On 30.07.2019 09:51, Rodger Combs wrote:
This avoids using the CUDA SDK at all; instead, we provide a minimal
reimplementation of the basic functionality that lavfi actually uses.
It generates very similar code to what NVCC produces.
The header contains no implementation code derived from the SD
On 30.07.2019 09:51, Rodger Combs wrote:
This avoids using the CUDA SDK at all; instead, we provide a minimal
reimplementation of the basic functionality that lavfi actually uses.
It generates very similar code to what NVCC produces.
The header contains no implementation code derived from the SD
On Tue, Jul 30, 2019, at 09:57, Rodger Combs wrote:
> This avoids using the CUDA SDK at all; instead, we provide a minimal
> reimplementation of the basic functionality that lavfi actually uses.
> It generates very similar code to what NVCC produces.
Very very cool.
--
Jean-Baptiste Kempf - Pr
On 2019-07-30 15:51, Rodger Combs wrote:
This avoids using the CUDA SDK at all; instead, we provide a minimal
reimplementation of the basic functionality that lavfi actually uses.
It generates very similar code to what NVCC produces.
The header contains no implementation code derived from the SD
This avoids using the CUDA SDK at all; instead, we provide a minimal
reimplementation of the basic functionality that lavfi actually uses.
It generates very similar code to what NVCC produces.
The header contains no implementation code derived from the SDK.
The function and type declarations are d