Cheese

George Cozma | Editor in Chief of Chips and Cheese
All opinions are my own

[Cheese @System360Cheese]

All this does is make me even more excited for Supercomputing 2026!

[@fclc cmp lea char @FelixCLC_]

wowsers this feels like a lifetime ago;;

[Cheese @System360Cheese]

@johnrheritage Every ISA on the market decodes into micro-ops including Arm and RISC-V... that is not new or unique to x86...

[Cheese @System360Cheese]

And I ask again, what does the ISA have to do with power consumption?

The answer is it doesn't... SoC design is what impacts power consumption...

[Vadim Yuryev @VadimYuryev]

Finally! Looks like CES will be interesting.

AMD has been quite behind for a while and also have the worst battery life in laptops.

Time to change that.

[Cheese @System360Cheese]

Wut?
Ok, let's say that AMD "only" sells 8 million accelerators between 2026 and 2030... if they are some how only making... let's utterly lowball this and say 10K worth of profit on each accelerator... that is still 80 billion dollars of profit in 4 years...
This makes no sense

[Nick Dorsey @Midnight_Captl]

I’ve been saying for awhile now that it’s not a certainty that AMD gets to continue their accelerator program long term

Many AMD proponents will say that AMD will sell all the silicon they can produce, but that’s a false qualification

All useable silicon will be bought �� AMD will have the right to build their accelerator program long term

AMD is in a very precarious position. Stuck between the insatiable demand for NVIDIA hardware, and the insatiable demand for custom ASICs. I don’t think its an exaggeration to say that Google, Meta, and Amazon would all strongly prefer more wafer allocation to their own custom silicon programs rather than wafers go to AMD

Ultimately if there isn’t sufficient ‘true’ demand for AMD accelerators, then the program will fall further behind until it no longer makes economic sense to pursue it

[Cheese @System360Cheese]

I don't get why the 2 lines are blurred out...
The slightly darker highlighted runs are just the same system and CPU which is checked via CPUID...
Like this is just several 9950X3D2 runs...

[HXL @9550pro]

https://t.co/dpgJM4Er7l

[Cheese @System360Cheese]

At the @AMD booth, they had multiple versions of the new @OpenComputePrj OAC (Open Accelerator Card) with both air and liquid cooled versions which are aiming to replace the older PCIe CEM standard in the datacenter with support for up to 5000W per double wide liquid cooled OAC.

[Cheese @System360Cheese]

@Microsoft MAIA 300 spotted on the floor!

[Cheese @System360Cheese]

@FujitsuOfficial is showing off their dual socket Monaka server here @OpenComputePrj

[Cheese @System360Cheese]

So... @RaptorCompSys and @Solid_Silicon still has not given any updates on their planned POWER9 replacement 3 years after promising a replacement...

Will there be a replacement for POWER9?

Is Solid Silicon still working on a general purpose CPU?

Many questions, no answers...

[Cheese @System360Cheese]

So... it has been over 2 years since this announcement and we have had radio silence from both @RaptorCompSys and @SolidSilicon as to what the status of this is and Solid Silicon has removed the S1 CPU from their website earlier this year...

[Cheese @System360Cheese]

At the @intel booth, they were demoing Crescent Island running both LLMs and Video Generation along with the new Open Accelerator Card form factor.

[Cheese @System360Cheese]

I like fat caps and I can not lie!

[Cheese @System360Cheese]

Here are some more panels, but I couldn't tell what SoCs these panels belong too?

[Cheese @System360Cheese]

Oooo, saw some ASE Panels on the OCP showfloor!
Looks like they are the panels that Venice will be using.

[Cheese @System360Cheese]

Oooo, saw some ASE Panels on the OCP showfloor!
Looks like they are the panels that Venice will be using.

[Cheese @System360Cheese]

So... I just saw the verdict in @Qualcomm vs. @Arm and the TLDR is that Qualcomm won on the ALA and business interference arguments with Arm prevailing on the TLA arguments...

Here is the link to the full Jury verdict on CourtListener (https://t.co/JaCxdEip8n)

[Cheese @System360Cheese]

I spy with my little eye some LPXs...

[Cheese @System360Cheese]

Diamond Rapids Motherboard spotted at @OpenComputePrj

[Cheese @System360Cheese]

@opinali @OpenComputePrj @AMD I mean... it is a server oriented conference... I wouldn't expect any client parts from anyone at OCP Summit...

[Cheese @System360Cheese]

Here @OpenComputePrj 2026, @AMD's Lisa Su showed off their upcoming Verano CPU which pairs Zen 6 CCDs with what looks like 4 memory controller dies that support LPDDR5X on the top and bottom of the IO dies.

[Cheese @System360Cheese]

@JumboShrimp787 @OpenComputePrj @AMD That is the most likely explaination to me, they could also be dies with xGMI connections as well for connecting to GPUs...

[Cheese @System360Cheese]

@stock_exch @SquashBionic The FP4 number should be 208 PF not 208 TF and the GPU bandwidth should be 120 TB/s not 120 GB/s...

[Cheese @System360Cheese]

@pilerks1 @OpenComputePrj @AMD Doubtful...
Likely is using SOCAMM modules like Vera does...