George Hotz
431666da74
POSTOPT=2 work ( #12012 )
...
* POSTOPT=2 work
* bugfixes
* add chain in one place
* tensor cores match
* better hcopt check
* match from old
* Change POSTOPT ContextVar value to 0
* we didn't need to check that
2025-09-04 16:55:56 -07:00
George Hotz
30eb42a69e
fix POSTOPT pad ( #11999 )
...
* fix POSTOPT=1
* fix some tests
* Revert "fix some tests"
This reverts commit 8ee058e206
2025-09-04 14:28:58 -07:00
qazal
da61b40604
some viz tests don't need track_rewrites ( #12010 )
2025-09-04 23:59:32 +03:00
qazal
be364a1adb
viz: add default tracing group ( #12009 )
...
This enables seeing rewrites in unit tests like `VIZ=1 python3 test/test_uop_graph.py TestUOpGraph.test_in_bounds_access_gated_local` that call graph_rewrite directly.
`@track_rewrites` keeps existing as an optional helper to organize larger traces.
2025-09-04 23:29:56 +03:00
chenyu
52166fd7eb
smaller test_ops inputs ( #12007 )
2025-09-04 16:22:33 -04:00
chenyu
dc8501af30
clean up wino tests ( #12008 )
...
removed the one that tests hcopt and added one for backward kernel counts
2025-09-04 16:14:55 -04:00
chenyu
8c720e8760
less iterations for symbolic double for loops ( #12006 )
2025-09-04 15:09:17 -04:00
George Hotz
70ce29b630
test pyrender ( #12005 )
...
* test pyrender
* make them print
* switch to pyrendered
2025-09-04 11:48:40 -07:00
George Hotz
560df206cc
split tc test ( #12003 )
...
* split tc test
* split hand coded opts
* remove some skipped tests
* skips on emulated
2025-09-04 11:47:56 -07:00
qazal
4996bb668b
load all traces before asserting in test_viz ( #12004 )
2025-09-04 21:34:48 +03:00
George Hotz
9dee724fc4
make EMULATE a context var ( #12002 )
...
* make EMULATE a context var
* fix test amx
2025-09-04 11:15:43 -07:00
George Hotz
09106e4aae
refactor and split test_linearizer ( #12001 )
...
* refactor and split test_linearizer
* forget that file
* imports
* remove from docs
* test gen float4
2025-09-04 10:53:07 -07:00
chenyu
fb71d1e5fd
delete some test_search tests ( #11998 )
...
TC_SEARCH_OVER_SHAPE was removed so should the tests
2025-09-04 11:19:49 -04:00
chenyu
ca7574cb2d
ci set PYTHONPATH for all ( #11997 )
2025-09-04 10:06:04 -04:00
nimlgen
e213b85810
cpu: add thread_id to worker ( #11995 )
2025-09-04 14:58:13 +03:00
qazal
35f37a64a9
viz: remove useless ctx.save and restore calls ( #11996 )
...
It's a UI no-op since we always set the styles right before drawing.
2025-09-04 14:56:41 +03:00
Sieds Lykles
572a3c15c6
Move Ops.SPECIAL arg to src ( #11918 )
...
* initial moving bound to src
* arg to src
* remove import
* fixup linearizer
* arg to src
* fix test_uop_graph
* fix more tests
* fix python renderer
* get const value from const uop
* ssimplify uop estimates
* fix webgpu locals
* fix old test
* gate Ops.SPECIAL in linearizer
* use ssimplify() for local/global_size
* remove toposort gate_parents_instead_of_self
* fix rendering in comment
* cleanup
* rename and add comments
* add BottomUpGate with test
2025-09-04 09:31:44 +02:00
George Hotz
5cf42dc4db
add Scheduler to replace Kernel with POSTOPT=2 ( #11924 )
...
* ** simple kernel to replace Kernel for postopt
* support old
* fix beam
* beaming
* beam on old
* bring tensor cores back
* raise
* postbeam
* test ops passes on mac
* skip that
* postopt default
* gate that
* fix tensor cores
* a few test fixes
* dsp fix
* tc fix
* loop
* support swap
* test_gemv
* fix beam for variable
* test opts from high level stuff
* range annoying
* compile slow
* metal slow
* better beam
* no POSTBEAM
* fix nolocals
* hc opt mostly works
* put that back
* lil
* some work
* fix that
* POSTOPT 2
* fix tests
* no postopt 2
* work
* back
* padded tensors cores
* shift_to
* postopt 0 passes?
* write PADTO
* fix padded tensor cores
* compare hcopt
* 18000 lines
* should pass tests
* fix rangeify
* put types back
2025-09-03 19:23:30 -07:00
chenyu
b13e071463
move test_winograd to unit test ( #11993 )
2025-09-03 21:47:32 -04:00
chenyu
edc8b99853
more tests that pass PTX now ( #11992 )
2025-09-03 21:18:14 -04:00
chenyu
ed2f45712b
remove skip PTX in test_arange ( #11991 )
...
all passes now
2025-09-03 20:45:19 -04:00
George Hotz
a5f2b4872a
use_tensor_cores is a heuristic ( #11989 )
...
* use_tensor_cores is a heuristic
* context
2025-09-03 17:05:10 -07:00
George Hotz
63e930fec3
apply_tensor_cores is a heuristic ( #11988 )
...
* apply_tensor_cores is a heuristic
* delete extra_opts
2025-09-03 16:39:33 -07:00
chenyu
d0e739453e
update many einsum tests ( #11981 )
...
correct the exception testing, and raise ValueError instead of assert when checking args
2025-09-03 15:40:20 -04:00
George Hotz
55e4bdd353
split_uop is a method ( #11984 )
2025-09-03 10:46:17 -07:00
ttomsa
1877eddde4
broadcast for upat ( #11940 )
2025-09-03 10:04:23 -07:00
George Hotz
5ed262982a
remove some tc hacks from BEAM ( #11980 )
...
* remove some tc hacks from BEAM
* cosmetic changes
* revert that
2025-09-03 09:59:10 -07:00
b1tg
6d53cac457
dtype fuzz: log need input > 0 ( #11979 )
...
Co-authored-by: b1tg <b1tg@users.noreply.github.com >
2025-09-03 12:10:42 -04:00
Jordan Chalupka
68e83b850f
nbytes should raise an exception when size is unlimited ( #11928 )
...
* nbytes should raise an exception when size is unlimited
* adding a test
2025-09-03 07:06:20 -07:00
Sieds Lykles
86e908db57
cast parents of int64 alu to int32 if possible ( #11977 )
...
* add overflows helper
* add rules
* x -> y
* check overflow of u too
* cleaner
* use alu instead of replace to preserve vectorization
* just one rule
* add test
2025-09-03 11:05:04 +02:00
Sieds Lykles
033184b3cb
parse_valid with non const rhs ( #11957 )
...
* const to using vmin/vmax
* add test
* convert to int
* remove left over part of and
2025-09-03 08:08:46 +02:00
Sieds Lykles
53eff8970a
add Ops.GEP to _min_max ( #11976 )
2025-09-03 07:07:54 +02:00
Sieds Lykles
d1d0960e6e
remove intermediate cast using bounds - weaker pattern ( #11974 )
2025-09-03 06:24:40 +02:00
Sieds Lykles
8a2846b31a
assert embedding input is integer dtype ( #11963 )
...
* cast embedding input
* raise error if not using int for index embedding
2025-09-03 01:44:26 +02:00
wozeparrot
d16cc6c012
feat: resume ckpt ( #11970 )
2025-09-02 15:47:48 -07:00
George Hotz
1b73993521
pyrender to render uops ( #11968 )
...
* pyrender to render uops
* new pyrender style
* pyrender works
* list str
* store render
2025-09-02 15:44:01 -07:00
chenyu
e921fb44ee
clean up testnvidia env ( #11969 )
2025-09-02 18:29:00 -04:00
chenyu
69dd1817d0
raise RuntimeError in merge_dicts instead of assert [pr] ( #11965 )
2025-09-02 17:18:44 -04:00
qazal
f750c15965
viz: add python marker ( #11952 )
...
* viz: add python marker
* remove duplicate
2025-09-02 23:44:00 +03:00
George Hotz
550cf2ca7f
tests from postopt ( #11964 )
...
* tests from postopt
* reraise is fine
2025-09-02 13:34:17 -07:00
qazal
b977ec0813
viz: axes domains cleanup ( #11962 )
2025-09-02 19:30:45 +03:00
nimlgen
897254ad6c
ci: add dev<->cpu copy speeds ( #11959 )
2025-09-02 15:22:44 +03:00
George Hotz
74040663bf
make ptrdtype a UOp property ( #11955 )
2025-09-01 16:35:43 -07:00
George Hotz
0dfca4e74b
add failing test for rangeify setitem ( #11954 )
2025-09-01 16:24:35 -07:00
wozeparrot
7c21271a5f
feat: end_lr envvar ( #11953 )
2025-09-01 14:53:07 -07:00
chenyu
6a40216724
correct bf16 fuzz input in test_dtype_alu ( #11933 )
...
it was using float16 inputs, now it's uint16 then convert to bf16
2025-09-01 10:52:26 -04:00
chenyu
965ea59b16
test_dtype_alu use AMD_LLVM from helpers ( #11950 )
2025-09-01 10:03:17 -04:00
b1tg
a9f07c31bc
fix amd llvm sqrt ( #11936 )
...
* fix amd llvm sqrt
* lint
---------
Co-authored-by: b1tg <b1tg@users.noreply.github.com >
Co-authored-by: chenyu <chenyu@fastmail.com >
2025-09-01 09:31:14 -04:00
qazal
0a53e72f70
viz: fix trace duration in python test decoder ( #11949 )
2025-09-01 14:32:25 +03:00
qazal
27c9ed5a84
viz: more consistent naming of events ( #11948 )
...
* s/shapes/events in test_viz
* s/bufs/events in the memory packer
2025-09-01 14:16:47 +03:00
