Comments on: AMD Teases Details On Future MI300 Hybrid Compute Engines

By: D.R.

D.R. — Mon, 19 Jun 2023 21:15:12 +0000

More like its time for AMD to start developing their hw using carbon composites instead of silicon… you know, like graphene, synthetic diamonds and carbon nanotubes (they could also throw in adaptive/programmable metamaterials into the mix).

By: Timothy Prickett Morgan

Timothy Prickett Morgan — Mon, 09 Jan 2023 16:48:49 +0000

In reply to Hubert. Could not agree more. I can't wait to see if more memory (500 GB at a slower speed) is more important than shared memory (both the CPU and the GPU sharing the same HBM).

By: Hubert

Hubert — Mon, 09 Jan 2023 11:29:40 +0000

In reply to Paul Berry. I think it is intended for HPC-oriented workloads, replacing the (winning) combination of EPYC+MI250x, found in Frontier, with integrated MI300As (for El Capitan and others), with the added bonus of HBM for the CPU. Performance and efficiency should benefit, maybe to the level of 2 DP ExaFlop/s in a 30MW (or better) envelope on HPL, as well as top spot on HPCG. Watching how Grace+Hopper systems perform relative to MI300As (and vice-versa; eg. in top500) will be riveting I think.

By: Paul Berry

Paul Berry — Fri, 06 Jan 2023 17:46:43 +0000

900 Watts per part! Is it time for evaporative cooling?

By: Paul Berry

Paul Berry — Fri, 06 Jan 2023 17:45:15 +0000

They keep moving the pieces closer together, is that enough? So now the cpu and the gpu are on the same package, and share a memory controller. So there are no memory copies to move data between them, though there will likely be cache invalidates. However, they are distinct dies, so you’re still passing program control from processor to coprocessor. I would think it more efficient to take 64 GPU compute units, and attach them to the ryzen core. Can they be made an execution unit of the cpu? Obviously that’s a lot more invasive of a change, but FPUs did it 30 years ago. There’s a constant struggle between adding more vector/matrix compute capability to the GPU, and finding code segments with a long enough vector length to amortize the latency of handing the problem off to the coprocessor. The CPU keep getting better vector performance too, so it’s always hard to figure out which codes actually benefit from user a GPU. Mi300 sure is a heck of a lot of on-paper flops, but what percent of codes will make good use of them? How many will just want a fast cpu core?

By: HuMo

HuMo — Fri, 06 Jan 2023 08:40:45 +0000

This looks to me to be as close to 100% perfect design as it gets.

By: Xpea

Xpea — Fri, 06 Jan 2023 03:15:03 +0000

AMD is late. Nobody wants dedicated inference accelerators anymore. Customers want single AI accelerators that can do training and inference within same APIs/libraries/framework. IMHO this A70 will get small market adoption, unless it’s dirty cheap