Announcement

Collapse
No announcement yet.

Intel Developing "oneAPI" For Optimized Code Across CPUs, GPUs, FPGAs & More

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • #11
    Originally posted by coder View Post
    IMO, the main win from CUDA and OpenCL is by exposing enough of the hardware's performance bottlenecks and strengths that you can architect your code around it. As such, if Intel's oneAPI is any good, I'd expect it to look structurally similar.
    The problem is that when you're trying to support CPUs, GPUs and FPGAs it's inevitably going to end up either as something that's "More like OpenACC than OpenACC" or just multiple very different APIs crammed in under one.

    Comment


    • #12
      Originally posted by L_A_G View Post
      The problem is that when you're trying to support CPUs, GPUs and FPGAs it's inevitably going to end up either as something that's "More like OpenACC than OpenACC" or just multiple very different APIs crammed in under one.
      Are you aware that OpenCL already does support CPUs, GPUs, and FPGAs? Why should the oneAPI look more like OpenACC than OpenCL or be significantly more disjoint than OpenCL?

      Comment


      • #13
        Originally posted by coder View Post
        Are you aware that OpenCL already does support CPUs, GPUs, and FPGAs? Why should the oneAPI look more like OpenACC than OpenCL or be significantly more disjoint than OpenCL?
        Having actually used OpenCL I know from experience CPU mode is mostly there to make it so that you don't need to re-write the compute code in use cases where a compute-capable GPU isn't available. Code that takes proper advantage of a GPU is always going to be far from the best solution on a CPU and the fact that OpenCL uses a subset of C doesn't help that much either as the best results on CPUs are typically reached by writing the critical parts of the compute code using code in (x86) assembly.

        I personally haven't tried it out, but the fact that support has been there for years and years, but the fact that FPGA compute, let alone OpenCL-based FPGA compute, hasn't taken off would suggest that it's not all that great. The only time I remember FPGAs gaining some kind of real ground in HPC was a bit before the first crypto-"currency" bubble burst when miners moved to FPGA miners due to their higher energy efficiency before moving on to ASIC miners not long after.

        Comment

        Working...
        X