30 @@ An error will be given if:
}];
}
+def AMDGPUNumWorkGroupsDocs : Documentation {
+ let Category = DocCatAMDGPUAttributes;
+ let Content = [{
+The number of work groups specifies the number of work groups when the kernel
+is dispatched.
+
+Clang suppor
@@ -2705,6 +2705,30 @@ An error will be given if:
}];
}
+def AMDGPUNumWorkGroupsDocs : Documentation {
+ let Category = DocCatAMDGPUAttributes;
+ let Content = [{
+The number of work groups specifies the number of work groups when the kernel
+is dispatched.
+
+Clang suppor
@@ -2705,6 +2705,30 @@ An error will be given if:
}];
}
+def AMDGPUNumWorkGroupsDocs : Documentation {
+ let Category = DocCatAMDGPUAttributes;
+ let Content = [{
+The number of work groups specifies the number of work groups when the kernel
+is dispatched.
+
+Clang suppor
@@ -2705,6 +2705,30 @@ An error will be given if:
}];
}
+def AMDGPUNumWorkGroupsDocs : Documentation {
+ let Category = DocCatAMDGPUAttributes;
+ let Content = [{
+The number of work groups specifies the number of work groups when the kernel
jwanggit86 wro
@@ -0,0 +1,84 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s
| FileCheck %s
jwanggit86 wrote:
Removed.
https://github.com/llvm/llvm-project/pull/79035
___
cfe-commits mailing list
cf
@@ -356,6 +356,19 @@ void AMDGPUTargetCodeGenInfo::setFunctionDeclAttributes(
if (NumVGPR != 0)
F->addFnAttr("amdgpu-num-vgpr", llvm::utostr(NumVGPR));
}
+
+ if (const auto *Attr = FD->getAttr()) {
+uint32_t X = Attr->getNumWorkGroupsX();
+uint32_t Y = Attr
@@ -2031,6 +2031,13 @@ def AMDGPUNumVGPR : InheritableAttr {
let Subjects = SubjectList<[Function], ErrorDiag, "kernel functions">;
}
+def AMDGPUNumWorkGroups : InheritableAttr {
+ let Spellings = [Clang<"amdgpu_num_work_groups", 0>];
jwanggit86 wrote:
Cha
https://github.com/jwanggit86 updated
https://github.com/llvm/llvm-project/pull/79035
>From 5c088a59bd36df40bae9a3a712f3994feded359d Mon Sep 17 00:00:00 2001
From: Jun Wang
Date: Mon, 22 Jan 2024 12:43:27 -0600
Subject: [PATCH 1/7] [AMDGPU] Adding the amdgpu-num-work-groups function
attribute
jwanggit86 wrote:
> Did you try to move this to SIInsertWaitCnt, as suggested?
> Did you try to move this to SIInsertWaitCnt, as suggested?
Pls see my reply on Feb 15, which is copy-pasted below.
Regarding the question about SIInsertWaitcnt, initially the code was indeed put
there (see PR h
@@ -355,6 +356,18 @@ class SICacheControl {
MachineBasicBlock::iterator &MI) const {
return false;
}
+
+public:
+ // The following is for supporting precise memory mode. When the option
+ // amdgpu-precise-memory is enabled, an s_waitc
@@ -167,6 +167,10 @@ def FeatureCuMode : SubtargetFeature<"cumode",
"Enable CU wavefront execution mode"
>;
+def FeaturePreciseMemory
jwanggit86 wrote:
The function `hasFlag()` actually appears to be pretty expensive, and it's
going to be called every time
https://github.com/jwanggit86 edited
https://github.com/llvm/llvm-project/pull/79236
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -8069,6 +8069,26 @@ static void handleAMDGPUNumVGPRAttr(Sema &S, Decl *D,
const ParsedAttr &AL) {
D->addAttr(::new (S.Context) AMDGPUNumVGPRAttr(S.Context, AL, NumVGPR));
}
+static void handleAMDGPUMaxNumWorkGroupsAttr(Sema &S, Decl *D,
+
@@ -167,6 +167,10 @@ def FeatureCuMode : SubtargetFeature<"cumode",
"Enable CU wavefront execution mode"
>;
+def FeaturePreciseMemory
jwanggit86 wrote:
@Pierre-vh With the suggested change, the func `getAMDGPUTargetFeatures` looks
something like the follow
https://github.com/jwanggit86 edited
https://github.com/llvm/llvm-project/pull/79236
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -167,6 +167,10 @@ def FeatureCuMode : SubtargetFeature<"cumode",
"Enable CU wavefront execution mode"
>;
+def FeaturePreciseMemory
jwanggit86 wrote:
A possible fix is to check `hasFlag` after calling `handleTargetFeaturesGroup`,
and if the check is true
https://github.com/jwanggit86 edited
https://github.com/llvm/llvm-project/pull/79236
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/jwanggit86 updated
https://github.com/llvm/llvm-project/pull/79236
>From 9c40b1151b0673430ff53eb121784724a5b090e5 Mon Sep 17 00:00:00 2001
From: Jun Wang
Date: Tue, 23 Jan 2024 19:19:00 -0600
Subject: [PATCH 1/7] [AMDGPU] Emit a waitcnt instruction after each memory
instruct
@@ -167,6 +167,10 @@ def FeatureCuMode : SubtargetFeature<"cumode",
"Enable CU wavefront execution mode"
>;
+def FeaturePreciseMemory
jwanggit86 wrote:
Thanks! This works. Code has been updated. Pls take a look.
https://github.com/llvm/llvm-project/pull/79
jwanggit86 wrote:
> Also note, this is missing Clang lit tests, and doesn't seem to be correctly
> handling dependent expressions for x,y, and z.
