boda
boda copied to clipboard
moskewcz
Boda: A C++ Framework for Efficient Experiments in Computer Vision
With this feature, we will be able to select a specific GPU within a single system. We just have to pass "--use_platform_id" and "--use_device_id" if necessary to the boda command.
Currently, I'm limited to ~30% efficiency, and it's not clear why or what i might do to improve from there. Peak compute was roughly determined from microbenchmarks as ~256GF/s. Local...
I am trying to find the right way to see the code with the correct indentation. But, I couldn't find a solution yet. In every editor (vim, emacs, sublime, CLion)...
I've downloaded the .prototxt and .caffemodel files for Resnet from https://github.com/KaimingHe/deep-residual-networks and put them to the models and nets folder in Boda. However when I want to run them with...
I've added a new variable in `rtc_compute_t`: `uint32_t use_device_no; //NESI(default=0,help="device number of OpenCL device to use")` With this variable, a user can choose which device to use if multiple ones...
I tried to auto tune a convolution with following input parameters: `ops-prof --out-fn="%(boda_output_dir)/cnn_op_info.txt" --kg-tune-tag=ocl-def --func-mrd-toler="(cudnn_conv=4e-4)" --wisdom-out-fn="%(boda_output_dir)/wisdom.wis" --ops-fn="%(boda_test_dir)/conv-ops-debug.txt" --gen-data="(str_vals=(type=gen_data),nda_vals=(vi=(tn=float,v=0.0),mode=(tn=uint32_t,v=5)))" --wisdom-in-fn="%(boda_test_dir)/good_tr/conv-gen5/wisdom.wis" --op-tunes="(ocl-def=(use_be=ocl,),ocl-default=(use_be=ocl,MNt=32:16,MNb=8:16,Kb=8,k1conv=0,tconv=1,ipconv=0,tconv_max_ksz=19:19))"` This leads to a failure because the tuned kernel uses...
When running a CNN with "run_cnet" mode, Boda generates each convolution function of the CNN one by one and OpenCL compiles and run them one by one. The generated functions...
The existing auto-tuner in Boda is only able to tune one operation per call i.e. we have to pass the desired operation and some additional informations. What if we want...
Does the sgemm.cucl file have any usage for running a neural network in boda? When I run the run_cnet mode I don't see that the sgemm.cucl (or any related sgemm...
The ops-prof mode requires a wisdom file and also produces a wisdom file e.g. the wisdom file located in /boda/test/good_tr/sgemm-gen5 ```op_wisdom_t (str_vals=(type=sgemm),nda_vals=(a=(dims=(K=2048,M=2048)),b=(dims=(K=2048,N=2048)),c=(dims=(M=2048,N=2048)))) kg c 0105000000666C6F61740101DADA0000000000000000020000000008000000080000010000004D0008000001000000010000004E05000000666C6F61740000400000000000018DFC7924BA111898493CEEC41E948E463C000000FC7A094C2AB9884BA959044C4B0FDA4A3C67DA4A323AA34A9DEF964AD967514A7C9E3D4A38824F4A6F602F4A66C81A4AB8E51F4A41A7E7493C15F649221A044A2E68044A4A06FE49B145F9496113F049FEAF9949F9D7B34962ABC249A0AA8B4926668E495F8D9849C2849749C8F04846BC2C8EC384525FC54C377146186C064720434547E3D2CB46429383461957F0C43E79D2C4CF78EFC3227BEF43D4C952C30397FB4316AEBBC266358343B7788EC3AE4014427CAFEF410E14D7C36AE843C363438EC3317E47C405384DC38672A043BD0A404263419FC326BB55C3EB8FB7C3C4CD1644C14EB3C218915443941379C3 /op_wisdom_t ``` Can you explain...