Nguyenhuh, isn't the RTX3090 already capable of ~36 TFLOPS of FP32 at 350W TGP, what's so special about a MCM solution getting 45 TFLOPS at 600W LMAO.NVidia A100 (the $10,000 server card) is only 19.5 FP32 TFlops: And only 9.7 FP64 TFlops. Posted on Aug 21st 2021, 0:48 Reply #13 TheGuruStud :) I think people use the term "crossbar" as shorthand for a "switch that has no restriction on bandwidth" (which a nonblocking CLOS network qualifies), and not necessarily a "physical crossbar" (which takes up O(n^2 space), while CLOS network is O(n*log(n)) space) Note: most "crossbars" are just nonblocking CLOS networks. But I'm assuming Intel is aiming at the big boy, the A100 600GByte/sec fabric. ![]() Its "passable" because 16x PCIe 4 is just 32GByte/sec, so really, anything "faster than PCIe" is kind of a win. But if its "Gbits", then that's only 90GByte/sec (which is probably passable, but much slower than NVidia). The ArchDay21claims site doesn't provide details ( /content/8x links gets us to 720 "G" per second, hopefully that's "GBytes" which would be a bit faster than NVSwitch and competitive. Unfortunately, its giving me more questions rather than answers. I'd interpret this slide as "crossbar"Thanks for the slide.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |