George Hotz
ddda9420be
push contract through cast to fix test_float2_acc ( #5581 )
...
* push contract through cast to fix test_float2_acc
* no_vectorized_alu applies to cast too
2024-07-19 09:30:26 -07:00
chenyu
3f590c3b31
some limit_dims to limit global merging ( #5489 )
...
only supports merging dims in a way that does not surpass limit, no splitting yet
2024-07-19 12:17:46 -04:00
George Hotz
e04704faff
put acc first again ( #5580 )
2024-07-19 08:55:19 -07:00
chenyu
fc5b9f8dc9
Kernel.required_optimizations and Kernel.hand_coded_optimizations returns self ( #5576 )
...
[run_process_replay]
2024-07-19 10:55:14 -04:00
qazal
da34e1f617
scheduler refactors from the fuse_index branch ( #5579 )
...
* make simple_pads a safe set
* use is for comparing base
* 1 should continue
2024-07-19 16:23:31 +03:00
qazal
ecf88bb775
move assign_targets assignment ( #5578 )
2024-07-19 20:29:50 +08:00
George Hotz
0ad87021e2
move acc to end ( #5568 )
...
* move acc to end
* confirmed pictures are the same
* relax that
* Update test_ops.py
2024-07-19 03:06:52 -07:00
George Hotz
2de82b8a5d
remove get_lazyop_info ( #5570 )
...
* don't use get_lazyop_info more
* keep that min
* no ptx for that test
2024-07-19 03:05:33 -07:00
nimlgen
9d7edc9269
hcq rename HCQCompat -> HCQ ( #5577 )
2024-07-19 11:34:17 +03:00
chenyu
2b2f8ad18c
failed example of float2 acc no long applies ( #5573 )
...
* failed example of float2 acc no long applies
* # noqa: E501
2024-07-19 02:40:04 -04:00
chenyu
efccb1c3ba
swap global for size 3 too ( #5567 )
...
hc path resnet on green 10% faster
2024-07-18 23:31:15 -04:00
chenyu
abe29a05b0
swap first and last global in hcopt / hc tc path ( #5566 )
2024-07-18 18:54:44 -04:00
George Hotz
946da97820
swap action ( #5565 )
...
* swap action
* don't allow same action expressed differently
* oops, was reversed
* one line is fine
* only swap
2024-07-18 15:19:40 -07:00
qazal
e7a057c20f
retire replay_schedule ( #5563 )
2024-07-18 23:07:02 +03:00
qazal
50aba32ea8
hotfix: don't assert process replay in master. ( #5562 )
...
This is because https://github.com/tinygrad/tinygrad/actions/runs/9996754763/job/27631802686 ran exactly when master changed state, causing the diff to assert.
if [run_process_replay] is green pre merge it's ok.
2024-07-18 22:05:00 +03:00
George Hotz
223d9283ee
fix float4 acc by moving contracts ( #5559 )
2024-07-18 11:30:16 -07:00
George Hotz
c41cd55556
remove vectorized alu in expander [run_process_replay] ( #5561 )
2024-07-18 11:27:40 -07:00
kormann
c951bc99af
fix abstracions2 printout ( #5557 )
2024-07-18 21:21:45 +03:00
George Hotz
a7fec05acc
fix broken store rule [run_process_replay] ( #5558 )
...
* remove unused store rule [run_process_replay]
* that should preserve behavior i think
2024-07-18 11:07:34 -07:00
chenyu
f5af98c450
failed test case that DEFINE_ACC no long uses float4 ( #5555 )
...
* failed test case that DEFINE_ACC no long uses float4
* line
2024-07-18 10:55:59 -07:00
George Hotz
923e0fe0b8
fix half4 folding ( #5556 )
2024-07-18 10:47:39 -07:00
chenyu
12e6771209
failed test case for unrolled half4 ( #5552 )
2024-07-18 13:05:52 -04:00
George Hotz
d1a7279605
indexing fold with casted bool ( #5551 )
...
* cast bool is where
* universal transform is wrong
2024-07-18 10:02:29 -07:00
qazal
fdfc0015a7
[run_process_replay] for opencl/openpilot ( #5009 )
...
* lil reset script
* find the prg
* use lower_schedule_item
* add process replay back
* cleanups
2024-07-18 19:42:33 +03:00
kormann
2c4add6844
pretty print lazy op per default ( #5505 )
...
* pretty lop
* min diff
* walrus
* fix
* min diff
* simplify
* pretty helper function
* ws
* pretty uop upat
* tests
* stricter tests
* test passes
* ws
* stronger upat test
* delete print_tree
* min diff
* stricter exp test
* fix merge
* stronger uops eval test
* +readable and deep upat test
* +readable and deep upat test
* sort inv fix
* fix
* revert allowed_len
2024-07-18 09:34:08 -07:00
nimlgen
c30092e56d
amd remove useless barrier ( #5550 )
2024-07-18 18:05:33 +03:00
nimlgen
4e9d2b1615
nv memory_barrier command ( #5548 )
2024-07-18 16:23:11 +03:00
qazal
6d7cd34250
more save_schedule tooling ( #5547 )
2024-07-18 15:59:53 +03:00
qazal
0ad1672d5f
fuse indexing (LazyOp creation) ( #5506 )
...
* bring FUSE_AS_ONE_KERNEL back
* operands need reshape?
