16 Commits

Author	SHA1	Message	Date
George Hotz	e3c2579537	flip stride to match canonical	2022-06-26 19:19:53 -07:00
George Hotz	3e13e3330a	UNSAFE_FLOAT4 env	2022-06-22 08:20:29 -07:00
George Hotz	73415e20ab	this fixes 2 of the conv recomputes...but it's ugh	2022-06-22 08:18:12 -07:00
George Hotz	b2d5df6049	3 convs are being recomputed	2022-06-22 07:54:52 -07:00
George Hotz	ba2defcdef	elif False	2022-06-21 23:54:09 -07:00
George Hotz	9cb0522574	noargs	2022-06-21 23:48:58 -07:00
George Hotz	1074dfbb71	unstrided	2022-06-21 23:42:21 -07:00
George Hotz	9ae01290ba	pass in shorts	2022-06-21 23:33:23 -07:00
George Hotz	18d74c01b1	float4 opt	2022-06-21 21:27:51 -07:00
George Hotz	ff3d5fe962	debugging while we compile	2022-06-21 21:12:04 -07:00
George Hotz	9d06a86f7f	CL class, debugging	2022-06-21 20:16:29 -07:00
George Hotz	1ebc2b5545	lazy opencl works	2022-06-21 19:41:08 -07:00
George Hotz	c53c91f949	opencl tests passed (#347)	2022-06-21 18:57:09 -07:00
George Hotz	77f5cef8a6	First batch from lazy branch (#332) ... * test and helpers from lazy * lazy pt2	2022-06-18 17:26:59 -07:00
George Hotz	52505faaf4	minor	2022-06-16 15:53:45 -07:00
George Hotz	d5b3e18540	Accelerate with CL (#325) ... * accelerated opencl * it's running, it's just wrong * bugfix * model is correct in opencl * lazy image convert * add padding support to convolution * that stuff was all upstreamed * remove HEAD * oops * test_simple_conv2d_4 passes, add dilation support * put logic in ops_opencl * fix crash * hmm, stride seems okay * padding for batched inputs * just an issue now with cout%4 * op model still passes * fix startPackedInputChannel * pre and post processing ops for graph * don't break other llops * shapetrackering * reshapes are free * lazy movement ops	2022-06-16 15:40:52 -07:00