Intel CR 23.35.27191.9 Released As A Big Update To Their Open-Source GPU Compute Stack

[phoronix]

Phoronix: Intel CR 23.35.27191.9 Released As A Big Update To Their Open-Source GPU Compute Stack

Intel today published Compute-Runtime 23.35.27191.9 as their latest update to this open-source GPU compute stack enabling OpenCL and oneAPI Level Zero support on Linux and Windows. With this being their first tagged release since September, it's coming in heavy on changes...

https://www.phoronix.com/news/Intel-CR-23.35.27191.9

[coder]

Gotta love the Skylake iGPU support! Systems with those iGPUs (used up through Comet Lake) will continue to be in the field and under support contract for quite some time.

Fun fact: skylake iGPUs had half-rate fp64 arithmetic (i.e. relative to fp32)! They also had double-rate packed fp16. So, quite versatile, especially for their size and age. By gen 12 (Xe), Intel iGPUs have completely dropped native fp64 support!

[TemplarGR]

Gotta love the Skylake iGPU support! Systems with those iGPUs (used up through Comet Lake) will continue to be in the field and under support contract for quite some time.

Fun fact: skylake iGPUs had half-rate fp64 arithmetic (i.e. relative to fp32)! They also had double-rate packed fp16. So, quite versatile, especially for their size and age. By gen 12 (Xe), Intel iGPUs have completely dropped native fp64 support!

And nothing of value was lost. Consumers never needed fp64, and even in the enterprise its usage is rare. It would make no sense to waste silicon on tiny igpus for fp64 to be used only in demos and benchmarks.

[stormcrow]

And nothing of value was lost. Consumers never needed fp64, and even in the enterprise its usage is rare. It would make no sense to waste silicon on tiny igpus for fp64 to be used only in demos and benchmarks.

Another fun fact, the hardware used in the iGPUs is essentially the same in the scaled up ARCs and Xeons. That's the legacy of Larrabee (along with AVX and other such extensions). It doesn't matter. It's there and it'll eventually be used. Double precision acceleration is necessary in statistical simulations.

[TemplarGR]

Another fun fact, the hardware used in the iGPUs is essentially the same in the scaled up ARCs and Xeons. That's the legacy of Larrabee (along with AVX and other such extensions). It doesn't matter. It's there and it'll eventually be used. Double precision acceleration is necessary in statistical simulations.

No, this isn't true. Igpus do not have hardware fp64 since Xe (12th) generation. They have actually removed it from hardware and can only be used with emulation. I googled it. In the generation previous to Xe they did have it on silicon but was disabled and used with emulation. Arc is not the same silicon as the integrated chips, even though they share the architecture, there are many differences.

And it makes sense, Intel igpus are extremely underpowered to the point that they don't make sense for heavy applications that benefit from fp64. And the cpu cores are really powerful enough to emulate it when needed, for example for a student project etc. It is more efficient to not include it.

[coder]

And nothing of value was lost. Consumers never needed fp64,

Which is why your CPU doesn't have it, either.

...oh, wait.

No, you're just ignorant. Luckily, that's not a crime. Do you think OpenGL made it a requirement just for fun? Not if you care about numerical stability of matrix inversions. Don't forget that GPUs don't implement support for denormals, so fp32 doesn't get you as far as good 'ol x87 floating point.

Sure, you can use emulation, but at a considerable performance penalty. Why do you think even Nvidia and AMD consumer GPUs retain hardware fp64 support at 1:32?

and even in the enterprise its usage is rare. It would make no sense to waste silicon on tiny igpus for fp64 to be used only in demos and benchmarks.

Sure, if you exclude SQL databases, spreadsheets, CAD, statistical modeling, and probably even a fair amount of the financial software out there, then you might be right.

And it makes sense, Intel igpus are extremely underpowered to the point that they don't make sense for heavy applications that benefit from fp64. And the cpu cores are really powerful enough to emulate it when needed, for example for a student project etc. It is more efficient to not include it.

The iGPU in a regular Skylake i7 could sustain about 220 GFLOPS of fp64. That's about what all four CPU cores could manage, together. So, it effectively doubled your compute capacity. The real kicker is that it could do that at a mere 10 W, while it would take the CPU cores 90 W.

Now, if you had an Iris Pro iGPU, they doubled the EUs and we could start to talk about some real muscle. They even had a Broadwell with 3x the amount of EUs and 128 MB of eDRAM. Definitely more than enough horsepower to be interesting.

[Paradigm Shifter]

Can you actually buy 16GB A770s any more? I have one sitting on my shelf at work, but our IT supplier says they are no longer able to be sourced.

[coder]

Can you actually buy 16GB A770s any more? I have one sitting on my shelf at work, but our IT supplier says they are no longer able to be sourced.

Only the Intel-branded ones are discontinued. Those were sold as a "Limited Edition" model, so that's hardly surprising.

Currently, 16 GB models are available from ASRock, Sparkle, and Acer, for prices starting at $260.

https://www.newegg.com/p/pl?N=100007709%20601406707%20601110192%204841&ComboBundle=true

[zboszor]

The downside is that the new version still doesn't support LLVM 16 or newer.

[TemplarGR]

Which is why your CPU doesn't have it, either.

...oh, wait.

No, you're just ignorant. Luckily, that's not a crime. Do you think OpenGL made it a requirement just for fun? Not if you care about numerical stability of matrix inversions. Don't forget that GPUs don't implement support for denormals, so fp32 doesn't get you as far as good 'ol x87 floating point.

Sure, you can use emulation, but at a considerable performance penalty. Why do you think even Nvidia and AMD consumer GPUs retain hardware fp64 support at 1:32?


Sure, if you exclude SQL databases, spreadsheets, CAD, statistical modeling, and probably even a fair amount of the financial software out there, then you might be right.


The iGPU in a regular Skylake i7 could sustain about 220 GFLOPS of fp64. That's about what all four CPU cores could manage, together. So, it effectively doubled your compute capacity. The real kicker is that it could do that at a mere 10 W, while it would take the CPU cores 90 W.

Now, if you had an Iris Pro iGPU, they doubled the EUs and we could start to talk about some real muscle. They even had a Broadwell with 3x the amount of EUs and 128 MB of eDRAM. Definitely more than enough horsepower to be interesting.

Basically, the whole of your reply is a snarky attempt to prove to everyone to this forum that you are completely ignorant about coding....

You are confusing gpu compute fp64 with cpu fp64.....

Yes, cpus could calculate at fp64 since forever.... But we are talking about gpgpu here, remember? They are not the same thing. Their programing paradigms are not the same, and the vast majority of applications that use double precision floating point are not gpgpu apps. And even the apps that do use it, do not use it all the time, most of the calculations do not need it.

Also, while Skylate did have fp64, you are confusing theoritical throughput with realistic performance. Unless software does fp64 calculations all day with no branching, you are not seeing those 220glops, not in your dreams. Gpgpu has tons of latency, even on a SoC. While a cpu core has much less theoritical fp64 throughput, it doesn't stall nearly as much. Or else we wouldn't be using cpus at all, everything would have been gpu only by now....

In the end, i repeat, igpus do not need hardware fp64. Applications that for some reason need to run gpgpu fp64, can do it with emulation for a small performance hit. Anyone needing serious fp64 grunt, will use a dedicated gpu anyway. For igpus were silicon space matters, it is better to not have it and use the transistor budget for other things.