[llvm-branch-commits] [llvm] cb5b52a - AMDGPU: Annotate amdgpu.noclobber for global loads only

Author: Changpeng Fang Date: 2021-01-05T14:47:19-08:00 New Revision: cb5b52a06eeb7cc868944bb08f71fffe13f33412 URL: https://github.com/llvm/llvm-project/commit/cb5b52a06eeb7cc868944bb08f71fffe13f33412 DIFF: https://github.com/llvm/llvm-project/commit/cb5b52a06eeb7cc868944bb08f71fffe13f33412.diff

[llvm-branch-commits] [llvm] ce0c001 - AMDGPU: If a store defines (alias) a load, it clobbers the load.

Author: Changpeng Fang Date: 2020-12-14T16:34:32-08:00 New Revision: ce0c0013d8b11e9ce9820c0add2a013f5992e6a6 URL: https://github.com/llvm/llvm-project/commit/ce0c0013d8b11e9ce9820c0add2a013f5992e6a6 DIFF: https://github.com/llvm/llvm-project/commit/ce0c0013d8b11e9ce9820c0add2a013f5992e6a6.diff

[llvm-branch-commits] [llvm] [AMDGPU] Add the code generation support for `llvm.[sin/cos].bf16` (PR #149631)

https://github.com/changpeng approved this pull request. https://github.com/llvm/llvm-project/pull/149631 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] [AMDGPU] Add support for `v_prng_b32` on gfx1250 (PR #149450)

https://github.com/changpeng edited https://github.com/llvm/llvm-project/pull/149450 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] [AMDGPU] Add support for `v_prng_b32` on gfx1250 (PR #149450)

https://github.com/changpeng approved this pull request. LGTM. But has the builtin definition always been added in clang? https://github.com/llvm/llvm-project/pull/149450 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://

[llvm-branch-commits] [llvm] [AMDGPU][SDAG] Enable ISD::PTRADD for 64-bit AS by default (PR #146076)

changpeng wrote: > Rebase and updated new test checks. @changpeng, could you please verify if > the AMDGPU/no-folding-imm-to-inst-with-fi.ll test that #151263 recently added > still does what it is supposed to do with the updated checks in this PR? It is good (as long as it passes) https://gi

[llvm-branch-commits] [llvm] AMDGPU: Improve v4f16/v4bf16 copysign handling (PR #142174)

https://github.com/changpeng approved this pull request. https://github.com/llvm/llvm-project/pull/142174 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU] Adjust hard clause rules for gfx1250 (PR #152592)

https://github.com/changpeng approved this pull request. https://github.com/llvm/llvm-project/pull/152592 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU] Use encodeFieldVaVdst in hazard recognizer. NFCI. (PR #153881)

https://github.com/changpeng approved this pull request. https://github.com/llvm/llvm-project/pull/153881 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU] Update GCNHazardRecognizer's understanding of gfx12 waitcount instructions (PR #153880)

https://github.com/changpeng approved this pull request. https://github.com/llvm/llvm-project/pull/153880 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU] w/a for s_setreg_b32 gfx1250 hazard with MODE register (PR #153879)

https://github.com/changpeng approved this pull request. https://github.com/llvm/llvm-project/pull/153879 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits