readme : partial OpenCL GPU support via CLBlast (ggml-org#863)

* ggml : CLBlast support as in llama.cpp

Building with CLBlast speeds up whisper.cpp ~2x on low end / older AMD APUs (CPU with integrated GPU) such as the A9.

Usage:
WHISPER_CLBLAST=1 make

* CMake/Makefile : CLBlast support as in llama.cpp

Building with CLBlast speeds up whisper.cpp ~2x on low end / older AMD APUs (CPU with integrated GPU) such as the A9.

Usage:
```
Makefile:
cd whisper.cpp
WHISPER_CLBLAST=1 make

CMake:
cd whisper.cpp ; mkdir build ; cd build
cmake -DWHISPER_CLBLAST=ON  ..
make
```

* Update README.md

Added OpenCL Build Instructions

* Instruction: Partial OpenCL GPU support via CLBlast

Added build instructions and examples for Make and CMake to support OpenCL enabled GPUs.

Author: trholding

README.md

@@ -20,6 +20,7 @@ High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisp
 - Zero memory allocations at runtime
 - Runs on the CPU
 - [Partial GPU support for NVIDIA via cuBLAS](https://github.com/ggerganov/whisper.cpp#nvidia-gpu-support-via-cublas)
+- [Partial OpenCL GPU support via CLBlast](https://github.com/ggerganov/whisper.cpp#opencl-gpu-support-via-clblast)
 - [C-style API](https://github.com/ggerganov/whisper.cpp/blob/master/whisper.h)
 
 Supported platforms:
@@ -311,6 +312,29 @@ make clean
 WHISPER_CUBLAS=1 make -j
 ```
 
+## OpenCL GPU support via CLBlast
+
+For cards and integrated GPUs that support OpenCL, the Encoder processing can be largely offloaded to the GPU through CLBlast. This is especially useful for users with AMD APU's or low end devices for up to ~2x speedup.
+
+First, make sure you have installed `CLBlast` for your OS or Distribution: https://github.com/CNugteren/CLBlast
+
+Now build `whisper.cpp` with CLBlast support:
+
+```
+Makefile:
+cd whisper.cpp
+make clean
+WHISPER_CLBLAST=1 make -j
+
+CMake:
+cd whisper.cpp ; mkdir build ; cd build
+cmake -DWHISPER_CLBLAST=ON  ..
+make clean
+make -j
+cp bin/* ../ 
+```
+
+
 Run all the examples as usual.
 
 ## Limitations