Home Blog Page 53
Moffett Antoum AI Inference Accelerator _Page_18
The Moffett Antoum is an AI inference accelerator that seeks to aggressively leverage sparsity to speed AI inference
Intel 8 Core 528 Thread Chip With Optical Networking For DARPA
Intel showed an 8 core CPU with 66 hardware threads per core for 528 threads and it even included silicon photonics networking
Lightelligence Hummingbird Card At Hot Chips 2023
Lightelligence showed off its Hummingbird AI inference chip with its optical network on chip (or package?) technology
Cerebras Wafer Scale Cluster HC35_Page_32
The new Cerebras Wafer-Scale cluster is an architecture designed for big AI jobs instead of trying to copy NVIDIA
Google Machine Learning Supercomputer With An Optically Reconfigurable Interconnect _Page_14 Large
Google detailed how its TPUv4 pods use optically reconfigurable networks to support efficient, large scale, AI workloads
Ampere AmpereOne A160 30 At Computex 2023 1
The new Ampere AmpereOne CPU is landing first in the Google Cloud C3A instances. This next-gen Arm server CPU we expect to see more of soon
SiFive P870 RISC V HC35_Page_04
At Hot Chips 2023, we learned about the upcoming SiFive P870 performance RISC-V core and hints of next-gen Napa performance cores
Intel Granite Rapids Top Hot Chips 2023
This is the HUGE new Intel Xeon Granite Rapids CPU that will arrive in 2024 and that will offer a much higher level of performance
Intel E Core Focus HC35_Page_12
At Hot Chips 2023, Intel went into more details around its most important CPU of 2024, Sierra Forest based on Sierra Glen E-cores
Arm CSS N2 HC35_Page_18
The Arm Neoverse CSS will make dropping Neoverse N2 cores into silicon designs much easier. This new offering was detailed at Hot Chips 2023