Hopper, Startups Debut MLPerf Scores
The MLPerf 2.1 inference release includes preliminary results that put Nvidia’s Hopper H100 in the performance lead. Asian startups Biren and Sapeon also made impressive debuts.
The MLPerf 2.1 inference release includes preliminary results that put Nvidia’s Hopper H100 in the performance lead. Asian startups Biren and Sapeon also made impressive debuts.
Ryzen 7000 Upgrades to Zen 4 and 5nm
AMD’s Ryzen 7000-series processors for high-end desktops employ the new Zen 4 CPU to achieve greater performance and power efficiency.
AMD’s Ryzen 7000-series processors for high-end desktops employ the new Zen 4 CPU to achieve greater performance and power efficiency.
Snapdragon 6 Boosts Graphics and AI
Qualcomm updated its Snapdragon 6 and 4 lines, moving to a new process, improving performance, and selectively adding features. The new nomenclature aligns with the 7- and 8-series.
Qualcomm updated its Snapdragon 6 and 4 lines, moving to a new process, improving performance, and selectively adding features. The new nomenclature aligns with the 7- and 8-series.
Cerebras Dives Into WSE Architecture
The startup disclosed new details about how its tiny cores deliver tremendous performance and how its sparsity support boosts performance when training large AI models.
The startup disclosed new details about how its tiny cores deliver tremendous performance and how its sparsity support boosts performance when training large AI models.
CXL 3.0 Opens New Use Cases
The newly unveiled CXL 3.0 introduces memory sharing, direct device peer-to-peer memory access without involving a host, and multilevel switching. A new global fabric-attached memory can be shared by 4,096 hosts.
The newly unveiled CXL 3.0 introduces memory sharing, direct device peer-to-peer memory access without involving a host, and multilevel switching. A new global fabric-attached memory can be shared by 4,096 hosts.
Updated Trident 4 Monitors Connections
Broadcom has added a network-scanning engine to its 12.8Tbps Trident 4 Ethernet switch. Capable of fingerprinting every packet, the engine improves network security.
Broadcom has added a network-scanning engine to its 12.8Tbps Trident 4 Ethernet switch. Capable of fingerprinting every packet, the engine improves network security.
Lightmatter Connects Chiplets Optically
Lightmatter’s Passage substrate is an active photonic interposer for interconnecting chiplets. All the photonic components and supporting electrical circuits reside in a single multi-reticle piece of silicon.
Lightmatter’s Passage substrate is an active photonic interposer for interconnecting chiplets. All the photonic components and supporting electrical circuits reside in a single multi-reticle piece of silicon.
MediaTek T830 Accelerates 5G Broadband
To capitalize on growing adoption of 5G cellular for broadband access, MediaTek has boosted the throughput of its fixed-wireless-access chipset.
To capitalize on growing adoption of 5G cellular for broadband access, MediaTek has boosted the throughput of its fixed-wireless-access chipset.
Nvidia Grace Supports AI Acceleration
To tackle the largest AI models, Nvidia has designed a processor to feed its powerful new Hopper GPU. Grace has twice the memory bandwidth of any x86 processor and can hold GPT-3 in DRAM.
To tackle the largest AI models, Nvidia has designed a processor to feed its powerful new Hopper GPU. Grace has twice the memory bandwidth of any x86 processor and can hold GPT-3 in DRAM.
Biren GPGPU Aims for the Clouds
In the data-center accelerator race, the three-year-old startup has burst from the gate with a chiplet-based design that aims to compete with Nvidia for general-purpose-GPU (GPGPU) cloud computing.
In the data-center accelerator race, the three-year-old startup has burst from the gate with a chiplet-based design that aims to compete with Nvidia for general-purpose-GPU (GPGPU) cloud computing.
Grai Matter Pivots to Floating Point
The startup has made progress on its Grai VIP deep-learning accelerator, changing native processing from INT8 to FP16 and adding audio workloads to its target applications.
The startup has made progress on its Grai VIP deep-learning accelerator, changing native processing from INT8 to FP16 and adding audio workloads to its target applications.
Intel PC Processors Move to Chiplets
Meteor Lake will introduce a multidie arrangement using Intel’s silicon-substrate and advanced packaging technologies. This chiplet approach will appear across all PC price tiers beginning late next year.
Meteor Lake will introduce a multidie arrangement using Intel’s silicon-substrate and advanced packaging technologies. This chiplet approach will appear across all PC price tiers beginning late next year.
MCUs Moving to RISC-V
Renesas has introduced the first embedded processor with a user-programmable RISC-V CPU. Chinese processors are already adopting RISC-V; more will follow in a direct challenge to Arm.
Renesas has introduced the first embedded processor with a user-programmable RISC-V CPU. Chinese processors are already adopting RISC-V; more will follow in a direct challenge to Arm.
ST BlueNRG Tracks People and Assets
ST’s newest BlueNRG microcontroller targets location services and reduces cost.
ST’s newest BlueNRG microcontroller targets location services and reduces cost.
Untether Boqueria Targets AI Lead
The startup’s unique at-memory architecture targets an eye-popping 30 teraflop/s per watt and 12,000 teraflop/s in a single card. The second-generation chip is due to sample in 1H23.
The startup’s unique at-memory architecture targets an eye-popping 30 teraflop/s per watt and 12,000 teraflop/s in a single card. The second-generation chip is due to sample in 1H23.
