Bondrewd
Veteran
But it's not slower!Of course going slower (than the process would allow to) and wider always pays in this metric
Frontier part has ~1700MHz fmax.
But it's not slower!Of course going slower (than the process would allow to) and wider always pays in this metric
But it's not slower!
Frontier part has ~1700MHz fmax.
Can someone remind me why GCN is better for HPC than RDNA? Better flops per mm^2?
Quite probably that, and the much better FP64 support since Radeon VII. When Vega was out, there was a long debate about it being more a compute oriented architecture rather than a gaming architecture.
Edit: I've found this interestng article about the diferences between these two architectures.
https://www.hardwaretimes.com/difference-between-amd-rdna-vs-gcn-gpu-architectures/
HPC/ML workloads are cache/shmem/TLP benchmarks which GCN is/was really good at overall.Can someone remind me why GCN is better for HPC than RDNA?
Those are stretchy as balls clocks that net not much real world(tm) performance.the latest Vega derivatives going at >2GHz speed in a low power budget
Easier to dance around that.But doesn’t the underutilization problem in games also affect HPC workloads?
It's likely more complicatedy. 560 W for MI250X (not 600 W) is related to water-cooled version used in Frontier. Standard version is 500W. 400W value is correct for standard version of A100, but according to Anandtech some custom deployments use up-to 600W (probably water-cooled) versions. So in some circumstances it can be 560 W for MI250X and 600 W for A100.Flops per W, mainly, as this is one of the main metrics for HPC. So the comparison is 42.2@600W vs 15.5@400W (as the referenced A100 is not the PCIE version, I'll consider the nominal TDP for both as we have no data about thre real power draw).
It's likely more complicatedy. 560 W for MI250X (not 600 W) is related to water-cooled version used in Frontier. Standard version is 500W. 400W value is correct for standard version, but according to Anandtech some custom deployments use up-to 600W (probably water-cooled) versions. So in some circumstances it can be 560 W for MI250X and 600 W for A100.
You can get an aircooled 500W A100 80GB but caveats inbound (same as 500W MI250(X) anyhow).but according to Anandtech some custom deployments use up-to 600W (probably water-cooled) versions
250W PCI-E A100 definitely has frequency/voltage curve tuned towards Max-Q, it's not that far away from A100 SXM.Yes, I know, as there is also the PCI-E version of A100 but that's quite probably power limited
It says: "ORNL’s partners in the exascale effort, HPE and AMD, have delivered the new Frontier system to ORNL ahead of the schedule for this fall."
apparently there are some scaling issues with SlingshotIt says: "ORNL’s partners in the exascale effort, HPE and AMD, have delivered the new Frontier system to ORNL ahead of the schedule for this fall."
apparently there are some scaling issues with Slingshot
Hardware on the floor != system running public science.It says: "ORNL’s partners in the exascale effort, HPE and AMD, have delivered the new Frontier system to ORNL ahead of the schedule for this fall."