Pierre-vh wrote:
@shiltian Please also remove `warn_drv_amdgpu_cov6` - it's a warning I added
while v6 was being worked on.
Now that it's supported by the stack we can remove it.
https://github.com/llvm/llvm-project/pull/118515
___
cfe-commits mailing
llvm-ci wrote:
LLVM Buildbot has detected a new failure on builder
`openmp-offload-libc-amdgpu-runtime` running on `omp-vega20-1` while building
`clang,libc,llvm,offload` at step 7 "Add check check-offload".
Full details are available at:
https://lab.llvm.org/buildbot/#/builders/73/builds/955
shiltian wrote:
The OpenMP failure has nothing to do with this PR. Please update ROCm to a
version that supports COV6.
https://github.com/llvm/llvm-project/pull/118515
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-
llvm-ci wrote:
LLVM Buildbot has detected a new failure on builder
`openmp-offload-amdgpu-runtime` running on `omp-vega20-0` while building
`clang,libc,llvm,offload` at step 7 "Add check check-offload".
Full details are available at:
https://lab.llvm.org/buildbot/#/builders/30/builds/11492
llvm-ci wrote:
LLVM Buildbot has detected a new failure on builder `clang-hip-vega20` running
on `hip-vega20-0` while building `clang,libc,llvm,offload` at step 3 "annotate".
Full details are available at:
https://lab.llvm.org/buildbot/#/builders/123/builds/10534
Here is the relevant piece o
https://github.com/shiltian closed
https://github.com/llvm/llvm-project/pull/118515
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -0,0 +1,7 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa %s -o - | FileCheck %s
+
+; CHECK: .amdhsa_code_object_version 6
shiltian wrote:
ah, they check the IR match Lol. I will add one later then.
https://github.com/llvm/llvm-project/pull/118515
_
https://github.com/arsenm approved this pull request.
https://github.com/llvm/llvm-project/pull/118515
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -0,0 +1,7 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa %s -o - | FileCheck %s
+
+; CHECK: .amdhsa_code_object_version 6
arsenm wrote:
`git grep "\.amdhsa_code_object_version" llvm/test/CodeGen/AMDGPU/` does not
find them
https://github.com/llvm/llvm-project/pul
https://github.com/shiltian updated
https://github.com/llvm/llvm-project/pull/118515
>From 8ba940796d4092c225ce34ff883b80d36fee58fe Mon Sep 17 00:00:00 2001
From: Shilei Tian
Date: Tue, 3 Dec 2024 11:25:37 -0500
Subject: [PATCH] [AMDGPU] Use COV6 by default
---
clang/docs/ReleaseNotes.rst
@@ -0,0 +1,7 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa %s -o - | FileCheck %s
+
+; CHECK: .amdhsa_code_object_version 6
shiltian wrote:
We already have multiple tests that have explicit module flag and checks for
the match.
https://github.com/llvm/llvm-project/
@@ -818,6 +818,8 @@ Target Specific Changes
AMDGPU Support
^^
+- Bump the default code object version to 6.
