Home Blog Page 8
FuriosaAI RNGD Without Cooler_1
The FuriosaAI RNGD processor was detailed and shown at Hot Chips 2024 for lower power AI inference applications
AMD MI300X Delidded 2
AMD had a talk on its big AI GPU at Hot Chips 2024. The AMD Instinct MI300X is a multi-billion dollar product line for the company
Intel Gaudi 3 OAM Working Sample Package 1
We have more details of the Intel Gaudi 3 for AI training and inference at Hot Chips 2024 including generational performance gains
SambaNova SN40L Large
This is the SambaNova SN40L a dataflow architecture AI accelerator with 520MB of SRAM, 64GB of HBM, and 1.5TB of DDR memory
NVIDIA Roadmap 2024-08
At Hot Chips 2024, we got another look at the NVIDIA Blackwell platform which will be the company's big AI chip in 2025
OpenAI Hot Chips 2024_Page_19
At Hot Chips 2024, OpenAI has an hour-long keynote about why building scalable AI infrastructure is important, and what is needed to do so
Hot Chips 2024 Intel Xeon 6 Granite Rapids D_Page_06
In 2025 Intel Xeon D will get HUGE with the Intel Xeon 6 Granite Rapids-D platform. 100GbE, AMX, media encoders, 8-channel memory, and more
SK Hynix Hot Chips 2024 AiMX XPU_Page_12
SK Hynix showed off its AiMX-xPU concept at Hot Chips 2024 for more efficient LLM inference compute being done in-memory
Tenstorrent Hot Chips 2024_Page_13
At Hot Chips 2024, we got more information on the Tenstorrent Blackhole, a RISC-V based AI accelerator that uses 10x 400GbE for interconnect
IBM Telum II And Spyre Hot Chips 2024_Page_05
The new IBM Telum II is the company's next-gen IBM Z mainframe processor with built-in AI and DPU. The company also has a Spyre AI processor