George Hotz
e7b5d8a434
assembly/amd: more RDNA4 asm ( #14062 )
...
* rdna4 more
* asm
* fixes
* assembly/amd: handwritten wmma failing test
* passes
* wmma default hacks
* space
* 0 skips in rdna3/rdna4 disasm
* more RDNA4 tests
---------
Co-authored-by: qazal <qazal.software@gmail.com >
2026-01-08 05:09:37 -08:00
nimlgen
e372c841ba
hevc: beam in decode ( #14067 )
...
* hevc: beam in decode
* fine
* g
2026-01-08 15:47:16 +03:00
nimlgen
f3aceaa08b
hevc: fast decoder ( #14057 )
2026-01-08 15:20:37 +03:00
qazal
309197bca5
assembly/amd: test_roundtrip for cdna/rdna4 ( #14066 )
2026-01-08 21:03:13 +09:00
qazal
15a056715d
fix amd assembly IDE tests on macbook ( #14063 )
2026-01-08 17:27:52 +09:00
George Hotz
2db04d0696
assembly/amd: start adding RDNA4 support ( #14060 )
...
* assembly/amd: start adding RDNA4 support
* rdna4 asm
2026-01-07 21:19:30 -08:00
George Hotz
cb500466c2
assembly/amd: amd_asm_matmul ( #13989 )
...
* amd_asm_matmul
* dsl transform
* asm roundtrip
* fixed
* less
* better
* more
* simpler
* simplify
* lil
* simpler
* compact
* work
* cleanups
* simplify
* simpler
* cleanup
* name the regs
* simp
* big simp
* big simp
* simp
* acc grid
* fast
* stuff
* fast
* simpler
* owrks
* save vgprs
* save vgprs
* Compact
* less VGPRs
* after
* SQTT support
* fastest
* faster
* lil faster
* tile regs
* faster
* readable
* one more
* simpler
* lil simpler
* NO_GLOBAL skips early globals
* stock kernel
* cleanups
* cleanups
* one b reg
* safe reg changes
* acc is compact now
* remove confusing stuff
* sregs
* lds cleanups
* vopd
2026-01-07 20:11:05 -08:00
nimlgen
5bd4593eda
hevc: cleaner decoder ( #14056 )
...
* hevc: cleaner decoder
* nn
2026-01-07 18:29:30 +03:00
chenyu
c714881832
don't allow jit input to be const ( #14045 )
...
* don't allow jit input to be unbuffered like const
* just const to fix multi
* fix rnnt
2026-01-06 18:15:22 -05:00
wozeparrot
2b3e01e79c
tk: support sliced local -> reg load ( #14034 )
2026-01-06 05:33:24 -05:00
George Hotz
45f7fd073d
assembly/amd: pcode bug fixes ( #14032 )
...
* bring over pcode parser
* fixes
* pdf test
* delay alu
2026-01-06 00:15:48 -08:00
wozeparrot
21d0f6bb76
tk: flat global -> local load ( #14033 )
2026-01-05 23:35:53 -08:00
George Hotz
20653d2996
assembly/amd: make pdf.py code shine ( #14029 )
...
* assembly/amd: make pdf.py code shine
* no merge
* pdf2 is the future
* something
* regen enums
* test
* work
* remove junk
* write
* pcode extraction
* pdf2 passes all tests
* simplify
* simpler pdf
* late filter
* remove hacks
* simplify pdf2.py
* field type
* remove defaults
* don't export srcenum
* simple pdf.py
* simpler
* cleaner
* less hack in PDF
2026-01-05 18:49:40 -08:00
qazal
ea7b149ca5
viz command line tool ( #14030 )
2026-01-06 10:19:47 +09:00
nimlgen
70405b4f3c
am_smi: mi350 ( #14018 )
2026-01-05 13:10:56 +03:00
George Hotz
404eed6172
assembly/amd: improve tests for asm ( #14007 )
...
* assembly/amd: improve tests for asm
* upd
* skip
* tests
* re bug
* more passing
* cleanups
* cdna fixups
* improve tests, better CDNA parsing
* fix CI
* no defs
* simpler
* all pass
* from pdf
* regen
2026-01-04 15:14:08 -08:00
George Hotz
7ebda28692
assembly/amd: add CDNA support to asm ( #13982 )
...
