Monday, September 21st 2026

Intel Introduces "PISA" Virtual ISA for Greater GPU Software Portability

Intel today updated its Compute Runtime with support for Portable Instruction Set Architecture (PISA) format, a new virtual ISA and programming model for Intel GPUs. Unlike CPUs, where software commonly targets established ISAs such as Arm or x86, GPUs have their own native instruction sets and hardware-specific architectures. As GPU generations introduce new hardware capabilities, execution features, and native instructions, compilers targeting the machine ISA have to account for differences between architectures. A standardized virtual ISA changes this by introducing an abstraction layer between compiler output and the GPU's native machine code. Essentially, PISA provides a common compiler target that allows generalized code to be written once and then finalized for multiple compatible Intel GPU architectures.

With PISA, Intel aims to provide a stable and portable ISA for compilers that target Intel GPUs. This means that a workload compiled to PISA can potentially run across multiple compatible Intel GPU architectures without requiring architecture-specific code generation for each generation. The PISA representation can then be finalized into native machine instructions for the target GPU, allowing the same workload to take advantage of the capabilities of newer hardware where supported, without requiring changes to the original PISA code. This does not mean that every PISA workload will automatically run on every Intel GPU, however, as compatibility depends on the target architecture and the features and instructions used by the program. PISA is also not Intel's first virtual GPU ISA, as the company's existing vISA has long served as an intermediate representation for its GPU compiler stack, while PISA introduces a newer portable ISA and programming model.
For example, NVIDIA does something similar with its Parallel Thread Execution (PTX) virtual ISA, which serves as an intermediate representation between high-level CUDA code and the GPU's native machine code. PTX provides a hardware-independent compiler target while still exposing low-level GPU concepts to developers. If Intel's implementation follows a similar model, PISA will allow close-to-metal programming, essentially allowing code to operate very close to the actual hardware while still being written at a higher layer of abstraction. Intel itself lists close-to-the-metal performance, along with support for handwritten libraries and inline assembly, among PISA's goals.

Currently, PISA is at version 0.1, with supporting documentation on the OpenCL 3.0-based execution and memory model, and how the ISA defines data types like integers and floating-point numbers, as well as addresses, access to registers, and many other standard parts of ISA documentation. This also indicates that Intel's future GPU efforts will continue, as the company has invested significant resources in creating this.
Sources: Intel on GitHub, PISA, via Phoronix
Add your own comment

3 Comments on Intel Introduces "PISA" Virtual ISA for Greater GPU Software Portability

#2
_JP_
It supports back to the DG1. That is surprising because I didn't know it got enough adoption to result in development support.
Posted on Reply
#3
jdrch
meanwhile CUDA has existed for how long?
Posted on Reply
Nov 21st, 2026 09:06 PST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts