Intel Corporation

Clark F Nelson

Milind Baburao Girkar

Bratin Saha

Xinmin Tian

Stephen Junkins

David M Putzolu

Shoumeng Yan

Ying Gao

Seth Abraham

Robert Geva

Mohan Rajagopalan

Xiaocheng Zhou

Sai Luo

Hideki Ido

Kevin B Smith

Ravi Narayanaswamy

Rajiv Deodhar

Serge V Preis

Sergey Stanislavoich Kozhukhov

Tiger Chen

Patrick Xi

Sergey V Maslov

Jianfei Yu

Technologies for indirectly calling vector functions include a compute device that includes a memory device to store source code and a compiler module. The compiler module is to identify a set of declarations of vector variants for scalar functions in the source code, generate a vector variant address map for each set of vector variants, generate an offset map for each scalar function, and identify, in the source code, an indirect call to the scalar functions, wherein the indirect call is to be vectorized. The compiler module is also to determine, based on a context of the indirect call, a vector variant to be called and store, in object code and in association with the indirect call, an offset into one of the vector variant address maps based on (i) the determined vector variant to be called and (ii) the offset map that corresponds to each scalar function.

Technologies for indirectly calling vector functions

A computer system may comprise a computer platform and input-output devices. The computer platform may include a plurality of heterogeneous processors comprising a central processing unit (CPU) and a graphics processing unit) GPU, for example. The GPU may be coupled to a GPU compiler and a GPU linker/loader and the CPU may be coupled to a CPU compiler and a CPU linker/loader. The user may create a shared object in an object oriented language and the shared object may include virtual functions. The shared object may be fine grain partitioned between the heterogeneous processors. The GPU compiler may allocate the shared object to the CPU and may create a first and a second enabling path to allow the GPU to invoke virtual functions of the shared object. Thus, the shared object that may include virtual functions may be shared seamlessly between the CPU and the GPU.

Two way communication support for heterogenous processors of a computer platform

A computer-implemented method identifies a code segment which is to be customized to a plurality of different processor types. The method generates object code for the code segment, including generating a plurality of sections for the code segment, each of the plurality of sections being object code for the code segment customized for one of the plurality of different processor types, and generating a control section that causes a selected one of the plurality of sections to be called during execution of the object code in accordance with an executing processor's processor type.

Method and apparatus for supporting multiple processor-specific code

Growing community of inventors

Portland, OR, United States of America

Clark F Nelson