By: Michael S (already5chosen.delete@this.yahoo.com), August 25, 2015 1:58 pm
Room: Moderated Discussions
Afterthoughts of Core-M vs Cherry Trail comparison.
Until yesterday I didn't look at Intel Core-M and Cherry Trail too closely, but yesterday I did.
And what I saw? Top of the line Core-M (M-5Y71) is better than top of the line Cherry Trail (x7-Z8700) in every single aspect except selling price:
Single Threaded Performance - ALOT better
Graphics - ALOT better
Multithreaded FP - ALOT better
These two were expected
What I didn't expect is that Core-M is also significantly ahead in multithreaded Integer tests. So far ahead that it seems that multithreaded Integer performance per Watt is likely about equal.
Jumping from mobile to HPC.
It means that it was very possible, and may be still possible for Intel to base their GPGPU competitor on Sandy Bridge derivative. Probably, not exactly Broadwell and not exactly Skylake, but slightly different 14nm core. Tuned for 2.5-3 GHz operation instead of 4 GHz, probably same number of execution ports as sandyB, less aggressive bypasses, less agressive divide units etc... In short, slightly compromised absolute performance relatively to Broadwell and Skylake, but almost the same performance per Watt at low frequency and at 20-30% smaller area. Now let's put 33 such cores running at 1.4/2.6 GHz (Base/Turbo) on a single huge die. Or, may be, if it fits, 39 cores with Base=1.2 GHz. Or somthing in the middle, you got the idea.
Just like in the case of Core-M vs Cherry Trail we will get ALOT better (than KNL) single threaded performance, ALOT better scalar multithreaded FP and about the same multithreaded integer at about the same power envelop. Now, you are asking: "Who cares? this thing are important for smart customers, but the whole point of KNL is pleasing stupid customers by showing them that we can run LINPACK as fast the biggest baddest Maxwell and than slightly faster yet! You variant is not even close!".
And here you understood why AVX512 is a huge mistake. Core-based GPGPU killer absolutely needs AVX-1024. Or wider.
Until yesterday I didn't look at Intel Core-M and Cherry Trail too closely, but yesterday I did.
And what I saw? Top of the line Core-M (M-5Y71) is better than top of the line Cherry Trail (x7-Z8700) in every single aspect except selling price:
Single Threaded Performance - ALOT better
Graphics - ALOT better
Multithreaded FP - ALOT better
These two were expected
What I didn't expect is that Core-M is also significantly ahead in multithreaded Integer tests. So far ahead that it seems that multithreaded Integer performance per Watt is likely about equal.
Jumping from mobile to HPC.
It means that it was very possible, and may be still possible for Intel to base their GPGPU competitor on Sandy Bridge derivative. Probably, not exactly Broadwell and not exactly Skylake, but slightly different 14nm core. Tuned for 2.5-3 GHz operation instead of 4 GHz, probably same number of execution ports as sandyB, less aggressive bypasses, less agressive divide units etc... In short, slightly compromised absolute performance relatively to Broadwell and Skylake, but almost the same performance per Watt at low frequency and at 20-30% smaller area. Now let's put 33 such cores running at 1.4/2.6 GHz (Base/Turbo) on a single huge die. Or, may be, if it fits, 39 cores with Base=1.2 GHz. Or somthing in the middle, you got the idea.
Just like in the case of Core-M vs Cherry Trail we will get ALOT better (than KNL) single threaded performance, ALOT better scalar multithreaded FP and about the same multithreaded integer at about the same power envelop. Now, you are asking: "Who cares? this thing are important for smart customers, but the whole point of KNL is pleasing stupid customers by showing them that we can run LINPACK as fast the biggest baddest Maxwell and than slightly faster yet! You variant is not even close!".
And here you understood why AVX512 is a huge mistake. Core-based GPGPU killer absolutely needs AVX-1024. Or wider.