* add CDNA support
* more cdna tests
* something
* fix more stuff
* more work
* simpler
* simplier
* cdna
* disasm
* less skip
* fixes
* simpler
2026-01-04 08:53:56 -08:00
George Hotz
34ea053b26
assembly/amd: clean up pcode, jit pcode instead of static ( #14001 )
...
* assembly/amd: clean up pcode
* regen
* lil
* jit the pcode
* sendmsg
* cleanups
* inst prefetch lol
2026-01-03 23:06:15 -08:00
George Hotz
8328511808
assembly/amd: make the emu.py code shine ( #13996 )
...
* assembly/amd: make the code shine
* lil clean
* reg back in pcode
* cleanups
* gen fma_mix
* no writelane hacks
* fn cleanup
* dead vgpr_write
* readable
* smem
* cleanup bench_emu
* speedups
* simpler and faster
* direct inst._fn
* split fxn
* Revert "simpler and faster"
This reverts commit e85f6594b3 .
* move lds to wavestate
* dispatcher
* pc in dispatch
* literal isn't wavestate
* cleanups + program
* one readlane
* exec_vop3sd in exec_vop
* cleaner exec_vopd
* fully merge VOP3P
* no special paths
* no SliceProxy
* low=0
* no bigint
* failing tests
* fma on python 3.13
2026-01-03 20:33:09 -08:00
qazal
bd55507ee4
RDNA3 fp16 assembly gemm 85 TFLOPS ( #13990 )
2026-01-03 18:34:23 +09:00
wozeparrot
6242a9d151
tk: no global copy and clear ranges ( #13988 )
2026-01-02 23:45:15 -08:00
wozeparrot
9f082e8e25
fa: split kv bwd into 2 kernels ( #13981 )
2026-01-02 18:45:51 -08:00
qazal
2cc64d71b0
simplify mi350x gemm / viz asm tests ( #13984 )
...
* mi350x gemm cleanup
* asm tests work
* simpler asm tests
2026-01-03 11:11:07 +09:00
George Hotz
0e282025ff
assembly/amd: split test_emu into hw tests ( #13966 )
...
* assmebly/amd: split test_emu into hw tests
* hw tests
* bugfixes
* more tests and fix
2026-01-02 08:04:56 -08:00
chenyu
2e2b5fed12
fix misspellings ( #13976 )
2026-01-02 10:37:38 -05:00
nietras
f49e4714af
Fix spelling errors in README for AMD assembly ( #13975 )
2026-01-02 10:15:20 -05:00
qazal
5f52266225
mi350x gemm: use Tensor.custom_kernel in asm test ( #13969 )
...
* mi350x gemm: use Tensor.custom_kernel in asm test
* A @ B for baseline
2026-01-02 18:30:50 +09:00
George Hotz
5a1a561e0f
assembly/amd: rdna4 autogen ( #13967 )
...
* assembly/amd: add pcode ds ops
* refactors
* fix ds op
* update autogen
* fix flat bug
* more tests
* fix emu test
* that's a hack
* generic
* fix all tests
* two tests
* fix test failure
* better
* remove __all__
* assembly/amd: fix autogen for RDNA4
2026-01-01 23:12:18 -05:00
wozeparrot
b27527f05a
fix: missed inner tracked range ( #13964 )
2026-01-01 18:09:57 -08:00
wozeparrot
ecbac8a338
tk: fa cleanups + causal test ( #13963 )
2026-01-01 18:05:00 -08:00
George Hotz
dfb813b760
assembly/amd: add pcode ds ops ( #13939 )
...
* assembly/amd: add pcode ds ops
* refactors
* fix ds op
* update autogen
* fix flat bug
* more tests
* fix emu test
* that's a hack
* generic
* fix all tests
* two tests
* fix test failure
* better
* remove __all__
2026-01-01 16:24:13 -05:00
b1tg
24723327ac
fix tc_up in search ( #13438 )
...
