Author: James Y Knight
Date: 2024-06-28T01:02:40-04:00
New Revision: a2fb2a16f3d93364b8eaae82db443eb354299158
URL:
https://github.com/llvm/llvm-project/commit/a2fb2a16f3d93364b8eaae82db443eb354299158
DIFF:
https://github.com/llvm/llvm-project/commit/a2fb2a16f3d93364b8eaae82db443eb354299158.diff
Author: Zequan Wu
Date: 2024-06-28T00:36:19-04:00
New Revision: 62d7d5611e70682f8743e7322e34204480ffe189
URL:
https://github.com/llvm/llvm-project/commit/62d7d5611e70682f8743e7322e34204480ffe189
DIFF:
https://github.com/llvm/llvm-project/commit/62d7d5611e70682f8743e7322e34204480ffe189.diff
LOG
@@ -322,24 +306,20 @@ struct hash_state {
}
};
-
-/// A global, fixed seed-override variable.
-///
-/// This variable can be set using the \see llvm::set_fixed_execution_seed
-/// function. See that function for details. Do not, under any circumstances,
-/// set or read this
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/96922
>From 84a2f69e71372891e2721552b10e0105b9430257 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 27 Jun 2024 09:28:22 -0700
Subject: [PATCH 1/2] Updated file headers
Created using spr 1.3.4
---
bolt/inclu
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/96922
>From 84a2f69e71372891e2721552b10e0105b9430257 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 27 Jun 2024 09:28:22 -0700
Subject: [PATCH 1/2] Updated file headers
Created using spr 1.3.4
---
bolt/inclu
https://github.com/efriedma-quic commented:
I think I'm happier restricting the non-determinism to +Asserts for now, at
least as an incremental step.
> Due to Avalanche effects, even a few ASLR bits are sufficient to cover many
> different scenarios and expose latent bugs.
On Windows specific
@@ -322,24 +306,20 @@ struct hash_state {
}
};
-
-/// A global, fixed seed-override variable.
-///
-/// This variable can be set using the \see llvm::set_fixed_execution_seed
-/// function. See that function for details. Do not, under any circumstances,
-/// set or read this
https://github.com/efriedma-quic edited
https://github.com/llvm/llvm-project/pull/96282
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/96596
>From 05d59574d6260b98a469921eb2fccf5398bfafb6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Mon, 24 Jun 2024 23:00:59 -0700
Subject: [PATCH 1/5] Added call to matchWithCallsAsAnchors
Created using spr 1.3.
MaskRay wrote:
https://llvm-compile-time-tracker.com/compare.php?from=abfff89b743584d2796000318198bf60d3622a1f&to=5c2a6b5ba62d2b7ed2c0ad3be29fba8558f5627b&stat=instructions:u
stage2-O3: `instruction:u` change (larger than expected):
|Benchmark|Old|New|
|--- |--- |--- |
|kimwitu++|38847M|38705M
@@ -415,11 +423,116 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
if (!YamlBF.Used && BF && !ProfiledFunctions.count(BF))
matchProfileToFunction(YamlBF, *BF);
+ // Uses name similarity to match functions that were not matched by name.
+ uint64_t Matc
https://github.com/maksfb edited https://github.com/llvm/llvm-project/pull/95884
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
@@ -23,6 +26,11 @@ extern cl::opt Verbosity;
extern cl::OptionCategory BoltOptCategory;
extern cl::opt InferStaleProfile;
+cl::opt NameSimilarityFunctionMatchingThreshold(
+"name-similarity-function-matching-threshold",
+cl::desc("Matches functions using namespace and
@@ -0,0 +1,64 @@
+## Tests function matching in YAMLProfileReader by name similarity.
+
+# REQUIRES: system-linux
+# RUN: split-file %s %t
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown %t/main.s -o %t.o
+# RUN: %clang %cflags %t.o -o %t.exe -Wl,-q -nostdlib
+# RUN:
@@ -0,0 +1,64 @@
+## Tests function matching in YAMLProfileReader by name similarity.
