llvm-project.git/llvm/lib/Target/AMDGPU/AMDGPU.td, branch users/nico/python-2 Unnamed repository; edit this file 'description' to name the repository. AMDGPU: Implement ds_atomic_async_barrier_arrive_b64/ds_atomic_barrier_arrive_rtn_b64 (#146409) 2025-07-01T18:08:49+00:00 Changpeng Fang changpeng.fang@amd.com 2025-07-01T18:08:49+00:00 5035d20dcbcea1edced779148ac69b84d3c97577 These two instructions are supported by gfx1250. We define the instructions and implement the corresponding intrinsic and builtin. Co-authored-by: Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> 
These two instructions are supported by gfx1250. We define the
instructions and implement the corresponding intrinsic and builtin.

Co-authored-by: Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
 AMDGPU: Add MC layer support for load transpose instructions for gfx1250 (#146024) 2025-06-27T05:30:31+00:00 Changpeng Fang changpeng.fang@amd.com 2025-06-27T05:30:31+00:00 47292428785fe1b19f5253f1d4d0f229ce18d69a Co-authored with @jayfoad 
Co-authored with @jayfoad
 AMDGPU: Remove LDS-direct(param)-loads and VINTERP ops from gfx1250 support (#145631) 2025-06-25T05:44:35+00:00 Changpeng Fang changpeng.fang@amd.com 2025-06-25T05:44:35+00:00 2550a637a12710b53a4d939232228ba959d33ea3 






AMDGPU: Remove export and related instructions from gfx1250 support (#145624)
2025-06-25T02:59:26+00:00

Changpeng Fang
changpeng.fang@amd.com

2025-06-25T02:59:26+00:00

3de2af3ef56c66de2f20695fc8854684095f5d50












AMDGPU: Remove Formatted MUBUF instructions from gfx1250 support (#145590)
2025-06-24T21:17:13+00:00

Changpeng Fang
changpeng.fang@amd.com

2025-06-24T21:17:13+00:00

fe8a26263a123be61f4c1badee1d234f02469060












AMDGPU: Remove MTBUF instructions from gfx1250 support (#145563)
2025-06-24T18:59:13+00:00

Changpeng Fang
changpeng.fang@amd.com

2025-06-24T18:59:13+00:00

ce4d21494764b69246540d4efb9a7631ad6dfe72












[AMDGPU] Replace dynamic VGPR feature with attribute (#133444)
2025-06-24T09:09:36+00:00

Diana Picus
Diana-Magda.Picus@amd.com

2025-06-24T09:09:36+00:00

a201f8872a63aa336e4f79a40e196b6c20c9001e

Use a function attribute (amdgpu-dynamic-vgpr) instead of a subtarget
feature, as requested in #130030.




Use a function attribute (amdgpu-dynamic-vgpr) instead of a subtarget
feature, as requested in #130030.






[AMDGPU] Add s_setprio_inc_wg gfx1250 instruction (#145152)
2025-06-22T19:52:05+00:00

Stanislav Mekhanoshin
rampitec@users.noreply.github.com

2025-06-22T19:52:05+00:00

40eee8ec7fb64dd1c6f15e8cd6e087f5d9f9d37e












[AMDGPU] Rename call instructions from b64 to i64 (#145103)
2025-06-22T04:42:09+00:00

Stanislav Mekhanoshin
rampitec@users.noreply.github.com

2025-06-22T04:42:09+00:00

fa0b84f23c08994ce4e780f7c406e981d37599b1

These get renamed in gfx1250 and on from B64 to I64:

  S_CALL_I64
  S_GET_PC_I64
  S_RFE_I64
  S_SET_PC_I64
  S_SWAP_PC_I64




These get renamed in gfx1250 and on from B64 to I64:

  S_CALL_I64
  S_GET_PC_I64
  S_RFE_I64
  S_SET_PC_I64
  S_SWAP_PC_I64






[AMDGPU] Add s_wait_xcnt gfx1250 instruction (#145086)
2025-06-20T19:28:18+00:00

Stanislav Mekhanoshin
rampitec@users.noreply.github.com

2025-06-20T19:28:18+00:00

affcc5e728c86260590ae398c136d43ac6cfbfb0