Dear Qualcomm,
In the QSML header file (qsml_info.h), am seeing below source ,
============
enum QSML_INFO_TYPE { QSML_BLAS_CPU=1, QSML_BLAS_CPU_AND_DSP=2 };
============
1. Does QSML supports execution on DSP ?
2. Latest version of QSML executes on Multi CPU and GPU using symphony or execution happening only on multi CPU ?
Thanks for your valuable time.
Regards,
Senthil
Hi Senthil,
Thank you for the question! We currently only support the CPU, but we continue to add support for new primitives and plan to support additional parts of the SoC in the future.
Thank you,
Matthew
Dear Mr Mbadin,
Thanks for your reply.
Am trying to use QSML along with caffe for MSM8996 chipset.
By default i cannot able to see any envirnonment variables for configuring the NUMBER_OF_THREADS and setting the number of CPU.
From the QSML document i can able to see some configuration for 8x26.
==========================
On x86 based systems, over subscription can be a problem for compute bound workloads as it causes cache thrashing which destroys performance. To prevent this, three environmental variables are available: SYMPHONY_NUM_THREADS= Controls the number of threads in the Symphony threadpool at launch time. QSML_NUM_THREADS= Controls the degree of parallelism of QSML functions, does not affect the size of the Symphony threadpool. The number of tasks launched by QSML will be the minimum of QSML_NUM_THREADS and SYMPHONY_NUM_THREADS.
============================
1. Is it applicable to Android 64 bit platform also ?
2. Kindly let me know ,how to configure the same for Android ?
Regards,
Senthil
Dear Madbin,
Thanks for your prompt response.
From the QSML FAQ page, there is a claim from QC that QSML is 5 times faster than Eigen.
I have measured the execution time of QSML and EIGEN integrated with caffee. Basically QSML and Eigen are performing convolution operations in my case. But QSML is only 1.8 times better compared to Eigen. I cannot able to see the 5x performance as claimed by QC.
Is there any configurations involved to get the maximum performance out of QSML ? like increasing/decreasing the number of threads involved, increasing/decreasing the number of cores involved ? Please share the interfaces/configurations (if any ) to achive 5x times performance than Eigen.
Regards,
Senthil
As mentioned in this thread several months ago, QSML only supported CPU back then. Just wondering, has GPU and/or DSP support been added since then? Thanks.
Dear Wilford ,
Good to see this thread is alive :)
Can you please tell me whether latest QSML supports DSP ?
Regards,
Senthil .
The current version of QSML does not run on the DSP. It's something we hope to do, but don't have a release date yet.
- Rick