Marat Dukhan

`fp16_alt_to_fp32_value` and `fp16_ieee_to_fp32_value` fail the unit test under Emcripten/Asm.js: ``` [ FAILED ] 1 test, listed below: [ FAILED ] FP16_ALT_TO_FP32_VALUE.negative_denormalized_values ``` ``` [ FAILED ] FP16_IEEE_TO_FP32_VALUE.negative_normalized_values [ FAILED ]...

High-level functions which use Winograd transform work and pass the tests. Need to investigate.

Integration with deep learning frameworks

21

NNPACK needs to be integrated into deep learning frameworks to deliver performance benefits to end-users. If you would like to work on such integration, please comment here. @ajtulloch contributed basic...

Example instructions: - VGATHERDPS (AVX-512 & KNCNI) - VSCATTERDPS (AVX-512 & KNCNI) - VADDSETSPS (KNCNI) - VPADDSETSD (KNCNI)

Problems with the current code: - Functionality is very complex and scattered all over the place - There are likely bugs and/or inefficiencies - Unclear how it works with Golang...

RETURN pseudo-instruction for non-constant values

1

`RETURN` pseudo-instruction currently accepts only constant values. - `RETURN` should accept general-purpose registers for functions with integer or pointer return type. Lower to `STORE.RESULT` for Go and to `MOV[ZX/SX](rax/eax, reg)`...

Currently PeachPy does not object the syntax xmmN(k0). This is illegal according to Intel spec (`aaa = 000` used to encode no mask)