+
+# REQUIRES: system-linux
+# RUN: split-file %s %t
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown %t/main.s -o %t.o
+# RUN: %clang %cflags %t.o -o %t.exe -Wl,-q -nostdlib
+# RUN:
@@ -415,11 +423,116 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
if (!YamlBF.Used && BF && !ProfiledFunctions.count(BF))
matchProfileToFunction(YamlBF, *BF);
+ // Uses name similarity to match functions that were not matched by name.
+ uint64_t Matc
https://github.com/maksfb commented:
Please refactor new code into a separate function. Add a comment on how the
matching is done such that the interface can be understood without reading the
code.
https://github.com/llvm/llvm-project/pull/95884
___
https://github.com/MaskRay updated
https://github.com/llvm/llvm-project/pull/96282
>From a341e03cb6376d50a4fa219933d3f161e41a567a Mon Sep 17 00:00:00 2001
From: Fangrui Song
Date: Thu, 27 Jun 2024 14:44:02 -0700
Subject: [PATCH] move seed inside #if
Created using spr 1.3.5-bogner
---
llvm/inc
https://github.com/nikic approved this pull request.
LGTM, but please wait a bit in case there is more feedback.
https://github.com/llvm/llvm-project/pull/96282
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.
@@ -322,24 +306,20 @@ struct hash_state {
}
};
-
-/// A global, fixed seed-override variable.
-///
-/// This variable can be set using the \see llvm::set_fixed_execution_seed
-/// function. See that function for details. Do not, under any circumstances,
-/// set or read this
Author: Med Ismail Bennani
Date: 2024-06-27T11:34:19-07:00
New Revision: 148a109bcd1592032bdda31694717bbeef5a976d
URL:
https://github.com/llvm/llvm-project/commit/148a109bcd1592032bdda31694717bbeef5a976d
DIFF:
https://github.com/llvm/llvm-project/commit/148a109bcd1592032bdda31694717bbeef5a976d.
https://github.com/AaronBallman commented:
The changes generally LGTM, though I would appreciate a second set of eyes on
the CMake and Python changes because I have a bit less confidence in my review
abilities there.
Thank you for adding the documentation to the header file, I think that will
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/96922
>From 84a2f69e71372891e2721552b10e0105b9430257 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 27 Jun 2024 09:28:22 -0700
Subject: [PATCH 1/2] Updated file headers
Created using spr 1.3.4
---
bolt/inclu
https://github.com/shawbyoung edited
https://github.com/llvm/llvm-project/pull/96922
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
aaupov wrote:
Please also retitle as an imperative statement, e.g. "Move CallGraph from
Passes to Core"
https://github.com/llvm/llvm-project/pull/96922
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-
@@ -178,6 +178,20 @@ bool AMDGPUAtomicOptimizerImpl::run(Function &F) {
return Changed;
}
+static bool shouldOptimizeForType(Type *Ty) {
arsenm wrote:
Name this something that states why this should be handled, not a vague
"shouldOptimize"
https://github
@@ -178,6 +178,20 @@ bool AMDGPUAtomicOptimizerImpl::run(Function &F) {
return Changed;
}
+static bool shouldOptimizeForType(Type *Ty) {
+ switch (Ty->getTypeID()) {
+ case Type::FloatTyID:
+ case Type::DoubleTyID:
+return true;
+ case Type::IntegerTyID: {
+if (T
MaskRay wrote:
The non-determinism is now restricted to `LLVM_ENABLE_ABI_BREAKING_CHECKS`
builds.
LLVM_ENABLE_ABI_BREAKING_CHECKS defaults to `WITH_ASSERTS` . Release builds
that disable assertions disable `LLVM_ENABLE_ABI_BREAKING_CHECKS`. This change
yields a slight code size/performance ad
https://github.com/MaskRay updated
https://github.com/llvm/llvm-project/pull/96282
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
https://github.com/MaskRay edited
https://github.com/llvm/llvm-project/pull/96282
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
https://github.com/MaskRay updated
https://github.com/llvm/llvm-project/pull/96282
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
@@ -178,6 +178,20 @@ bool AMDGPUAtomicOptimizerImpl::run(Function &F) {
return Changed;
}
+static bool shouldOptimizeForType(Type *Ty) {
+ switch (Ty->getTypeID()) {
+ case Type::FloatTyID:
+ case Type::DoubleTyID:
+return true;
+ case Type::IntegerTyID: {
+if (T
Author: jeanPerier
Date: 2024-06-27T19:21:19+02:00
New Revision: 5c45ad8a20989bd9ca9fdf8148ce690dc28c834c
URL:
https://github.com/llvm/llvm-project/commit/5c45ad8a20989bd9ca9fdf8148ce690dc28c834c
DIFF:
https://github.com/llvm/llvm-project/commit/5c45ad8a20989bd9ca9fdf8148ce690dc28c834c.diff
LO
llvmbot wrote:
@llvm/pr-subscribers-llvm-globalisel
Author: Vikram Hegde (vikramRH)
Changes
---
Patch is 1.18 MiB, truncated to 20.00 KiB below, full version:
https://github.com/llvm/llvm-project/pull/96934.diff
11 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/AMDGPUAtomicOpti
https://github.com/vikramRH ready_for_review
https://github.com/llvm/llvm-project/pull/96934
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
https://github.com/aaupov approved this pull request.
