Introduction

Intel® Compute Libraries BLAS (Intel® clBLAS) is an open source implementation of Basic Linear Algebra Subprograms (BLAS) functions.

Intel® clBLAS is intended to accelerate mathematical operations using Intel® Processor Graphics - including HD Graphics and Iris® Graphics.

It includes optimized kernels for mathematical operations based on BLAS Library written with C and C++ interfaces.

Limitations

At this time Intel® clBLAS library supports only positive values for vector strides (i.e. incx, incy, ..).

Intel® clBLAS supports Intel® HD Graphics and Intel® Iris® Graphics and is optimized for:

Codename Skylake:
- Intel® HD Graphics 510 (GT1, client market)
- Intel® HD Graphics 515 (GT2, client market)
- Intel® HD Graphics 520 (GT2, client market)
- Intel® HD Graphics 530 (GT2, client market)
- Intel® Iris® Graphics 540 (GT3e, client market)
- Intel® Iris® Graphics 550 (GT3e, client market)
- Intel® Iris® Pro Graphics 580 (GT4e, client market)
- Intel® HD Graphics P530 (GT2, server market)
- Intel® Iris® Pro Graphics P555 (GT3e, server market)
- Intel® Iris® Pro Graphics P580 (GT4e, server market)
Codename Apollolake:
- Intel® HD Graphics 500
- Intel® HD Graphics 505
Codename Kabylake:
- Intel® HD Graphics 610 (GT1, client market)
- Intel® HD Graphics 615 (GT2, client market)
- Intel® HD Graphics 620 (GT2, client market)
- Intel® HD Graphics 630 (GT2, client market)
- Intel® Iris® Graphics 640 (GT3e, client market)
- Intel® Iris® Graphics 650 (GT3e, client market)
- Intel® HD Graphics P630 (GT2, server market)
- Intel® Iris® Pro Graphics 630 (GT2, server market)

clGPU currently uses OpenCL™ with multiple Intel® OpenCL™ extensions and requires Intel® Graphics Driver to run.

The definition of Intel® clBLAS may differ from BLAS interface in some cases, so be informed to check our implementation definition first.

Usage

To use the Intel® clBLAS Library, user has to allocate required by functions parameters in host memory space (The Library will automatically copy data to GPU memory space if needed). Next step is to fill allocated buffers with data and call the function from API. When computation ends result will be automatically copied back to host memory and stored as function definition describes.