Stanislav Mekhanoshin
57c1e01e48
[AMDGPU] Don't allow wgp mode on gfx1250 ( #153680 )
...
- gfx1250 only supports cu mode
2025-08-14 15:16:56 -07:00
Stanislav Mekhanoshin
80d430df5d
[AMDGPU] Add MSG_SAVEWAVE_HAS_TDM on gfx1250 ( #153483 )
2025-08-13 23:01:50 -07:00
Stanislav Mekhanoshin
fc911fe928
[AMDGPU] Add HW_REG_IB_STS2 on gfx1250 ( #153479 )
2025-08-13 23:01:28 -07:00
Stanislav Mekhanoshin
cc0d227154
[AMDGPU] Disable s_setkill on gfx1250 ( #153471 )
2025-08-13 23:01:04 -07:00
Stanislav Mekhanoshin
d0ee82040c
[AMDGPU] Add s_barrier_init|join|leave instructions ( #153296 )
2025-08-12 15:07:07 -07:00
Stanislav Mekhanoshin
dddeb07c2e
[AMDGPU] Restrict packed math FP32 instructions to read only one SGPR per operand on gfx12+ ( #152465 )
...
Sec. 4.6.7.1 of the gfx1250 SPG states that if an SGPR is used
as an operand, only one SGPR will be read for both the low and high
operations. As a result, the corresponding bits in `op_sel` and
`op_sel_hi` must be the same when the operand is an SGPR.
Co-authored-by: Tian, Shilei <Shilei.Tian@amd.com>
Co-authored-by: Tian, Shilei <Shilei.Tian@amd.com>
2025-08-07 16:13:34 -07:00
Stanislav Mekhanoshin
b296ea9c14
[AMDGPU] s_get_shader_cycles_u64 gfx1250 instruction ( #152390 )
...
It is the same as reading SHADER_CYCLES_LO and SHADER_CYCLES_HI
but with a single instruction.
2025-08-06 15:32:28 -07:00
Stanislav Mekhanoshin
66392a8d8d
[AMDGPU] Add XNACK_STATE_PRIV and _MASK gfx1250 registers ( #152374 )
...
Co-authored-by: Pierre Vanhoutryve <pierre.vanhoutryve@amd.com>
Co-authored-by: Pierre Vanhoutryve <pierre.vanhoutryve@amd.com>
2025-08-06 14:44:17 -07:00
Stanislav Mekhanoshin
c3103068b7
[AMDGPU] Add more gfx1250 MC tests. NFC. ( #152388 )
...
These are already working, but left downstream.
2025-08-06 14:38:28 -07:00
Stanislav Mekhanoshin
184821b63d
[AMDGPU] Add gfx1250 DS MC tests. NFC. ( #152378 )
2025-08-06 14:15:35 -07:00
Stanislav Mekhanoshin
34aed0ed56
[AMDGPU] Add gfx1250 wmma_scale[16]_f32_32x16x128_f4 instructions ( #152194 )
2025-08-05 15:15:21 -07:00
Stanislav Mekhanoshin
d08c2977e8
[AMDGPU] Add MC support for new gfx1250 src_flat_scratch_base_lo/hi ( #152203 )
2025-08-05 14:35:48 -07:00
Stanislav Mekhanoshin
37fe9f6382
[AMDGPU] Add gfx1250 v_wmma_scale[16]_f32_16x16x128_f8f6f4 MC support ( #152014 )
...