arsenm wrote:
Also should update the llvm release notes
https://github.com/llvm/llvm-project/pull/118515
@@ -0,0 +1,7 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa %s -o - | FileCheck %s
+
+; CHECK: .amdhsa_code_object_version 6
arsenm wrote:
It seems we have no other tests checking this field, which seems hard to
believe. We probably should have one that tests it with
@@ -34,7 +34,7 @@
static llvm::cl::opt DefaultAMDHSACodeObjectVersion(
"amdhsa-code-object-version", llvm::cl::Hidden,
-llvm::cl::init(llvm::AMDGPU::AMDHSA_COV5),
+llvm::cl::init(llvm::AMDGPU::AMDHSA_COV6),
shiltian wrote:
> The .amdhsa_code_objec
https://github.com/shiltian updated
https://github.com/llvm/llvm-project/pull/118515
>From af3d46f389a2b4e77f0d4681c1f62eca86c3140f Mon Sep 17 00:00:00 2001
From: Shilei Tian
Date: Tue, 3 Dec 2024 11:25:37 -0500
Subject: [PATCH] [AMDGPU] Use COV6 by default
---
clang/docs/ReleaseNotes.rst
@@ -34,7 +34,7 @@
static llvm::cl::opt DefaultAMDHSACodeObjectVersion(
"amdhsa-code-object-version", llvm::cl::Hidden,
-llvm::cl::init(llvm::AMDGPU::AMDHSA_COV5),
+llvm::cl::init(llvm::AMDGPU::AMDHSA_COV6),
shiltian wrote:
It does things. If we do
@@ -34,7 +34,7 @@
static llvm::cl::opt DefaultAMDHSACodeObjectVersion(
"amdhsa-code-object-version", llvm::cl::Hidden,
-llvm::cl::init(llvm::AMDGPU::AMDHSA_COV5),
+llvm::cl::init(llvm::AMDGPU::AMDHSA_COV6),
arsenm wrote:
Actually this is broken, t
@@ -34,7 +34,7 @@
static llvm::cl::opt DefaultAMDHSACodeObjectVersion(
"amdhsa-code-object-version", llvm::cl::Hidden,
-llvm::cl::init(llvm::AMDGPU::AMDHSA_COV5),
+llvm::cl::init(llvm::AMDGPU::AMDHSA_COV6),
arsenm wrote:
The .amdhsa_code_object_ve
@@ -34,7 +34,7 @@
static llvm::cl::opt DefaultAMDHSACodeObjectVersion(
"amdhsa-code-object-version", llvm::cl::Hidden,
-llvm::cl::init(llvm::AMDGPU::AMDHSA_COV5),
+llvm::cl::init(llvm::AMDGPU::AMDHSA_COV6),
shiltian wrote:
Not really. Nothing chan
@@ -34,7 +34,7 @@
static llvm::cl::opt DefaultAMDHSACodeObjectVersion(
"amdhsa-code-object-version", llvm::cl::Hidden,
-llvm::cl::init(llvm::AMDGPU::AMDHSA_COV5),
+llvm::cl::init(llvm::AMDGPU::AMDHSA_COV6),
arsenm wrote:
Missing test update for th
shiltian wrote:
> Why change the clang default only, and not the backend?
Yeah, initially I thought that was dictated by the front end but forgot we
could invoke directly via `opt`, `llc`, etc. Done.
https://github.com/llvm/llvm-project/pull/118515
_
https://github.com/shiltian updated
https://github.com/llvm/llvm-project/pull/118515
>From a0dfb34e2c0711826b5bbf5dc0ed15e87918fa27 Mon Sep 17 00:00:00 2001
From: Shilei Tian
Date: Tue, 3 Dec 2024 11:25:37 -0500
Subject: [PATCH] [AMDGPU] Use COV6 by default
---
clang/docs/ReleaseNotes.rst
https://github.com/arsenm commented:
Why change the clang default only, and not the backend?
https://github.com/llvm/llvm-project/pull/118515
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-co
https://github.com/shiltian updated
https://github.com/llvm/llvm-project/pull/118515
>From 88df866f5d1cc7fef7bea0d938f9457a3969025b Mon Sep 17 00:00:00 2001
From: Shilei Tian
Date: Tue, 3 Dec 2024 11:25:37 -0500
Subject: [PATCH] [AMDGPU] Use COV6 by default
---
clang/docs/ReleaseNotes.rst
https://github.com/shiltian updated
https://github.com/llvm/llvm-project/pull/118515
>From 57fa521750d902926d210eb9d783a9cbed71ef36 Mon Sep 17 00:00:00 2001
From: Shilei Tian
Date: Tue, 3 Dec 2024 11:25:37 -0500
Subject: [PATCH] [AMDGPU] Use COV6 by default
---
clang/include/clang/Driver/Opti
https://github.com/shiltian updated
https://github.com/llvm/llvm-project/pull/118515
>From dc6f54cd68819ad280e004f3969fd61db94f31b4 Mon Sep 17 00:00:00 2001
From: Shilei Tian
Date: Tue, 3 Dec 2024 11:25:37 -0500
Subject: [PATCH] [AMDGPU] Use COV6 by default
---
clang/docs/ReleaseNotes.rst
shiltian wrote:
> > AFAIK it has nothing fancy for runtime.
>
> The `libc` CMake has a variable that sets it to 5, might be worth bumping
> that up since it's actively tested. It's in the
> `prepare_libc_gpu_build.cmake`.
Done.
https://github.com/llvm/llvm-project/pull/118515
___
27 matches
Mail list logo