LGTM but please ensure that the diff passes NFC checks and shared build work.
https://github.com/llvm/llvm-project/pull/96922
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
vikramRH wrote:
> [!WARNING]
> This pull request is not mergeable via GitHub because a downstack PR is
> open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/96934?utm_source=stack-comment-downstack-mergeability-warning";
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/96922
>From 84a2f69e71372891e2721552b10e0105b9430257 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 27 Jun 2024 09:28:22 -0700
Subject: [PATCH] Updated file headers
Created using spr 1.3.4
---
bolt/include/b
@@ -10,7 +10,7 @@
//
//===--===//
-#include "bolt/Passes/CallGraph.h"
+#include "bolt/Core/CallGraph.h"
aaupov wrote:
Please also update file headers (first line)
https://github.com/llvm/ll
https://github.com/aaupov edited https://github.com/llvm/llvm-project/pull/96922
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
https://github.com/aaupov commented:
Please build with shared libraries mode to ensure cross-component dependencies
are satisfied.
https://github.com/llvm/llvm-project/pull/96922
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
llvmbot wrote:
@llvm/pr-subscribers-bolt
Author: shaw young (shawbyoung)
Changes
Moved CallGraph and BinaryFunctionCallGraph from Passes to
Core for future use in stale matching.
---
Full diff: https://github.com/llvm/llvm-project/pull/96922.diff
18 Files Affected:
- (renamed) bolt/in
https://github.com/shawbyoung edited
https://github.com/llvm/llvm-project/pull/96922
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
https://github.com/shawbyoung created
https://github.com/llvm/llvm-project/pull/96922
Moved CallGraph and BinaryFunctionCallGraph from Passes to
Core for future use in stale matching.
Test Plan: n/a
___
llvm-branch-commits mailing list
llvm-branch-
https://github.com/fhahn updated https://github.com/llvm/llvm-project/pull/76261
>From 733b3ed3f7441453889157834e0a5b6c288bf976 Mon Sep 17 00:00:00 2001
From: Florian Hahn
Date: Thu, 27 Jun 2024 15:48:05 +0100
Subject: [PATCH] [tysan] Add runtime support
---
clang/runtime/CMakeLists.txt
https://github.com/fhahn updated https://github.com/llvm/llvm-project/pull/76260
>From f45d4dc65537f3664472c873062fbda2a9bed984 Mon Sep 17 00:00:00 2001
From: Florian Hahn
Date: Thu, 18 Apr 2024 23:01:03 +0100
Subject: [PATCH 1/2] [TySan] A Type Sanitizer (Clang)
---
clang/include/clang/Basic/
https://github.com/gbMattN edited
https://github.com/llvm/llvm-project/pull/95387
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
@@ -221,7 +221,17 @@ __tysan_check(void *addr, int size, tysan_type_descriptor
*td, int flags) {
OldTDPtr -= i;
OldTD = *OldTDPtr;
-if (!isAliasingLegal(td, OldTD))
+tysan_type_descriptor *InternalMember = OldTD;
gbMattN wrote:
Done!