* tensor_core is missing from Scheduler
* test upcast max
---------
Co-authored-by: chenyu <chenyu@fastmail.com >
2026-01-01 10:25:08 -05:00
qazal
9726500de8
enable using assembly in Tensor.custom_kernel ( #13895 )
2026-01-02 00:12:01 +09:00
qazal
c0f52c9dcb
split assembly gemm to per arch directory ( #13953 )
2026-01-02 00:10:22 +09:00
qazal
6a5430ab00
correct args order in mi350x gemm ( #13949 )
2026-01-01 23:01:46 +09:00
George Hotz
2bb07d4824
assembly/amd: move Reg out of the psuedocode ( #13934 )
...
* assembly/amd: move Reg out of the psuedocode
* remove extra
* fix pcode tests
* simpler pcode
* simpler
* simpler
* cleaner
* fix mypy
2025-12-31 15:34:51 -05:00
George Hotz
f14428090f
assembly/amd: speed up emulator ( #13932 )
2025-12-31 13:32:25 -05:00
George Hotz
29402034a1
assembly/amd: cleanups to asm and emu ( #13912 )
...
* a bunch of cleanups
* ops are back
* bug fixes
* cleanups
* a lil simpler
* more refactors
* _disasm_vop1
* sops
* more
* continue
* more
* num_srcs
* simpler
* no _is16
* op cleanups
* isinstnace
2025-12-31 12:46:11 -05:00
George Hotz
b998a80b5d
assembly/amd: split generated stuff into enum/ins ( #13924 )
2025-12-31 10:10:52 -05:00
qazal
b23f4517ab
prep mi350x gemm for python dsl ( #13918 )
...
* start by pruning existing asm
* better branch names
* split to template and real instructions
2025-12-31 20:00:57 +09:00
qazal
3f3786ded9
mmapeak: fix compiler import ( #13915 )
2025-12-31 16:52:23 +09:00
George Hotz
0221b96761
assembly/amd: fix all ops tests ( #13910 )
...
* assembly/amd: fix all ops tests
* test_ops with smaller sizes
* ds store/load 2addr
2025-12-30 18:01:34 -05:00
George Hotz
efc99d0c55
assembly/amd: more refactors ( #13907 )
...
* assembly/amd: more refactors
* more refactors
* more refactors
* simpler emu
* generate.py
* regen all
* cleanups
* more
* work
* more readme
* lil
2025-12-30 16:13:24 -05:00
George Hotz
49d1bf93d6
assembly/amd: refactor asm.py to be simpler ( #13900 )
...
* assembly/amd: refactor asm.py
* assembly/amd: refactor asm.py to be simpler
* multiple fxns
* fast
* more tests pass
* regen
* stop decode
2025-12-30 13:51:40 -05:00
George Hotz
7e14cdcb06
assembly/amd: clean up clt/ctz hack ( #13901 )
...
* assembly/amd: clean up clt/ctz hack
* add breaks
2025-12-30 11:59:28 -05:00
George Hotz
69cdc8066d
assembly/amd: add dtype tests to AMD IDE CI ( #13899 )
...
* add dtype tests to AMD IDE CI
* more tests
* add trig preop
* regen done
* split to amd autogen
* simpler
2025-12-30 11:09:51 -05:00
George Hotz
9c89be5235
assembly/amd: fix v_perm_b32 + PC fixes ( #13897 )
...
* assembly/amd: fix v_perm_b32
* add pc support
2025-12-30 09:25:40 -05:00
George Hotz
2b838dc1d8
assembly/amd: fix AMD_LLVM=1 support in emulator ( #13881 )
...
* fix AMD_LLVM=1 support in emulator
* more llvm with dtype
* work
* more fixes
* fix dtype
2025-12-30 09:09:57 -05:00
qazal
b557c46233
assembly gemm clean ups, instructions for cli ( #13892 )
2025-12-30 16:14:06 +09:00
qazal
d7e1f26e3d
command line interface for sqtt viz ( #13891 )
...
* command line interface for sqtt viz
* cleanup
* api surface area
* this confuses the llms
* document
2025-12-30 12:33:21 +09:00