This adds new VOP3PX2e encoding
2025-08-04 14:20:12 -07:00
Stanislav Mekhanoshin
dd0737bd99
[AMDGPU] gfx1250 v_wmma_ld_scale instructions ( #152010 )
2025-08-04 11:36:48 -07:00
Stanislav Mekhanoshin
d18511e10a
[AMDGPU] v_cvt_scalef32_sr_pk16_* gfx1250 instructions ( #151810 )
2025-08-02 15:21:59 -07:00
Stanislav Mekhanoshin
bc463c059c
[AMDGPU] v_cvt_scalef32_pk16_* gfx1250 instructions ( #151807 )
2025-08-02 12:42:12 -07:00
Stanislav Mekhanoshin
7598c25b5a
[AMDGPU] v_cvt_scale_pk16 gfx1250 instructions ( #151804 )
2025-08-02 10:45:02 -07:00
Stanislav Mekhanoshin
0988510ad4
[AMDGPU] gfx1250 v_perm_pk16_* instructions ( #151773 )
2025-08-01 20:12:35 -07:00
Stanislav Mekhanoshin
cc3932bf29
[AMDGPU] gfx1250 v_cvt_scalef32_sr_pk8_* instructions ( #151765 )
2025-08-01 19:25:57 -07:00
Stanislav Mekhanoshin
962ee7a568
[AMDGPU] gfx1250 v_cvt_scalef32_pk8_* instructions ( #151758 )
2025-08-01 18:29:45 -07:00
Stanislav Mekhanoshin
33abf05af4
[AMDGPU] gfx1250 v_permlane_* instructions ( #151749 )
2025-08-01 16:14:19 -07:00
Stanislav Mekhanoshin
c7bb105e97
[AMDGPU] Add v_cvt_scale_pk8_* gfx1250 instructions ( #151616 )
2025-07-31 18:55:59 -07:00
Stanislav Mekhanoshin
49d89bc9f4
[AMDGPU] Add gfx1250 cvt_pk|sr_fp8|bf8_f32 instructions ( #151595 )
2025-07-31 16:04:46 -07:00
Stanislav Mekhanoshin
e46d938ddf
[AMDGPU] v_cvt_sr_pk_f16_f32 gfx1250 instruction ( #151482 )
2025-07-31 12:25:55 -07:00
Stanislav Mekhanoshin
7f93487862
[AMDGPU] Add v_cvt_pk_f16_f32 instruction for gfx1250 ( #151469 )
2025-07-31 10:45:06 -07:00
Stanislav Mekhanoshin
ce40863209
[AMDGPU] Add v_cvt_sr|pk_bf8|fp8_f16 gfx1250 instructions ( #151415 )
2025-07-30 17:24:45 -07:00
Stanislav Mekhanoshin
b3b36d3590
[AMDGPU] Add V_ASHR_PK_I8_I32 and V_ASHR_PK_U8_I32 on gfx1250 ( #151389 )
2025-07-30 16:30:47 -07:00
Stanislav Mekhanoshin
62187a60e6
[AMDGPU] Add gfx1250 v_cvt_sr_pk_bf16_f32 instruction ( #151385 )
2025-07-30 14:02:03 -07:00
Jun Wang
82f00ea40a
[AMDGPU][MC] In GFX11+ v_pk_fmac_f16 should not allow DPP ( #148751 )
...
In GFX11+ the instruction v_pk_fmac_f16 should not allow DPP.
2025-07-30 13:44:24 -07:00
Stanislav Mekhanoshin
d70f228e83
[AMDGPU] Add gfx1250 V_ADD_{MIN|MAX}_{U|I}32 instructions ( #151379 )
2025-07-30 13:12:14 -07:00
Stanislav Mekhanoshin
3dfd939a16
[AMDGPU] gfx1250 V_{MIN|MAX}_{I|U}64 opcodes ( #151256 )
2025-07-29 19:13:51 -07:00
Changpeng Fang
9b4a44d63d
[AMDGPU] Update MC tests for vflat instructions on GFX1250 ( #151232 )
...
These instructions have already been supported (at MC layer) with
current upstream code base.
2025-07-29 15:39:14 -07:00
Stanislav Mekhanoshin
7eaf1f2b2d
[AMDGPU] Bitop3 opcodes for gfx1250 ( #151235 )
2025-07-29 15:36:56 -07:00
Stanislav Mekhanoshin
d99238263c
[AMDGPU] Implement v_mad_u32/v_mad_nc_u|i64_u32 on gfx1250 ( #151226 )
2025-07-29 15:06:35 -07:00
Changpeng Fang
6184ef1c2f
[AMDGPU] Support f64 atomics on gfx1250 ( #151172 )
...
