9457 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
George Hotz	68959be05d	precompute weights for opencl	2022-07-08 10:56:48 -07:00
George Hotz	d8e7f1f8bc	opencl type ignore	2022-07-08 10:33:55 -07:00
George Hotz	ae335b6d3e	opencl works, but tons of kernels	2022-07-08 10:22:04 -07:00
George Hotz	5b66d1bb0b	begin fixing up opencl	2022-07-08 10:20:14 -07:00
George Hotz	7e17f2ae8d	fix mypy, add TODOs	2022-07-08 09:57:22 -07:00
George Hotz	8557ed88df	use ast engine for merged reduceop	2022-07-08 09:37:40 -07:00
George Hotz	3656a5615a	MERGE_ELEMENTWISE_INTO_REDUCE	2022-07-08 09:32:28 -07:00
George Hotz	ca9532ce29	less lines, and typing found a bug	2022-07-08 08:57:12 -07:00
George Hotz	2035b89e54	wooo 1k lines	2022-07-08 08:44:57 -07:00
George Hotz	2a8c1071d9	cleanups	2022-07-08 08:36:31 -07:00
George Hotz	e6733286df	unify conv and reduce	2022-07-08 08:27:30 -07:00
George Hotz	9c34b3eef3	tighten up gpu kernels	2022-07-08 07:59:04 -07:00
George Hotz	563bf2d8e8	force input/weight to be contiguous (uncached)	2022-07-08 07:40:30 -07:00
George Hotz	1cf805a56a	fix no MERGE_MOVEMENT_OPS bug	2022-07-08 07:27:53 -07:00
George Hotz	c0ef998b48	remove finished todo	2022-07-07 11:39:25 -07:00
George Hotz	715e335c60	fix types	2022-07-07 11:36:09 -07:00
George Hotz	9ee8426c51	much better cache	2022-07-07 11:32:00 -07:00
George Hotz	eb6696c3a5	only childless elementwise ops get merged	2022-07-07 11:13:25 -07:00
George Hotz	04e7e4104c	track graph children and make lazycache use weak references	2022-07-07 11:01:18 -07:00
George Hotz	001cfe83a2	local	2022-07-07 10:05:26 -07:00
George Hotz	2720ef49ca	extra and test and tuple	2022-07-07 10:01:33 -07:00
George Hotz	059fe94700	junk import	2022-07-06 21:47:38 -07:00
George Hotz	a61a4d09ad	merge conv and binary op	2022-07-06 08:27:26 -07:00
George Hotz	6e0015095f	LBCACHE	2022-07-04 16:05:19 -07:00
George Hotz	7a5acd3ace	cache	2022-07-04 16:04:48 -07:00
George Hotz	d5d9cffe7c	training param for batchnorm	2022-07-04 13:28:03 -07:00
George Hotz	21c78b9316	can be v slow	2022-07-04 13:23:34 -07:00
George Hotz	46bce4156f	CL profiling	2022-07-04 13:22:12 -07:00
George Hotz	34f43ea10e	LAZY and CLCACHE are defaults	2022-07-04 13:09:15 -07:00
George Hotz	425b0dcd58	sorry linecount, CLCACHE	2022-07-04 12:52:04 -07:00
George Hotz	b7afd83267	track cl mem used	2022-07-04 12:19:00 -07:00
George Hotz	5ef62c33a1	SHUFFLE_MOVEMENT_OPS is OPT=3	2022-07-04 09:55:30 -07:00
George Hotz	d5de8452c6	dashed loadops	2022-07-04 09:50:56 -07:00
George Hotz	e74adcce5c	refactoring	2022-07-04 09:25:19 -07:00
George Hotz	0bdb021880	separate realize functions for different ops	2022-07-04 09:07:22 -07:00
George Hotz	81b73f97a3	Optiimzation (#355) ... * constant folding into kernels * that opt worth it? * fix mypy * ast one kernel * save 2 lines in conv kernel * debug print kernel count * cl debugging * early realize inputs * refactor Device	2022-07-04 08:58:57 -07:00
George Hotz	df7976248b	be lazy with the gpubuffer copies for host for constant folding	2022-07-03 23:04:14 -07:00
George Hotz	4d4ea47ca7	one more line	2022-07-03 17:28:42 -07:00
George Hotz	02cd8510cb	cleanups	2022-07-03 17:23:20 -07:00
George Hotz	d89542640a	hmm, typechecker isn't checking everything	2022-07-03 17:12:51 -07:00
George Hotz	6b0aa2a902	sorry about the line count, this is a good optimization	2022-07-03 17:11:13 -07:00
George Hotz	748618530b	tests will run at okay speed now?	2022-07-03 16:41:52 -07:00
George Hotz	c3d13893f9	add SHUFFLE_MOVEMENT_OPS, exactly 1000 lines	2022-07-03 16:30:42 -07:00
George Hotz	e6e43e820e	should fix tests	2022-07-03 16:06:11 -07:00
George Hotz	71a812fbf2	elementwise_ops	2022-07-03 15:29:38 -07:00
George Hotz	d7aad46758	test lazy also, make TestMNIST faster	2022-07-03 15:19:19 -07:00
Nicklas Boman	64d986bc8b	add mypy to ci testing (#353)	2022-07-03 15:11:35 -07:00
George Hotz	57ebce8d67	first LazyBuffer optimizations	2022-07-03 15:09:16 -07:00
George Hotz	a1a20891ef	more types	2022-07-03 14:03:34 -07:00
George Hotz	99b287ed87	typechecks	2022-07-03 13:54:30 -07:00