7 Commits

Author	SHA1	Message	Date
Adeeb Shihadeh	cdfb090c7a	Wunused (#1841) ... * enable Wunused, first pass * unused stuff in snpe model * these are used on phone * handle sigint and sigterm in modeld * fix phone build * camera qcom * QCOM build works * delete unused camerad vars Co-authored-by: Comma Device <device@comma.ai> old-commit-hash: eb1aa3d831fd0d7fffd9aacec1accb0a5bdb0304	2020-07-09 09:25:32 -07:00
George Hotz	83f6ec221f	c++ify thneed to remove memory leaks (#1737) ... Co-authored-by: Comma Device <device@comma.ai> old-commit-hash: 01a486308d7fbcd661d8f8786c140222703f659a	2020-06-19 15:53:48 -07:00
Adeeb	d035394ce7	Add pre-commit hooks (#1629) ... old-commit-hash: ab83e48ec4f7c7ddaa742d9797b0d38646fdb268	2020-06-03 12:54:49 -07:00
George Hotz	6a68510918	remove the clCreateProgramWithSource interceptor (#1559) ... * remove the clCreateProgramWithSource interceptor * that's old code, thneed is better * label them thneed_, we shouldn't need to touch CL for anything not SNPE related old-commit-hash: b8571710e09e58b9e67170a9924eef79f32c480b	2020-05-24 03:33:36 -07:00
Comma Device	16c1926f64	wtf, how was that commented out and the tests still passed ... old-commit-hash: 495e0c4648b5c3d20709bb3e08f83dad62725c2d	2020-05-18 17:10:39 +00:00
George Hotz	988361dd92	This isn't bigmodel, but there's a lot of good stuff here (#1532) ... * bigmodel * more debug print * debugging bigmodel * remove the tanh, debugging * print images/buffers * disassemble the command queues * decompiler * dump the shaders * full disasm * support patching kernel and fixing convolution_horizontal_reduced_reads_1x1 * microbenchmark * 42 GFLOPS, 1 GB/s * gemm benchmark * 75 GFLOPS vs 42 GFLOPS * 115 GFLOPS * oops, never mind * gemm image is slow * this is pretty hopeless * gemm image gets 62 GFLOPS * this is addictive and still a waste of time * cleanup cleanup * that hook was dumb * tabbing * more tabbing Co-authored-by: Comma Device <device@comma.ai> old-commit-hash: 78a352a8ca8a948e86e7c752732e470f89d92280	2020-05-17 23:13:17 -07:00
George Hotz	206b6abe7d	thneed saves 45% of a core (#1512) ... * thneed runs the model * thneed is doing the hooking * set kernel args * thneeding the bufferS * print the images well * thneeds with better buffers * includes * disasm adreno * parse packets * disasm works * disasm better * more thneeding * much thneeding * much more thneeding * thneed works i think * thneed is patient * thneed works * 7.7% * gpuobj sync * yay, it mallocs now * cleaning it up, Thneed * sync objs and set power * thneed needs inputs and outputs * thneed in modeld * special modeld runs * can't thneed the DSP * test is weird * thneed modeld uses 6.4% CPU * add thneed to release * move to debug * delete some junk from the pr * always track the timestamp * timestamp hacks in thneed * create a new command queue * fix timestamp * pretty much back to what we had, you can't use SNPE with thneed * improve thneed test * disable save log Co-authored-by: Comma Device <device@comma.ai> old-commit-hash: 302d06ee709cb65dba39e836917f5693f0819efb	2020-05-15 13:53:01 -07:00