* fused but arange didnt fold
* something deeply wrong
* yay, fused
* derive broadcasts
* s/input/reduce_input
* _fixup_ones proved a point
* this is what it takes
* down to 3 required reshapes:
1. output_shape
2. the second reduce merge dims
3. remove dims for above reshape
* start real reshapes
* resolve shape in the edges pre lazyop
* outputs are the same shape
* rewrite1: just the reduce
* more correct
* fuse_as_one_kernel
* closer
* this passes
* dont rerun info
* dont need these
* not needed
2024-07-18 14:09:17 +03:00
wozeparrot
6ccb2390c3
feat: update_benchmark_staging ( #5529 )
2024-07-17 20:40:57 -07:00
chenyu
e569c927cf
remove Kernel.shape_offsets [run_process_replay] ( #5544 )
...
the only use case now can be further simplified
2024-07-17 23:16:47 -04:00
George Hotz
fa7e734b49
MetaOps.KERNEL ( #5543 )
2024-07-17 19:41:23 -07:00
George Hotz
d3b098299d
add failing regression test for image ( #5540 )
...
* add failing regression test for image
* tg type
* simpler test
* don't realize image to image casts caused issue
* simple pad
2024-07-17 17:27:18 -07:00
wozeparrot
218e157f00
benchmark on update_benchmark_staging ( #5541 )
2024-07-17 17:11:52 -07:00
wozeparrot
8845a5dbfd
feat: begin immediate ( #5539 )
2024-07-17 16:11:21 -07:00
George Hotz
a6e70f8a71
clean up expand function [run_process_replay] ( #5538 )
...
* clean up expand function [run_process_replay]
* lil cleaner
* add a type
2024-07-17 15:02:00 -07:00
qazal
61ee02e93d
start multireduce lowerer work (var/std) ( #5537 )
...
* multireduce no-opts works
* passed test_var_multireduce
* cleanup
* double reduce
* extra check for range_group
* more checking for range_groups
* cleaning up debug prints
* cleanup diff
* linters
* revert kernel changes
* these are uops toposort
---------
Co-authored-by: timmy <timmy0x@proton.me >
2024-07-17 23:43:46 +03:00
qazal
67ea4af01f
depth first recurse_reduceops ( #5536 )
...
* early recurse
p2
* yea cache shouldnt be there
2024-07-17 23:27:53 +03:00
Francis Lam
c4eb30a04c
test/test_linearizer_failures: add a new beautiful_mnist one ( #5531 )
...
* test/test_linearizer_failures: add a new beautiful_mnist one
this one is from a DEPTH=2 fuzz_linearizer search
* add GPU to test_failure_40
---------
Co-authored-by: chenyu <chenyu@fastmail.com >
2024-07-17 16:27:04 -04:00
qazal
0259d76183
use Context only in replaying Kernel [run_process_replay] ( #5535 )
2024-07-18 03:46:14 +08:00
George Hotz
1a68854766
PatternMatcher add ( #5532 )
...
* PatternMatcher add [run_process_replay]
* f4 dynamic
* test_failure_36 is fixed
* fix PTX
2024-07-17 12:44:42 -07:00
qazal
d3c137d478
utility for computing reduceop output_shape ( #5534 )
...
* refactor to reduce_st
* update lazy
2024-07-17 22:40:07 +03:00
qazal
0a7872a62f
use exec_alu in uops flop counting ( #5511 )
...
* use exec_alu for uops flop counting
* deal with sint
2024-07-17 22:39:27 +03:00
qazal
a7706e05f9
option to [skip_process_replay] ( #5533 )
2024-07-17 22:30:46 +03:00
chenyu
4193095f67
fix handcode_opt.py with DEBUG=2 ( #5530 )
...
only one ast per kernel now
2024-07-17 14:50:47 -04:00
chenyu
466555cd17
touchup Tensor.interpolate ( #5525 )
...
* touchup Tensor.interpolate and Tensor.lerp
rewrite lerp to save one sub and thus flops.
use Tensor.lerp for interpolate and some minor cleanups
* revert lerp change
2024-07-17 13:35:57 -04:00
George Hotz
1242b302fa
expand UOps with rewrite rules ( #5501 )
...
* expand UOps with rewrite rules [run_process_replay]
* progress
* much closer
* close, way less bugs
* bunch of expander tests
* fix contract
* ops tests pass
* fix barrier
* mostly passing
* bitcast in expanded ops
* support more expand merges
* all tests pass maybe
* fix empty EXPAND
* fix LIN fuzzing
* add ALL_SAME assert
* all same
* all same work
* raise CompileError
* pass fuzz linearizer
* revert whitespace
* fix nv tensor core test
* fix mypy
* bug fix
* fuzzer passes
* put tests back
* expand arg to idx
2024-07-17 10:17:50 -07:00
George Hotz
158221b36b
expand tests from uop_expander [run_process_replay] ( #5524 )
...
* expand tests from uop_expander
* more changes from the branch
2024-07-17 09:22:36 -07:00
George Hotz
42c25cc961
fix fixup_ast ( #5523 )
...
* fix fixup_ast
* these lin failures are fixed
2024-07-17 08:52:21 -07:00
qazal
fbe0233be3
infra for multi reduce asts ( #5522 )
...
* add reduce_info
* _recurse_reduceops base
* derive output shape
* refactor
* delete reduce_for_op
* save lines
* more line saving
2024-07-17 17:23:46 +03:00
