<feed xmlns='http://www.w3.org/2005/Atom'>
<title>llvm-project.git/llvm/lib/Target/AMDGPU, branch users/nico/python-2</title>
<subtitle>Unnamed repository; edit this file 'description' to name the repository.
</subtitle>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/'/>
<entry>
<title>MCAsmBackend: Simplify shouldForceRelocation overrides</title>
<updated>2025-07-03T06:30:36+00:00</updated>
<author>
<name>Fangrui Song</name>
<email>i@maskray.me</email>
</author>
<published>2025-07-03T06:30:36+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=b59763a7db7fc502b4e1d8aaa4da319d85006066'/>
<id>b59763a7db7fc502b4e1d8aaa4da319d85006066</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>MCAsmBackend: Merge addReloc into applyFixup (#146820)</title>
<updated>2025-07-03T06:14:11+00:00</updated>
<author>
<name>Fangrui Song</name>
<email>i@maskray.me</email>
</author>
<published>2025-07-03T06:14:11+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=dd2891535d4b6d80f92d9a69e9db3b787203b9d0'/>
<id>dd2891535d4b6d80f92d9a69e9db3b787203b9d0</id>
<content type='text'>
Follow-up to #141333. Relocation generation called both addReloc and
applyFixup, with the default addReloc invoking shouldForceRelocation,
resulting in three virtual calls. This approach was also inflexible, as
targets needing additional data required extending
`shouldForceRelocation` (see #73721, resolved by #141311).

This change integrates relocation handling into applyFixup, eliminating
two virtual calls. The prior default addReloc is renamed to
maybeAddReloc. Targets overriding addReloc now call their customized
addReloc implementation.</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Follow-up to #141333. Relocation generation called both addReloc and
applyFixup, with the default addReloc invoking shouldForceRelocation,
resulting in three virtual calls. This approach was also inflexible, as
targets needing additional data required extending
`shouldForceRelocation` (see #73721, resolved by #141311).

This change integrates relocation handling into applyFixup, eliminating
two virtual calls. The prior default addReloc is renamed to
maybeAddReloc. Targets overriding addReloc now call their customized
addReloc implementation.</pre>
</div>
</content>
</entry>
<entry>
<title>[AMDGPU][MC] Fix disassembly for v_permlane16_swap_b32 for GFX950 (#146600)</title>
<updated>2025-07-02T17:05:25+00:00</updated>
<author>
<name>Jun Wang</name>
<email>jwang86@yahoo.com</email>
</author>
<published>2025-07-02T17:05:25+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=641ad52b6ab4ea80c16becffb79e249fc5039f18'/>
<id>641ad52b6ab4ea80c16becffb79e249fc5039f18</id>
<content type='text'>
When targeting GFX950, disassembly of v_permlane16_swap_b32 and
v_permlane32_swap_b32 instructions produces errors when they use certain
vdst operand values, e.g., v_permlane16_swap_b32 v218, v219. This patch
fixes this problem.</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
When targeting GFX950, disassembly of v_permlane16_swap_b32 and
v_permlane32_swap_b32 instructions produces errors when they use certain
vdst operand values, e.g., v_permlane16_swap_b32 v218, v219. This patch
fixes this problem.</pre>
</div>
</content>
</entry>
<entry>
<title>[AMDGPU] Fix comment on DelayInfo::advance (#146718)</title>
<updated>2025-07-02T16:18:57+00:00</updated>
<author>
<name>Jay Foad</name>
<email>jay.foad@amd.com</email>
</author>
<published>2025-07-02T16:18:57+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=e717e503cae19e7e965972724a1476b2fa66ad2d'/>
<id>e717e503cae19e7e965972724a1476b2fa66ad2d</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>[AMDGPU] Remove HasSampler variable. NFC. (#146682)</title>
<updated>2025-07-02T14:44:32+00:00</updated>
<author>
<name>Jay Foad</name>
<email>jay.foad@amd.com</email>
</author>
<published>2025-07-02T14:44:32+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=ad715beca18469a483d14df3462446d37c039ac8'/>
<id>ad715beca18469a483d14df3462446d37c039ac8</id>
<content type='text'>
Putting the complex condition in a variable does not help readability.
It is simpler to use separate `if`s.</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Putting the complex condition in a variable does not help readability.
It is simpler to use separate `if`s.</pre>
</div>
</content>
</entry>
<entry>
<title>[AMDGPU] Use isImage. NFC. (#146677)</title>
<updated>2025-07-02T13:18:42+00:00</updated>
<author>
<name>Jay Foad</name>
<email>jay.foad@amd.com</email>
</author>
<published>2025-07-02T13:18:42+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=2b03efc7fba813bb0c52b7016867f200a91c2d34'/>
<id>2b03efc7fba813bb0c52b7016867f200a91c2d34</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>[AMDGPU] Add a debug option `-amdgpu-snop-padding` for `GCNHazardRecognizer` (#146587)</title>
<updated>2025-07-02T12:16:38+00:00</updated>
<author>
<name>Shilei Tian</name>
<email>i@tianshilei.me</email>
</author>
<published>2025-07-02T12:16:38+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=c0e9084b1ce1a93fd8c2a650e48b3e11d831b649'/>
<id>c0e9084b1ce1a93fd8c2a650e48b3e11d831b649</id>
<content type='text'>
This can help to identify if there is potential hazards.

