-
Sam Altman Proposes World’s Largest Cash Incinerator
In a spasm of incisive journalism, we’re reporting that various news sites are reporting that the Wall Street Journal has reported that Sam Altman wants several trillion dollars from Arab sovereign-wealth funds to fab and deploy AI chips, calling the project GlobalFoundries 2: AI Boogaloo. Shine bright, Sam. continue reading
-
AMD Ryzen Gets On Board With Xilinx Versal
Two years after completing its Xilinx acquisition, AMD has released a design combining an AMD-heritage processor with a Xilinx-heritage FPGA. The new AMD Embedded+ is a board, not a chip, however. It targets PC-like systems for industrial, medical, and other embedded applications. Taking over Xilinx, with its broad customer base, should help AMD expand its continue reading
-
You Would Think There’s a Single Optimal Heterogenous Multicore Configuration for Power, Performance, or Area
AMD’s blend of Zen 4 and Zen 4c cores in Phoenix 2 seems optimal, but the variety of heterogeneous multicore configurations in the wild suggests there’s no consensus optimum. continue reading
-
Why License Verilog When You Can Use Excel?
Some guy made a gate-level CPU design in Excel. I’m only disappointed the compiler is in Python instead of VBA. continue reading
-
Meta Attempts an Inference Chip Again
Reuters reports that Meta (Facebook) plans to deploy its own data-center inference chip. The appeal of such a design is clear, but Meta scrapped a past inference-chip design and turned down using off-the-shelf inference-only chips. continue reading
-
AMD Hawk Point and Phoenix 2 Deliver Value to Mainstream PC Users
Desktop and laptop PCs incorporating AMD’s Phoenix 2 and Hawk Point processors will soon be available. They’re follow-ons to last year’s Phoenix APU. To cut cost, Phoenix 2 mixes Zen 4 and Zen 4c CPUs, and it has a smaller GPU and no NPU, shrinking the die 23%. Hawk Point’s big selling point over Phoenix… continue reading
Popular
Sponsored Content and Plugs
- BWR 12: The Memory Episode
- Slash Server Costs Without Hardware or Software Changes
- Ceva Boosts NeuPro-M NPU Throughput and Efficiency
- MEXT Helps IT Leaders Find the Sweet Spot
- Chips Act Backs Chiplets
Other Sites You Might Like
Read More
Amazon AMD Arm auto Broadcom business Cerebras Ceva consumer CPU data center DPU DSP edge AI embedded FPGA Google GPU Imagination industrial Intel interconnect Marvell MCU MediaTek Meta MEXT Microsoft MLPerf NPU (AI accelerator) Nvidia NXP OpenAI PC process tech Qualcomm Renesas RISC-V SambaNova Semidynamics SiFive smartphone SoftBank software Tenstorrent