https://github.com/shawbyoung created
https://github.com/llvm/llvm-project/pull/96596
Test Plan: tbd
___
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/95884
>From 34652b2eebc62218c50a23509ce99937385c30e6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 20 Jun 2024 23:42:00 -0700
Subject: [PATCH 1/7] spr amend
Created using spr 1.3.4
---
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/95884
>From 34652b2eebc62218c50a23509ce99937385c30e6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 20 Jun 2024 23:42:00 -0700
Subject: [PATCH 1/7] spr amend
Created using spr 1.3.4
---
ldionne wrote:
> We don't have a great way to add release notes after the final release. I
> added this to the release announcement do you think that is enough?
Yes I think that is fine.
https://github.com/llvm/llvm-project/pull/96116
___
https://github.com/ldionne closed
https://github.com/llvm/llvm-project/pull/96116
___
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/95884
>From 34652b2eebc62218c50a23509ce99937385c30e6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 20 Jun 2024 23:42:00 -0700
Subject: [PATCH 1/7] spr amend
Created using spr 1.3.4
---
tstellar wrote:
We don't have a great way to add release notes after the final release. I
added this to the release announcement do you think that is enough?
https://github.com/llvm/llvm-project/pull/96116
___
llvm-branch-commits mailing list
https://github.com/shawbyoung converted_to_draft
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
https://github.com/shawbyoung closed
https://github.com/llvm/llvm-project/pull/96571
___
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-bolt
Author: shaw young (shawbyoung)
Changes
Test Plan: n/a
---
Full diff: https://github.com/llvm/llvm-project/pull/96571.diff
2 Files Affected:
- (modified) bolt/lib/Rewrite/RewriteInstance.cpp (-3)
- (modified)
https://github.com/shawbyoung created
https://github.com/llvm/llvm-project/pull/96571
Test Plan: n/a
___
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/95821
>From 92212c96ea169d26ac10bf8d750539bc5dd72c49 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Mon, 17 Jun 2024 15:39:02 -0700
Subject: [PATCH 01/20] spr amend
Created using spr 1.3.4
---
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/95821
>From 92212c96ea169d26ac10bf8d750539bc5dd72c49 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Mon, 17 Jun 2024 15:39:02 -0700
Subject: [PATCH 01/20] spr amend
Created using spr 1.3.4
---
https://github.com/rampitec approved this pull request.
https://github.com/llvm/llvm-project/pull/96444
___
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 updated
https://github.com/llvm/llvm-project/pull/96444
>From baaf96125e8f913a161f1c13216618a3de128182 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
---
https://github.com/ilovepi updated
https://github.com/llvm/llvm-project/pull/90267
___
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/ilovepi edited
https://github.com/llvm/llvm-project/pull/90267
___
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/ilovepi updated
https://github.com/llvm/llvm-project/pull/90267
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
ldionne wrote:
Gentle ping @tstellar, do we want to merge this?
The CI issues are unrelated.
https://github.com/llvm/llvm-project/pull/96116
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://github.com/rampitec approved this pull request.
https://github.com/llvm/llvm-project/pull/96443
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
Author: David Truby
Date: 2024-06-24T21:53:39+01:00
New Revision: 0f6f6ddbc0d84d2df23df8c8a771ace3c0dca988
URL:
https://github.com/llvm/llvm-project/commit/0f6f6ddbc0d84d2df23df8c8a771ace3c0dca988
DIFF:
https://github.com/llvm/llvm-project/commit/0f6f6ddbc0d84d2df23df8c8a771ace3c0dca988.diff
arsenm wrote:
> It is worse than that. It behaves differently depending on where atomic is
> executed. There is no single answer if this instruction supports denorms or
> not.
That doesn't matter. The flat case that sometimes flushes is just a no.
Flushing is never a guarantee, we only need
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/95821
>From 92212c96ea169d26ac10bf8d750539bc5dd72c49 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Mon, 17 Jun 2024 15:39:02 -0700
Subject: [PATCH 01/20] spr amend
Created using spr 1.3.4
---
https://github.com/ftynse approved this pull request.
https://github.com/llvm/llvm-project/pull/96329
___
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/fmayer approved this pull request.
https://github.com/llvm/llvm-project/pull/96527
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
@@ -788,6 +788,14 @@ def FeatureFlatAtomicFaddF32Inst
"Has flat_atomic_add_f32 instruction"
>;
+def FeatureAgentScopeFineGrainedRemoteMemoryAtomics
+ : SubtargetFeature<"agent-scope-fine-grained-remote-memory-atomics",
+ "HasAgentScopeFineGrainedRemoteMemoryAtomics",
+
https://github.com/vitalybuka edited
https://github.com/llvm/llvm-project/pull/96527
___
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-pgo
Author: Vitaly Buka (vitalybuka)
Changes
We use REAL() calls in interceptors, but
DEFINE_REAL_PTHREAD_FUNCTIONS has nothing to do
with them and only used for internal maintenance
threads.
---
Full diff:
https://github.com/vitalybuka created
https://github.com/llvm/llvm-project/pull/96527
We use REAL() calls in interceptors, but
DEFINE_REAL_PTHREAD_FUNCTIONS has nothing to do
with them and only used for internal maintenance
threads.
