laszloknowing intel cpu pricing somehow i doubt their gpu will be priced according to performance...

AleksandarKAdditionally, he states that Intel's current strategy revolves around price, not performance, providing best possible value to consumers.

lasThe 512 core version could have up to 14.7 TFLOPS depending on clockspeeds. FP32. Thats more than 2080 Ti.

I don't think it will beat 2080 Ti in gaming tho... xD but Intel could have something decent up their sleeve here. The 10th gen mobile chips are not bad in the iGPU department. 3 times faster than 9th gen on average and this is with very low core count and clockspeed.

Looking forward to see the performance on these 4 dGPU's.

HD64GExactly what any sensible person could predict for their 2nd try (Larrabee anyone?) on this market.

Our strategy revolves around price, not performance. First are GPUs for everyone at 200$

Massman3rd try - forgetting the i740 and doomed successor i752 en.wikipedia.org/wiki/Intel740

Turmania3 player competition is always good for us consumers. I do not expect instant fireworks from Intel and or Koduri himself. I would also love it if Nvdia goes into CPU business as well.

rvalenciaFor graphics, TFLOPS is nearly useless without good raster hardware.

Vya DomusNo it's not, TFLOPS is pretty much the only metric that can predict performance consistently, prove me wrong and show me any other hardware specification that is as reliable as TFLOPS. ROP count on the other hand is in fact almost useless as a metric used to estimate performance.

The general rule is that with time as the theoretical TFLOPS increases so does the actual performance. Pick any two random GPUs from the last decade and order their performance by the number of TFLOPS and I bet 80% of the time the prediction would be correct.

Vya DomusNo, you are mixing things up. AMD vs Nvidia shows that one TFLOP metric used for one architecture cannot 100% model the performance characteristics of another architecture. It does not contradict however my statement that TFLOPS are in general a good tool to approximate or predict performance. Please tell me how many 5 TFLOPS GPUs you find that consistently beat let's say an 8 TFLOP GPU, go ahead, find any pair as such, any generation, any manufacturer. Then tell me how many did you find that don't.



Important ? Yes. A good indicator of performance ? No, it's absolutely worthless.

GP104 : 64 ROPs, 8.8 TFLOPS
TU106 : 64 ROPs, 7.5 TFLOPS
TU104 : 64 ROPs, 10 TFLOPS

If we go by TFLOPS the ranking list should be :

TU104 > GP104
TU104 > TU106
GP104 > TU106

We know in fact it's more like :

TU104 > GP104
TU104 > TU104
GP104 < TU106

2 out 3, pretty damn good estimation considering I know absolutely nothing more than the theoretical FLOPS.

What does the ROP count tell us here ? Absolutely nothing, nada, zero. The unique Vega example which does seem to be limited by it's ROPs and that's an assumption by the way, because neither me or you knows that for sure it's known that GCN has other limitations and peculiarities. But there must a point where you need to realize TFLOPS are the dominant factor in all this and not the ROPs. It's a bizarre argument you got here, at the end of the day you can be limited by anything. You can extend this notion and claim that memory bandwidth is the most important thing because you can have as many execution ports and ROPs as you want if you don't have the memory bandwidth it's for nothing.

Here is a much more sensible explanation on why Vega performs better at higher clocks : unlike other GPU architectures GCN has scalar ports used for instructions that don't need multiple SIMD lanes, and we know GCN can very ineficient with it's 64 wide wavefront. It would make sense that for certain shaders that make use of a lot of instructions that cannot be efficiently scheduled in a wavefront would run a lot quicker if the clocks are higher.

Fact: ROP counts don't change that much generation to generation meanwhile shaders do, a lot.

I've read dozen of papers that had to do with graphics and compute and not once were ROP counts quoted as being indicators of performance, people always use GFLOPS theoretical or measured. It really boggles my mind why you all insist on this, it's simply not the case.



That's a funny statement because the only bits left in a GPU that are DSP like are in fact things like the ROPs or TMUs.

Terryg0t1tWhat's with the negative responses in the comment section?

ApocalypseeWhy this turns to be AMD vs nvidia thread? The fact is this is Intel next discrete GPU thread. The only thing I wished for is competitive price/performance and Intel really need to step up in their driver department. With Gen11 support integer scaling I'm pretty sure they will carry this to discrete card as well, with that we will (hopefully) see AMD and nvidia supporting them too.

lasThe 512 core version could have up to 14.7 TFLOPS depending on clockspeeds. FP32. Thats more than 2080 Ti.

I don't think it will beat 2080 Ti in gaming tho... xD but Intel could have something decent up their sleeve here. The 10th gen mobile chips are not bad in the iGPU department. 3 times faster than 9th gen on average and this is with very low core count and clockspeed.

Looking forward to see the performance on these 4 dGPU's.