* 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
* 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>
* 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>
George Hotz
Comma Device