Cardyak

Inspired by @InstLatX64, today I'm introducing the #SiliconGang Microarchitecture Cheat Sheet: bit.ly/2JTplfJ This can be viewed by all, and it offers centralised information about CPU μarch design such as caches, buffers, instruction width, etc. Some notes below:

@dylan522p Inference ATLAS

$1,000 for whoever comes up with the best name replacement for InferenceMAX InferenceMAX 2.0 dropping soon but we have to rename it because HBO MAX sent us a cease and desist. We have all NVIDIA GPUs from h100 to GB300 on large MoEs with SOTA optimizations like Disagg PD tested

dl.acm.org/doi/epdf/10.11… "SHADOW: Simultaneous Multi-Threading Architecture with Asymmetric Threads" "dynamically balances ILP and TLP by executing out-of-order and in-order threads simultaneously on the same core" Could this be what AheadComputing is working on? #CPU #μarch

dl.acm.org/doi/epdf/10.11… "ATR: Out-of-Order Register Release Exploiting Atomic Regions" Interesting μarch idea here. Instructions that have finished execution but not been committed yet, and also do not contain conditional branches can free up their PRF entry early #CPU #μarch

@OneRaichu Great data! Did you manage to confirm if Darkmont or Cougar Cove and handle 2 taken branches per cycle?

This Gen Mobile phone SoC size

A19Pro with A18Pro area surveying data A19Pro 与A18Pro的面积测绘数据

@boris_dg N3P only offers a 6% density gain, so by default it’s not enough to shrink down from the size you mentioned to 99mm. There’s more to it than that, especially when you remember the CPU and GPU had extra functionality added which increases the transistor count.

@Cardyak A18 Pro is 109.72 mm² And it's normal to be smaller. It's N3P vs N3E.

Apple A19 Pro die shot Die Size 98.68mm² P-Core 2.966mm² P-Core with L2 & Shared Logic 5.486mm² E-Core 0.782mm² E-Core with L2 & Shared Logic 2.217mm² SLC 11.026mm² Somehow looks to be smaller than the A18 Pro (~104mm²) #Apple #iPhone #CPU #A19 tieba.baidu.com/p/10206320725?…

@realnvmd They share cores with the A Series SoCs featured in the iPhone. Firestorm is the M1 big core, A19P is the big core in the M5 as well, etc

@Cardyak Why aren't any of the M series diagrams in the Drive folder?

Updated the Apple core diagrams to properly reflect the unconventional ROB structures that are used Still lots of work to do, I need to separate the dispatch queues from the schedulers and research/confirm the L1 ICache bandwidth μarch Block Diagrams: bit.ly/32qLLew

@Frederic_Orange @onrefaitlemac Do you have die size estimates for these chips?

A19 Pro and A19 comparison (slide of @OnRefaitLeMac French famous podcast) #tsmc #apple #iphone

@MCH2024 There’s also mistakes on their diagram, the ARM documentation tells us there’s 6 FP execution units, not 5. We know this for a fact. Also the ROB increased by up to 25%, so it can’t be above 960

@Cardyak Geekerwan block diagram is completely different.

ARM's new μarches added to the block diagram repo Scarce info this year, these diagrams will be updated and mistakes corrected once more devices are released μarch Block Diagrams: bit.ly/32qLLew μarch Cheat Sheet: bit.ly/2JTplfJ #ARM #CPU #MicroArchitecture

Nice work from @highyieldYT and also @chipwise_tech, wish we had the mm2 measurements to be able to truly compare against the A18 & A18 Pro

@divBy_zero @handleym99 @MrMadbrain Interesting confession! I assume it saved enough area to be worth the compromise? How easily do you think ARM can expand the decode/allocate stage to 12 or even 16 wide?

@handleym99 @MrMadbrain @Cardyak Thanks, let me review and comment. Know up front I’m the guy who removed uop cache from ARM, so I’m biased. :)

Block diagrams for A19 P & A19 E by Apple. Info sourced by Geekerwan and the Apple Silicon Optimization Guide μarch Block Diagrams: bit.ly/32qLLew μarch Cheat Sheet: bit.ly/2JTplfJ #ARM #CPU #ARM #Apple #A19 #CPU #MicroArchitecture

@divBy_zero Would love to see them progress to 12 wide soon

@Cardyak Fixed length isa in the world of llvm and JITs. Burst 10-20 ops and branch. This is the Firestorm gold standard. Until sw changes behavior again, this is how to do it.

The IPC for the E Core is so high now, it's only slightly behind the P Core that was present in the A12 (Vortex)

Geekerwan's Initial Review of the A19 is out - bilibili.com/video/BV1cBp4z… P Core has ~12% more perf and 6% increase in IPC E Core has ~25% more perf and 17% increase in IPC If these result are accurate then the E core is simply a monster by this point. #iPhone #A19 #CPU #Apple

Looks like Apple’s A19-E Core is 6 wide

A19 Pro vs A18 Pro +6.0% better performance per clock vs prev gen