[GitHub] [tvm] csullivan opened a new pull request #7687: [Texture support][Part 2] Add opencl adreno target, topi schedules, and relay op strategies

[GitBox <gi...@apache.org>]

csullivan opened a new pull request #7687:
URL: https://github.com/apache/tvm/pull/7687


   This PR introduces the `opencl --device=adreno` target and corresponding relay strategies. The conv2d schedules introduced here utilize spatial and channel-wise packing for the weights (OIHW4o) and activations (NCHW4c), respectively, both with vector length 4 to support lowering to RGBA texture memory. 
   
   **AutoTVM support**
   - AutoTVM doesn't currently capture the runtime context of extracted tasks. Without capturing information about the runtime buffer scopes, the codegeneration during tuning will only occur on flat buffers (not texture). For now, we utilize a cache_read("texture") stage when tuning to explore the performance benefit of utilizing texture memory. We believe that with a sufficient number of iteration's per trial, the copy time to texture prior to running the main compute kernel (which results from a cache_read) should be constant over the search and therefore not greatly impact the tuning results. 
   
   - Note that the cache_read is not needed when using the graph_runtime which supports passing in external texture buffers (see: PR#). Therefore, in the schedules one will observe `if autotvm.GLOBAL_SCOPE.in_tuning:` which around scheduling related to adding a cache_read to texture stage. 
   
   - The schedules can be simplified once either 1) AutoTVM tuning supports capturing this runtime information during task extraction (thereby removing the need for a cache_read to texture) or  2) once texture lowering in tir.TextureFlatten fully supports cache_read cancellation (external buffer forwarding through the cache_read). Cancellation currently is supported except for the cases of padding wherein an extra texture to texture copy results.
   
   RFC in progress, once posted I will add a link here.


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] elvin-nnov commented on pull request #7687: [Texture support][Part 2] Add opencl adreno target, topi schedules, and relay op strategies

[GitBox <gi...@apache.org>]

elvin-nnov commented on pull request #7687:
URL: https://github.com/apache/tvm/pull/7687#issuecomment-828674475


   Need to add FP32 support. Currently if we do not convert convolutions to FP16 and try to compile it for Adreno, we get the follow error: `AssertionError: No float32 input/output tensor support is currently provided for Adreno GPU`


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org