___
llvmbot wrote:
@llvm/pr-subscribers-llvm-transforms
@llvm/pr-subscribers-clang-driver
Author: Paul Kirth (ilovepi)
Changes
Add basic plumbing to clang so that diagnostics can be surfaced to
users.
---
Full diff: https://github.com/llvm/llvm-project/pull/96525.diff
9 Files Affected:
-
llvmbot wrote:
@llvm/pr-subscribers-pgo
@llvm/pr-subscribers-llvm-transforms
Author: Paul Kirth (ilovepi)
Changes
---
Full diff: https://github.com/llvm/llvm-project/pull/96524.diff
3 Files Affected:
- (modified) llvm/lib/Transforms/Scalar/LowerExpectIntrinsic.cpp (+18)
- (modified)
https://github.com/ilovepi created
https://github.com/llvm/llvm-project/pull/96525
Add basic plumbing to clang so that diagnostics can be surfaced to
users.
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
llvmbot wrote:
@llvm/pr-subscribers-llvm-transforms
@llvm/pr-subscribers-pgo
Author: Paul Kirth (ilovepi)
Changes
Issue #56502 describes an enhancement related to the use of llvm.expect.
The request is for a diagnostic mode that can identify branches that
would benefit from the use of
https://github.com/ilovepi created
https://github.com/llvm/llvm-project/pull/96524
None
___
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/ilovepi created
https://github.com/llvm/llvm-project/pull/96523
Issue #56502 describes an enhancement related to the use of llvm.expect.
The request is for a diagnostic mode that can identify branches that
would benefit from the use of llvm.expect based on the branch_weights
arsenm wrote:
> need some tests
This does nothing as it is. The real use patches have thousands of tests
https://github.com/llvm/llvm-project/pull/96442
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
rampitec wrote:
It is worse than that. It behaves differently depending on where atomic is
executed. There is no single answer if this instruction supports denorms or not.
https://github.com/llvm/llvm-project/pull/96443
___
llvm-branch-commits
rampitec wrote:
Use it in a predicate when defining pseudos?
https://github.com/llvm/llvm-project/pull/96444
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
yxsamliu wrote:
need some tests
https://github.com/llvm/llvm-project/pull/96442
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
arsenm wrote:
No, the string description mentions this is for the non-PCIe supported cases
https://github.com/llvm/llvm-project/pull/96442
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://github.com/ilovepi updated
https://github.com/llvm/llvm-project/pull/90146
___
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/ilovepi updated
https://github.com/llvm/llvm-project/pull/90146
___
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/ilovepi updated
https://github.com/llvm/llvm-project/pull/90146
___
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/ilovepi updated
https://github.com/llvm/llvm-project/pull/90146
___
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/ilovepi updated
https://github.com/llvm/llvm-project/pull/86610
___
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/ilovepi updated
https://github.com/llvm/llvm-project/pull/86610
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
yxsamliu wrote:
If a sub target does not have this feature, does none of the atomic
instructions work for fine-grained remote memory, including integer atomic
add/xchg/cmpxchg?
https://github.com/llvm/llvm-project/pull/96442
___
llvm-branch-commits
https://github.com/gbMattN edited
https://github.com/llvm/llvm-project/pull/96507
___
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-compiler-rt-sanitizer
Author: None (gbMattN)
Changes
All the violation tests failed when running on my machine. By changing some
check lines to regular expressions, we can account for file locality, and
hardware specific type differences. There was
gbMattN wrote:
@fhahn (Sorry for the ping, I can't manually add reviewers yet)
https://github.com/llvm/llvm-project/pull/96507
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
github-actions[bot] wrote:
Thank you for submitting a Pull Request (PR) to the LLVM Project!
This PR will be automatically labeled and the relevant teams will be
notified.
If you wish to, you can add reviewers by using the "Reviewers" section on this
page.
If this is not working for you,
https://github.com/gbMattN created
https://github.com/llvm/llvm-project/pull/96507
All the violation tests failed when running on my machine. By changing some
check lines to regular expressions, we can account for file locality, and
hardware specific type differences. There was also an
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96444
>From 80c3f71f03d3b2ccbcd418d76d417f2a243fdbe4 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 17:07:53 +0200
Subject: [PATCH 1/2] AMDGPU: Add subtarget feature for memory atomic fadd f64
@@ -2638,4 +2638,41 @@ def WinogradConv2DOp : Op {
+ let description = [{
+Decompose winograd operators. It will convert filter, input and output
+transform operators into a combination of scf, tensor, and linalg
ftynse wrote:
Nit: operations
@@ -2760,6 +2760,89 @@ LogicalResult WinogradFilterTransformOp::verify() {
return success();
}
+SmallVector
+WinogradFilterTransformOp::getIterationDomain(OpBuilder ) {
+ Location loc = getLoc();
+ Value zero = builder.create(loc, 0);
+ Value one = builder.create(loc,
@@ -2760,6 +2760,89 @@ LogicalResult WinogradFilterTransformOp::verify() {
return success();
}
+SmallVector
+WinogradFilterTransformOp::getIterationDomain(OpBuilder ) {
+ Location loc = getLoc();
+ Value zero = builder.create(loc, 0);
+ Value one = builder.create(loc,
@@ -2760,6 +2760,89 @@ LogicalResult WinogradFilterTransformOp::verify() {
return success();
}
+SmallVector
+WinogradFilterTransformOp::getIterationDomain(OpBuilder ) {
+ Location loc = getLoc();
+ Value zero = builder.create(loc, 0);
+ Value one = builder.create(loc,
https://github.com/ftynse commented:
I think @MaheshRavishankar should take a look at the interface implementation
details.