Co-authored-by: Byrnes, Jeffrey &lt;Jeffrey.Byrnes@amd.com&gt;</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This can help to identify if there is potential hazards.

Co-authored-by: Byrnes, Jeffrey &lt;Jeffrey.Byrnes@amd.com&gt;</pre>
</div>
</content>
</entry>
<entry>
<title>AMDGPU: Implement tensor_save and tensor_stop for gfx1250 (#146590)</title>
<updated>2025-07-01T21:28:38+00:00</updated>
<author>
<name>Changpeng Fang</name>
<email>changpeng.fang@amd.com</email>
</author>
<published>2025-07-01T21:28:38+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=d99b14623f430fc141c583041f6a255ccdb2ac0e'/>
<id>d99b14623f430fc141c583041f6a255ccdb2ac0e</id>
<content type='text'>
MC layer only.</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
MC layer only.</pre>
</div>
</content>
</entry>
<entry>
<title>AMDGPU: Implement ds_atomic_async_barrier_arrive_b64/ds_atomic_barrier_arrive_rtn_b64 (#146409)</title>
<updated>2025-07-01T18:08:49+00:00</updated>
<author>
<name>Changpeng Fang</name>
<email>changpeng.fang@amd.com</email>
</author>
<published>2025-07-01T18:08:49+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=5035d20dcbcea1edced779148ac69b84d3c97577'/>
<id>5035d20dcbcea1edced779148ac69b84d3c97577</id>
<content type='text'>
These two instructions are supported by gfx1250. We define the
instructions and implement the corresponding intrinsic and builtin.

Co-authored-by: Stanislav Mekhanoshin &lt;Stanislav.Mekhanoshin@amd.com&gt;</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
These two instructions are supported by gfx1250. We define the
instructions and implement the corresponding intrinsic and builtin.

Co-authored-by: Stanislav Mekhanoshin &lt;Stanislav.Mekhanoshin@amd.com&gt;</pre>
</div>
</content>
</entry>
<entry>
<title>[AMDGPU] Remove an unnecessary cast (NFC) (#146548)</title>
<updated>2025-07-01T17:42:22+00:00</updated>
<author>
<name>Kazu Hirata</name>
<email>kazu@google.com</email>
</author>
<published>2025-07-01T17:42:22+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=e79e22c9af9722fa92335bfa71f568798985b6a5'/>
<id>e79e22c9af9722fa92335bfa71f568798985b6a5</id>
<content type='text'>
Val is already of uint64_t.</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Val is already of uint64_t.</pre>
</div>
</content>
</entry>
</feed>
