dinhv

Use only certain values in a range

1

Is there a way to choose only certain values in a given range? For example `manipulator.add_parameter(IntegerParameter('Kb', 1, 72)) manipulator.add_parameter(IntegerParameter('Mb', 72, 144))` and the run function def run(self, desired_result, input, limit):...

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...

NESI default arguments for rtc_compute

2

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...

Usage of shared memory for tiled convolution

5

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...

Integrating add_codegen_annotations to conv_pipe_fwd

16

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...

Tuning of a CNN

1

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...

Usage of sgemm.cucl in full connected networks

1

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...

Structure of a wisdom file

1

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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op_wisdom_t ``` Can you explain...

Understanding the input and output files when running ops-prof

1

When running the ops-prof mode with the following command ``` boda 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)/sgemm-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/sgemm-gen5/wisdom.wis" --op-tunes="(ocl-def=(use_be=ocl,),ocl4-16-4lm0(use_be=ocl,MNt=4:4,MNb=16:16,Kb=4,use_local_mem=0),ocl-4-16-4-lm2-vw4=(use_be=ocl,MNt=4:4,MNb=16:16,Kb=4,use_local_mem=2,vw=4),ocl-4-16-4-lm3-vw4=(use_be=ocl,MNt=4:4,MNb=16:16,Kb=4,use_local_mem=3,vw=4))" ``` it gets as input the following file sgemm-ops-debug.txt `(str_vals=(type=sgemm),nda_vals=(a=(dims=(K=2048,M=2048)),b=(dims=(K=2048,N=2048)),c=(dims=(M=2048,N=2048))))`...