https://github.com/llvm/llvm-project/pull/96184
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://github.com/ftynse edited https://github.com/llvm/llvm-project/pull/96184
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
@@ -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
@@ -100,6 +594,161 @@ Value matrixMultiply(RewriterBase , 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. We need
@@ -48,6 +287,261 @@ Value collapse2DData(RewriterBase , Location loc,
Value data) {
reassociation);
}
+// This function transforms the filter. The data layout of the filter is FHWC.
+// The transformation matrix is
@@ -289,6 +938,123 @@ FailureOr winogradConv2DHelper(RewriterBase
,
return transformedOutput.getDefiningOp();
}
+FailureOr
+decomposeWinogradFilterTransformHelper(RewriterBase ,
+ linalg::WinogradFilterTransformOp op) {
+ Location loc
@@ -48,6 +287,261 @@ Value collapse2DData(RewriterBase , Location loc,
Value data) {
reassociation);
}
+// This function transforms the filter. The data layout of the filter is FHWC.
+// The transformation matrix is
@@ -48,6 +287,261 @@ Value collapse2DData(RewriterBase , Location loc,
Value data) {
reassociation);
}
+// This function transforms the filter. The data layout of the filter is FHWC.
+// The transformation matrix is
@@ -323,5 +1089,12 @@ void populateWinogradConv2DPatterns(RewritePatternSet
, int64_t m,
patterns.insert(context, m, r);
}
+void populateDecomposeWinogradOpsPatterns(RewritePatternSet ) {
+ MLIRContext *context = patterns.getContext();
+ patterns.insert(context);
+
@@ -100,6 +594,161 @@ Value matrixMultiply(RewriterBase , 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. We need
@@ -100,6 +594,161 @@ Value matrixMultiply(RewriterBase , 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. We need
@@ -48,6 +287,261 @@ Value collapse2DData(RewriterBase , Location loc,
Value data) {
reassociation);
}
+// This function transforms the filter. The data layout of the filter is FHWC.
+// The transformation matrix is
@@ -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 {
ftynse wrote:
Please document top-level entities.
@@ -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
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96443
>From f99d34b66486a17e2fe70d372d67fbabde82d5fb Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 16:44:08 +0200
Subject: [PATCH 1/2] AMDGPU: Add subtarget feature for global atomic fadd
arsenm wrote:
> Actually not, we do not know the bus. Moreover, we know this is opposite.
On gfx940/gfx12, we don't need to know the bus to handle the agent scope case
correctly. The instructions still function, just always at device scope. We do
need to know the bus and/or location to handle
@@ -1701,17 +1732,33 @@ unsigned SILoadStoreOptimizer::getNewOpcode(const
CombineInfo ,
return AMDGPU::S_BUFFER_LOAD_DWORDX8_SGPR_IMM;
}
case S_LOAD_IMM:
-switch (Width) {
-default:
- return 0;
-case 2:
- return AMDGPU::S_LOAD_DWORDX2_IMM;
-
rampitec wrote:
> We do statically know for some of the targets (mostly gfx12 and gfx940) that
> it's supposed to work. This is the "scope downgrade" vs. "nop" cases in the
> atomic support table
Actually not, we do not know the bus. Moreover, we know this is opposite.
@@ -1701,17 +1732,33 @@ unsigned SILoadStoreOptimizer::getNewOpcode(const
CombineInfo ,
return AMDGPU::S_BUFFER_LOAD_DWORDX8_SGPR_IMM;
}
case S_LOAD_IMM:
-switch (Width) {
-default:
- return 0;
-case 2:
- return AMDGPU::S_LOAD_DWORDX2_IMM;
-
https://github.com/jayfoad edited
https://github.com/llvm/llvm-project/pull/96162
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
@@ -1701,17 +1732,33 @@ unsigned SILoadStoreOptimizer::getNewOpcode(const
CombineInfo ,
return AMDGPU::S_BUFFER_LOAD_DWORDX8_SGPR_IMM;
}
case S_LOAD_IMM:
-switch (Width) {
-default:
- return 0;
-case 2:
- return AMDGPU::S_LOAD_DWORDX2_IMM;
-
@@ -867,13 +867,104 @@ def SMRDBufferImm : ComplexPattern;
def SMRDBufferImm32 : ComplexPattern;
def SMRDBufferSgprImm : ComplexPattern;
+class SMRDAlignedLoadPat : PatFrag <(ops node:$ptr), (Op
node:$ptr), [{
+ // Returns true if it is a naturally aligned multi-dword
79 matches
Mail list logo