https:/
https://github.com/gbMattN updated
https://github.com/llvm/llvm-project/pull/95387
>From 8b9530d2efd2e8474fbeb1b788dd642d116fbc1d Mon Sep 17 00:00:00 2001
From: Matthew Nagy
Date: Thu, 13 Jun 2024 09:54:04 +
Subject: [PATCH] [TySan] Fixed false positive when accessing offset member
variabl
@@ -221,7 +221,17 @@ __tysan_check(void *addr, int size, tysan_type_descriptor
*td, int flags) {
OldTDPtr -= i;
OldTD = *OldTDPtr;
-if (!isAliasingLegal(td, OldTD))
+tysan_type_descriptor *InternalMember = OldTD;
fhahn wrote:
Could you add a
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96876
>From 4c2c159a6c3d4d7f509947bed2dc7873180565dd Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 23:18:32 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw for flat/global atomic min/max
f64
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96875
>From 39ecce1f9c4b668761b78fe3c901b9200fed43f7 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 19:34:43 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw for global/flat fadd v2bf16
builtin
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96874
>From 5df69e0bb808e808c0638a95ed4d14f135b88a09 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 19:15:26 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw from flat_atomic_{f32|f64}
builtins
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96873
>From f9fe227fedd64aab31d62e04f63cc1b709ce4d7f Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 19:12:59 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw from
{global|flat}_atomic_fadd_v2f1
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96872
>From 0f902e34937041d5171ad9e642724ec4594f601d Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Tue, 11 Jun 2024 10:58:44 +0200
Subject: [PATCH 1/2] clang/AMDGPU: Emit atomicrmw for
__builtin_amdgcn_global_ato
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96444
>From 234b772ad9a5f5a430da538474edcc968233f2ad Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 17:07:53 +0200
Subject: [PATCH] AMDGPU: Add subtarget feature for memory atomic fadd f64
---
ll
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96443
>From 5336548933c1ebd9a9e69938085a42d4ecac1511 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 16:44:08 +0200
Subject: [PATCH 1/3] AMDGPU: Add subtarget feature for global atomic fadd
denorma
arsenm wrote:
### Merge activity
* **Jun 27, 9:27 AM EDT**: @arsenm started a stack merge that includes this
pull request via
[Graphite](https://app.graphite.dev/github/pr/llvm/llvm-project/96739).
https://github.com/llvm/llvm-project/pull/96739
__
https://github.com/ergawy approved this pull request.
https://github.com/llvm/llvm-project/pull/92524
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
@@ -49,7 +49,7 @@ void test_s_wait_event_export_ready() {
}
// CHECK-LABEL: @test_global_add_f32
-// CHECK: {{.*}}call{{.*}} float
@llvm.amdgcn.global.atomic.fadd.f32.p1.f32(ptr addrspace(1) %{{.*}}, float
%{{.*}})
+// CHECK: = atomicrmw fadd ptr addrspace(1) %addr, float %x
@@ -49,7 +49,7 @@ void test_s_wait_event_export_ready() {
}
// CHECK-LABEL: @test_global_add_f32
-// CHECK: {{.*}}call{{.*}} float
@llvm.amdgcn.global.atomic.fadd.f32.p1.f32(ptr addrspace(1) %{{.*}}, float
%{{.*}})
+// CHECK: = atomicrmw fadd ptr addrspace(1) %addr, float %x
https://github.com/gbMattN ready_for_review
https://github.com/llvm/llvm-project/pull/95387
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
https://github.com/hokein updated
https://github.com/llvm/llvm-project/pull/96475
error: too big or took too long to generate
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-b
llvmbot wrote:
@llvm/pr-subscribers-llvm-globalisel
Author: Matt Arsenault (arsenm)
Changes
Need to emit syncscope and new metadata to get the native instruction,
most of the time.
---
Full diff: https://github.com/llvm/llvm-project/pull/96872.diff
5 Files Affected:
- (modified) clang/
llvmbot wrote:
@llvm/pr-subscribers-backend-amdgpu
Author: Matt Arsenault (arsenm)
Changes
Need to emit syncscope and new metadata to get the native instruction,
most of the time.
---
Full diff: https://github.com/llvm/llvm-project/pull/96872.diff
5 Files Affected:
- (modified) clang/l
llvmbot wrote:
@llvm/pr-subscribers-llvm-transforms
Author: Matt Arsenault (arsenm)
Changes
Need to emit syncscope and new metadata to get the native instruction,
most of the time.
