OpenCL-TTL

OpenCL-TTL copied to clipboard

Add ability to record and replay lists of ASync copies

1

By linking togeather a multiple ASync copies into a single user level transation the opportunity for gather scatter type operations becomes possible. This patch only allows this in the row...

chrisgearing

A small number of bugs/issues had crept into the code and so a CI runtime of the C samples as been added to try to prevent this. The issues fixed...

chrisgearing

TTL contains code code that looks like the follow // static inline TTL_int_void_sub_tensor_t attribute((overloadable)) TTL_step_buffering(TTL_import_double_const_void_tensor_buffering_t *const db, const TTL_tile_t next_tile); ...snip result.prev_tile = TTL_create_empty_tile(); TTL_step_buffering(&result, first_tile); return result; } ...snip...

chrisgearing

TTL contains code code that looks like the follow // ``` static inline TTL_int_void_sub_tensor_t __attribute__((overloadable)) TTL_step_buffering(TTL_import_double_const_void_tensor_buffering_t *const db, const TTL_tile_t next_tile); ...snip result.prev_tile = TTL_create_empty_tile(); TTL_step_buffering(&result, first_tile); return result; }...

chrisgearing

Add ability to record and replay lists of ASync copies

1

By linking togeather a multiple ASync copies into a single user level transation the opportunity for gather scatter type operations becomes possible. This patch only allows this in the row...

chrisgearing

Add Read The Docs

2

This migrates the existing Markdown documentation inside the `doc` folder to ReadTheDocs, which makes it more accessible and readible. Creating a ReadTheDocs account should be free and then we can...

noamzaks

Hey, I'm using TTL API for Import/Export memory transactions. However, In some cases I need the option to create global memory fence between some transactions. and for this case I...

amirBish

Element size argument in TTL create tensor API

1

Hey, In the official TTL documents it's shown that user could create TTL_tensor with providing: ``` 1- the pointer of the allocated memory 2- TTL_shape 3- TTL_layout. (without providing the...

amirBish

Whether it can support the mobile GPU well?

1

I learned from the Adreno GPU optimization manual(https://developer.qualcomm.com/download/adrenosdk/adreno-opencl-programming-guide.pdf?referrer=node/6114): Avoid using the function called async_work_group_copy. It is often tricky for the compiler to generate the optimal code to load local memory,...

ckhfor

Add the ability to Align Tensor Rows and Planes

2

Some platforms require that the Rows/Planes of tensors are aligned to a specific value. Add two macros TTL_DEFAULT_INTERNAL_ALIGNMENT and TTL_DEFAULT_EXTERNAL_ALIGNMENT to set these alignement values. The default if undefined is...

chrisgearing