llvm-project.git/clang/test/CodeGenOpenCL/amdgpu-features.cl, branch users/MaskRay/spr/main.elf-orphan-placement-remove-hasinputsections-condition Unnamed repository; edit this file 'description' to name the repository. [AMDGPU] Add a new target gfx1152 (#94534) 2024-06-06T16:16:11+00:00 Shilei Tian i@tianshilei.me 2024-06-06T16:16:11+00:00 1ca0055f45abe7e4d484a0af457fc20be318c8e2 






[test] %clang_cc1 -emit-llvm: remove redundant -S
2024-05-05T00:00:29+00:00

Fangrui Song
i@maskray.me

2024-05-05T00:00:28+00:00

c5de4dd1eab00df76c1a68c5f397304ceacb71f2

And replace -emit-llvm -o - with -emit-llvm-only





And replace -emit-llvm -o - with -emit-llvm-only







AMDGPU: Define a feature for v_dot4_f32_* instructions (#84248)
2024-03-06T22:37:03+00:00

Changpeng Fang
changpeng.fang@amd.com

2024-03-06T22:37:03+00:00

96813de52d09d983d14a30ef5e2b4b8658f8e952

FeatureDot11Insts (dot11-insts) for:
  v_dot4_f32_fp8_fp8, v_dot4_f32_fp8_bf8,
  v_dot4_f32_bf8_fp8, v_dot4_f32_bf8_bf8




FeatureDot11Insts (dot11-insts) for:
  v_dot4_f32_fp8_fp8, v_dot4_f32_fp8_bf8,
  v_dot4_f32_bf8_fp8, v_dot4_f32_bf8_bf8






[AMDGPU][GFX12] VOP encoding and codegen - add support for v_cvt fp8/… (#78414)
2024-01-24T11:21:15+00:00

Mariusz Sikora
mariusz.sikora@amd.com

2024-01-24T11:21:15+00:00

cfddb59be2124f7ec615f48a2d0395c6fdb1bb56

…bf8 instructions

    Add VOP1, VOP1_DPP8, VOP1_DPP16, VOP3, VOP3_DPP8, VOP3_DPP16
    instructions that were supported on GFX940 (MI300):
    - V_CVT_F32_FP8
    - V_CVT_F32_BF8
    - V_CVT_PK_F32_FP8
    - V_CVT_PK_F32_BF8
    - V_CVT_PK_FP8_F32
    - V_CVT_PK_BF8_F32
    - V_CVT_SR_FP8_F32
    - V_CVT_SR_BF8_F32

---------

Co-authored-by: Mateja Marjanovic <mateja.marjanovic@amd.com>
Co-authored-by: Mirko Brkušanin <Mirko.Brkusanin@amd.com>




…bf8 instructions

    Add VOP1, VOP1_DPP8, VOP1_DPP16, VOP3, VOP3_DPP8, VOP3_DPP16
    instructions that were supported on GFX940 (MI300):
    - V_CVT_F32_FP8
    - V_CVT_F32_BF8
    - V_CVT_PK_F32_FP8
    - V_CVT_PK_F32_BF8
    - V_CVT_PK_FP8_F32
    - V_CVT_PK_BF8_F32
    - V_CVT_SR_FP8_F32
    - V_CVT_SR_BF8_F32

---------

Co-authored-by: Mateja Marjanovic <mateja.marjanovic@amd.com>
Co-authored-by: Mirko Brkušanin <Mirko.Brkusanin@amd.com>






[AMDGPU] Do not emit `V_DOT2C_F32_F16_e32` on GFX12 (#78709)
2024-01-19T14:36:27+00:00

Jay Foad
jay.foad@amd.com

2024-01-19T14:36:27+00:00

ed123880826cd9a4acdcd05409b1fac4203a436a

That instruction is not supported on GFX12.
Added a testcase which previously crashed without this change.

Co-authored-by: pvanhout <pierre.vanhoutryve@amd.com>




That instruction is not supported on GFX12.
Added a testcase which previously crashed without this change.

Co-authored-by: pvanhout <pierre.vanhoutryve@amd.com>






[AMDGPU][GFX12] Add 16 bit atomic fadd instructions (#75917)
2024-01-18T13:01:09+00:00

Mariusz Sikora
mariusz.sikora@amd.com

2024-01-18T13:01:09+00:00

3e6589f21c8088d823377b648aaa1a20ec1bc3d5

- image_atomic_pk_add_f16
- image_atomic_pk_add_bf16
- ds_pk_add_bf16
- ds_pk_add_f16
- ds_pk_add_rtn_bf16
- ds_pk_add_rtn_f16
- flat_atomic_pk_add_f16
- flat_atomic_pk_add_bf16
- global_atomic_pk_add_f16
- global_atomic_pk_add_bf16
- buffer_atomic_pk_add_f16
- buffer_atomic_pk_add_bf16




- image_atomic_pk_add_f16
- image_atomic_pk_add_bf16
- ds_pk_add_bf16
- ds_pk_add_f16
- ds_pk_add_rtn_bf16
- ds_pk_add_rtn_f16
- flat_atomic_pk_add_f16
- flat_atomic_pk_add_bf16
- global_atomic_pk_add_f16
- global_atomic_pk_add_bf16
- buffer_atomic_pk_add_f16
- buffer_atomic_pk_add_bf16






[AMDGPU][NFC] Rename feature FP8Insts to FP8ConversionInsts (#78439)
2024-01-18T07:46:53+00:00

Mariusz Sikora
mariusz.sikora@amd.com

2024-01-18T07:46:53+00:00

264fd9e13e6006378b2d1de2851b39eec8e98225












[AMDGPU] Define new targets gfx1200 and gfx1201 (#73133)
2023-11-23T16:44:05+00:00

Jay Foad
jay.foad@amd.com

2023-11-23T16:44:05+00:00

cf1e0c0b07c09af6b72ee912a5e0529c8ff66cad

Define target names and ELF numbers for new GFX12 targets gfx1200 and
gfx1201. For now they behave identically to GFX11.




Define target names and ELF numbers for new GFX12 targets gfx1200 and
gfx1201. For now they behave identically to GFX11.






[AMDGPU] Add targets gfx1150 and gfx1151
2023-07-17T12:06:12+00:00

Jay Foad
jay.foad@amd.com

2023-07-17T08:34:45+00:00

92542f2a400024e8a878242afe8231e17df345e5

This is the target definition only. Currently they are treated the same
as GFX 11.0.x.

Differential Revision: https://reviews.llvm.org/D155429





This is the target definition only. Currently they are treated the same
as GFX 11.0.x.

Differential Revision: https://reviews.llvm.org/D155429







AMDGPU: Add basic gfx942 target
2023-05-10T15:51:06+00:00

Konstantin Zhuravlyov
kzhuravl_dev@outlook.com

2023-05-10T15:20:06+00:00

9d0572797233857397f3fdc35fffcfb490354f56

Differential Revision: https://reviews.llvm.org/D149983





Differential Revision: https://reviews.llvm.org/D149983