---
Full diff: https://github.com/llvm/llvm-project/pull/96872.diff
5 Files Affected:
- (modified) clang/
llvmbot wrote:
@llvm/pr-subscribers-llvm-globalisel
Author: Matt Arsenault (arsenm)
Changes
---
Full diff: https://github.com/llvm/llvm-project/pull/96876.diff
2 Files Affected:
- (modified) clang/lib/CodeGen/CGBuiltin.cpp (+15-27)
- (modified) clang/test/CodeGenOpenCL/builtins-fp-at
llvmbot wrote:
@llvm/pr-subscribers-backend-amdgpu
Author: Matt Arsenault (arsenm)
Changes
---
Full diff: https://github.com/llvm/llvm-project/pull/96876.diff
2 Files Affected:
- (modified) clang/lib/CodeGen/CGBuiltin.cpp (+15-27)
- (modified) clang/test/CodeGenOpenCL/builtins-fp-ato
llvmbot wrote:
@llvm/pr-subscribers-llvm-globalisel
@llvm/pr-subscribers-backend-amdgpu
Author: Matt Arsenault (arsenm)
Changes
---
Full diff: https://github.com/llvm/llvm-project/pull/96875.diff
3 Files Affected:
- (modified) clang/lib/CodeGen/CGBuiltin.cpp (+8-18)
- (modified) clan
https://github.com/arsenm ready_for_review
https://github.com/llvm/llvm-project/pull/96876
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
llvmbot wrote:
@llvm/pr-subscribers-llvm-globalisel
@llvm/pr-subscribers-backend-amdgpu
Author: Matt Arsenault (arsenm)
Changes
---
Full diff: https://github.com/llvm/llvm-project/pull/96874.diff
3 Files Affected:
- (modified) clang/lib/CodeGen/CGBuiltin.cpp (+6-11)
- (modified) clan
https://github.com/arsenm ready_for_review
https://github.com/llvm/llvm-project/pull/96875
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
llvmbot wrote:
@llvm/pr-subscribers-llvm-globalisel
Author: Matt Arsenault (arsenm)
Changes
---
Full diff: https://github.com/llvm/llvm-project/pull/96873.diff
4 Files Affected:
- (modified) clang/lib/CodeGen/CGBuiltin.cpp (+6-14)
- (modified) clang/test/CodeGenOpenCL/builtins-fp-ato
https://github.com/arsenm ready_for_review
https://github.com/llvm/llvm-project/pull/96874
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
https://github.com/arsenm ready_for_review
https://github.com/llvm/llvm-project/pull/96873
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
https://github.com/arsenm ready_for_review
https://github.com/llvm/llvm-project/pull/96872
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
arsenm wrote:
> [!WARNING]
> This pull request is not mergeable via GitHub because a downstack PR is
> open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/96876?utm_source=stack-comment-downstack-mergeability-warning";
>
arsenm wrote:
> [!WARNING]
> This pull request is not mergeable via GitHub because a downstack PR is
> open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/96875?utm_source=stack-comment-downstack-mergeability-warning";
>
https://github.com/arsenm created
https://github.com/llvm/llvm-project/pull/96876
None
>From 0e174a54c24c70343a0e28c6ca053ab4bbbae3d2 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 23:18:32 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw for flat/global atomic min/max
arsenm wrote:
> [!WARNING]
> This pull request is not mergeable via GitHub because a downstack PR is
> open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/96874?utm_source=stack-comment-downstack-mergeability-warning";
>
arsenm wrote:
> [!WARNING]
> This pull request is not mergeable via GitHub because a downstack PR is
> open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/96873?utm_source=stack-comment-downstack-mergeability-warning";
>
https://github.com/arsenm created
https://github.com/llvm/llvm-project/pull/96875
None
>From 94d04eb6576b811e11175ca36a340649a63bf007 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 19:34:43 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw for global/flat fadd v2bf16
b
https://github.com/arsenm created
https://github.com/llvm/llvm-project/pull/96874
None
>From 9347154207e5a8d75755b11813b870b207fd125a Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 19:15:26 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw from flat_atomic_{f32|f64}
bu
arsenm wrote:
> [!WARNING]
> This pull request is not mergeable via GitHub because a downstack PR is
> open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/96872?utm_source=stack-comment-downstack-mergeability-warning";
>
https://github.com/arsenm created
https://github.com/llvm/llvm-project/pull/96873
None
>From 65a690d80cf39df132cacff510371c9dcb1b97fd Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 19:12:59 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw from
{global|flat}_atomic_fad
https://github.com/arsenm created
https://github.com/llvm/llvm-project/pull/96872
Need to emit syncscope and new metadata to get the native instruction,
most of the time.