What does it mean to "handle dependent expressions for x,y, and z"? Thanks!
https://github.com/llvm/llvm-project/pull/79035
jwanggit86 wrote:
Thanks for explaining the "dependent exp". At present, template arguments are
not required for the attribute. In other words, only int constants are
supported. Diagnostics and test cases have been updated.
https://github.com/llvm/llvm-project/pull/79035
__
@@ -1054,12 +1054,6 @@ GCNUserSGPRUsageInfo::GCNUserSGPRUsageInfo(const
Function &F,
const CallingConv::ID CC = F.getCallingConv();
const bool IsKernel =
CC == CallingConv::AMDGPU_KERNEL || CC == CallingConv::SPIR_KERNEL;
- // FIXME: Should have analysis or somethin
@@ -677,6 +687,36 @@ struct AAAMDAttributesFunction : public AAAMDAttributes {
return !A.checkForAllCallLikeInstructions(DoesNotRetrieve, *this,
UsedAssumedInformation);
}
+
+ // Returns true if FlatScratchInit is needed, i.e
@@ -433,6 +433,13 @@ struct AAAMDAttributesFunction : public AAAMDAttributes {
indicatePessimisticFixpoint();
return;
}
+
+for (Instruction &I : instructions(F)) {
+ if (isa(I) || isa(I)) {
jwanggit86 wrote:
Thanks. This has been updat
jwanggit86 wrote:
Added a testcase that has flat_atomic_swap, which is an atomic without return.
https://github.com/llvm/llvm-project/pull/79236
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe
jwanggit86 wrote:
@jayfoad Do you have any more comments?
https://github.com/llvm/llvm-project/pull/79236
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/jwanggit86 closed
https://github.com/llvm/llvm-project/pull/79236
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -434,6 +434,15 @@ struct AAAMDAttributesFunction : public AAAMDAttributes {
indicatePessimisticFixpoint();
return;
}
+
+for (Instruction &I : instructions(F)) {
+ if (isa(I) &&
jwanggit86 wrote:
This test has been added.
https://gi
@@ -683,6 +706,59 @@ struct AAAMDAttributesFunction : public AAAMDAttributes {
return !A.checkForAllCallLikeInstructions(DoesNotRetrieve, *this,
UsedAssumedInformation);
}
+
+ // Returns true if FlatScratchInit is needed, i.e
@@ -683,6 +706,59 @@ struct AAAMDAttributesFunction : public AAAMDAttributes {
return !A.checkForAllCallLikeInstructions(DoesNotRetrieve, *this,
UsedAssumedInformation);
}
+
+ // Returns true if FlatScratchInit is needed, i.e
@@ -683,6 +706,59 @@ struct AAAMDAttributesFunction : public AAAMDAttributes {
return !A.checkForAllCallLikeInstructions(DoesNotRetrieve, *this,
UsedAssumedInformation);
}
+
+ // Returns true if FlatScratchInit is needed, i.e
@@ -683,6 +706,59 @@ struct AAAMDAttributesFunction : public AAAMDAttributes {
return !A.checkForAllCallLikeInstructions(DoesNotRetrieve, *this,
UsedAssumedInformation);
}
+
+ // Returns true if FlatScratchInit is needed, i.e
https://github.com/jwanggit86 closed
https://github.com/llvm/llvm-project/pull/109223
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
jwanggit86 wrote:
Based off wrong branch.
https://github.com/llvm/llvm-project/pull/109223
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -678,6 +690,37 @@ struct AAAMDAttributesFunction : public AAAMDAttributes {
return !A.checkForAllCallLikeInstructions(DoesNotRetrieve, *this,
UsedAssumedInformation);
}
+
+ // Returns true if FlatScratchInit is needed, i.e
@@ -434,6 +434,15 @@ struct AAAMDAttributesFunction : public AAAMDAttributes {
indicatePessimisticFixpoint();
return;
}
+
+for (Instruction &I : instructions(F)) {
+ if (isa(I) &&
jwanggit86 wrote:
@arsenm Following constants to see if
@@ -434,6 +434,15 @@ struct AAAMDAttributesFunction : public AAAMDAttributes {
indicatePessimisticFixpoint();
return;
}
+
+for (Instruction &I : instructions(F)) {
+ if (isa(I) &&
jwanggit86 wrote:
@arsenm Could you please give me an e
https://github.com/jwanggit86 closed
https://github.com/llvm/llvm-project/pull/94647
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
jwanggit86 wrote:
> Should have the git generated "Reapply..." message with reference to the
> original
I didn't notice that. Do you want me to put "Reapply " in the msg?
https://github.com/llvm/llvm-project/pull/118907
___
cfe-commits mailing list
c
jwanggit86 wrote:
@arsenm @kzhuravl If there are no more comments, I'm going to merge this PR.
https://github.com/llvm/llvm-project/pull/118907
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-
jwanggit86 wrote:
I plan to submit this PR next week by Nov 26. Pls let me know if you have
additional comments.
https://github.com/llvm/llvm-project/pull/94647
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mai
jwanggit86 wrote:
[PR 94647](https://github.com/llvm/llvm-project/pull/94647) was found to cause
build problems after merge with upstream. It has since been reverted by commit
1ef9410a96c1d9669a6feaf03fcab8d0a4a13bd5. This PR fixes the tests that caused
the build problems.
https://github.com/
https://github.com/jwanggit86 edited
https://github.com/llvm/llvm-project/pull/118907
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/jwanggit86 edited
https://github.com/llvm/llvm-project/pull/118907
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/jwanggit86 edited
https://github.com/llvm/llvm-project/pull/118907
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
101 - 161 of 161 matches
Mail list logo