- BUF/FLAT/GLOBAL_ADD/MIN/MAX_F64
- DS_ADD_F64
Co-authored-by: Konstantin Zhuravlyov <Konstantin Zhuravlyov@amd.com>
2025-07-29 09:41:00 -07:00
Changpeng Fang
67e2faa50c
[AMDGPU] MC support for async load and store on gfx1250 ( #151030 )
2025-07-28 13:45:37 -07:00
Changpeng Fang
ecd793cbb1
[AMDGPU] Add v_fma_mix_f32_f16 as an alias of v_fma_mix_f32 on gfx1250 ( #150502 )
...
Co-authored-by: Jay Foad <Jay.Foad@amd.com>
2025-07-24 12:42:30 -07:00
Changpeng Fang
34b6587249
[AMDGPU] MC support for load monitor instructions on gfx1250 ( #150496 )
2025-07-24 12:16:47 -07:00
Stanislav Mekhanoshin
a70f7dafc1
[AMDGPU] gfx1250 flat and global prefetch MC support ( #150455 )
2025-07-24 11:00:56 -07:00
Changpeng Fang
473bc0d188
[AMDGPU] Support V_FMA_MIX*_BF16 instructions on gfx1250 ( #150381 )
...
Co-authored-by: Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
2025-07-24 09:43:49 -07:00
Changpeng Fang
9a563b08e2
[AMDGPU] Support V_PK_MIN3/MAX3_NUM_F16 on gfx1250 ( #150326 )
...
Co-authored-by: Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
2025-07-23 15:15:19 -07:00
Changpeng Fang
203ea0a97e
AMDGPU: Support V_PK_MAXIMUM3_F16 and V_PK_MINIMUM3_F16 on gfx1250 ( #150307 )
...
Co-authored-by: Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
2025-07-23 13:45:01 -07:00
Stanislav Mekhanoshin
2346968807
[AMDGPU] Add V_ADD|SUB|MUL_U64 gfx1250 opcodes ( #150291 )
2025-07-23 13:17:56 -07:00
Changpeng Fang
bc1f85d234
AMDGPU: Support packed bf16 instructions on gfx1250 ( #150283 )
...
Co-authored-by: Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
2025-07-23 12:01:23 -07:00
Changpeng Fang
81185f7a2b
AMDGPU: Add packed fp32 instructions for gfx1250 ( #150253 )
...
Co-authored-by: Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
2025-07-23 10:26:50 -07:00
Changpeng Fang
d385e9d86b
AMDGPU: Support V_PK_ADD_{MIN|MAX}_{I|U}16 and V_{MIN|MAX}3_{I|U}16 on gfx1250 ( #150155 )
...
Co-authored-by: Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
2025-07-23 00:17:22 -07:00
Shilei Tian
fbeb801a71
[AMDGPU] Add support for v_cvt_pk_bf16_f32 on gfx1250 ( #150053 )
...
Co-authored-by: Mekhanoshin, Stanislav <Stanislav.Mekhanoshin@amd.com>
2025-07-22 20:00:50 -04:00
Stanislav Mekhanoshin
a0b854d576
[AMDGPU] MC support for gfx1250 scale_offset modifier ( #149881 )
2025-07-21 15:04:59 -07:00
Stanislav Mekhanoshin
b66084acd9
[AMDGPU] Verify asm VGPR alignment on gfx1250 ( #149880 )
...
Co-authored-by: Shilei Tian <Shilei.Tian@amd.com>
2025-07-21 14:23:27 -07:00
Jun Wang
234338852c
Reapply "[AMDGPU][MC] Allow op_sel in v_alignbit_b32 etc in GFX9 and … ( #149262 )
...
Fixed the problem in ce7851f6b7d59e50f92cb4e8dbfd801576c8b641.
This reverts commit ba271cc07334c74df55741701e5b22032c0cddbb.
2025-07-21 10:14:45 -07:00