>From bd298a4cb7aaa7f287da0654c8a530e378f0362a Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Tue, 11 Jun 2024 10:58:4
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96444
>From 0381e27b091f0cb6558fb9b4bf3e5359655acab0 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 17:07:53 +0200
Subject: [PATCH] AMDGPU: Add subtarget feature for memory atomic fadd f64
---
ll
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96443
>From eaa00157741d5e4f134df22ed27a80fe3d853e6e Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 16:44:08 +0200
Subject: [PATCH 1/3] AMDGPU: Add subtarget feature for global atomic fadd
denorma
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96739
>From 864e3bbfc5f40bfb1e87f7689ede0d5f33aa42da Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Tue, 11 Jun 2024 11:46:15 +0200
Subject: [PATCH] AMDGPU: Remove ds_fmin/ds_fmax intrinsics
These have been replac
@@ -323,5 +1089,12 @@ void populateWinogradConv2DPatterns(RewritePatternSet
&patterns, int64_t m,
patterns.insert(context, m, r);
}
+void populateDecomposeWinogradOpsPatterns(RewritePatternSet &patterns) {
+ MLIRContext *context = patterns.getContext();
+ patterns.insert(
@@ -289,6 +938,123 @@ FailureOr winogradConv2DHelper(RewriterBase
&rewriter,
return transformedOutput.getDefiningOp();
}
+FailureOr
+decomposeWinogradFilterTransformHelper(RewriterBase &rewriter,
+ linalg::WinogradFilterTransformOp op)
@@ -100,6 +594,161 @@ Value matrixMultiply(RewriterBase &rewriter, Location loc,
return expandOutput;
}
+// This function transforms the output. The data layout of the output is HWNF.
+// The transformation matrix is 2-dimension. We need to extract H x W from
+// HWNF first.
@@ -48,6 +287,261 @@ Value collapse2DData(RewriterBase &rewriter, Location loc,
Value data) {
reassociation);
}
+// This function transforms the filter. The data layout of the filter is FHWC.
+// The transformation matrix is 2
@@ -48,6 +287,261 @@ Value collapse2DData(RewriterBase &rewriter, Location loc,
Value data) {
reassociation);
}
+// This function transforms the filter. The data layout of the filter is FHWC.
+// The transformation matrix is 2
@@ -36,6 +189,92 @@ constexpr TransformMapKeyTy F_2_3{2, 3};
constexpr TransformMapKeyTy F_4_3{4, 3};
constexpr TransformMapKeyTy F_2_5{2, 5};
+struct TransformMatrix {
+ TransformMatrix(const float *table, int64_t rows, int64_t cols,
+ int64_t scalarFactor =
@@ -36,6 +189,92 @@ constexpr TransformMapKeyTy F_2_3{2, 3};
constexpr TransformMapKeyTy F_4_3{4, 3};
constexpr TransformMapKeyTy F_2_5{2, 5};
+struct TransformMatrix {
Hsiangkai wrote:
Done.
https://github.com/llvm/llvm-project/pull/96183
__
@@ -23,6 +26,156 @@ namespace linalg {
namespace {
+// clang-format off
+// Winograd Conv2D uses a minimal 2D filtering algorithm to calculate its
+// result. The formula of minimal 2D filtering algorithm F(m x m, r x r),
+// m is the output dimension and r is the filter dime
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96444
>From 36cbbdfaa31c6313c96a9c908bade1e6f7debc5b Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 17:07:53 +0200
Subject: [PATCH] AMDGPU: Add subtarget feature for memory atomic fadd f64
---
ll
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96443
>From f29955ee4dfb3319d0ea99187d2cc24587c9e716 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 16:44:08 +0200
Subject: [PATCH 1/3] AMDGPU: Add subtarget feature for global atomic fadd
denorma
99 matches
Mail list logo
