Delta Electronics unveiled its GoCool-150 liquid-to-air coolant distribution unit at ASRock Rack's Computex 2026 booth, designed to discharge up to 150kW of heat from a single liquid-cooled server rac…
AMD announced it will acquire Taalas, a startup making model-specific AI inference chips that burn model weights directly into CMOS, claiming up to 17,000 tokens per second per user on its HC1 demonst…
AMD's Helios rackscale system, combining EPYC 9006 'Venice' CPUs, Instinct MI455X GPUs, and Pensando NICs/DPUs, is now in production, delivering 2.9 EFLOPS of peak MXFP4 compute and 31TB of HBM4 memor…
Kioxia launched its CM10 series PCIe 6.0 enterprise SSDs ahead of FMS 2026, featuring direct liquid cooling for AI infrastructure and up to 92% higher sequential read and 85% higher random read perfor…
PCIe Gen6 servers will begin shipping in the second half of 2026, doubling per-lane transfer rates over Gen5 and enabling 800Gbps network bandwidth from a single x16 slot, but Gen5 storage will remain…
AMD launched the Ryzen Embedded AI X100, a high-end embedded SoC based on Strix Halo silicon, as part of its physical AI strategy. The chipmaker announced the new product at its Advancing AI keynote, …
ASRock Rack's 4U16X-GNR2 server, powered by two Intel Xeon 6 'Granite Rapids' processors and eight NVIDIA Blackwell Ultra GPUs with NVLink, targets high-end AI training and inference workloads. The sy…
Primate Labs released Geekbench 7, a major overhaul of the cross-platform benchmark suite with updated CPU and GPU tests, including NVIDIA CUDA support. The CPU benchmark now includes a media group an…
AMD CEO Dr. Lisa Su will deliver the Advancing AI 2026 keynote in San Francisco, unveiling the company's first rackscale system, Helios, which integrates MI455X GPUs, EPYC 'Venice' CPUs, and Pensando …
NVIDIA released new architectural details and SPEC CPU 2026 benchmarks for its upcoming Vera CPU, revealing a 88-core Olympus architecture with spatial multithreading and up to 1.2TB/s memory bandwidt…
Intel Foundry has secured a custom ASIC design win with Fortinet for the Fortinet Security Processor 6 (SP6), marking a significant customer acquisition outside the AI space. Fortinet, which previousl…
Intel announced that its Xeon 6 family will receive a mid-generation upgrade with support for faster memory, starting with DDR5-8000 RDIMMs for select Xeon 6 6700P SKUs in August 2025, and second-gene…
AMD's Instinct MI350P PCIe AI accelerator, featuring CDNA 4 architecture and HBM3E memory, has been showcased at multiple trade shows including Dell Tech World, HPE Discover, and Computex 2026. The ca…
NVIDIA announced it will expand its Jetson Thor lineup with two new mid-range modules, the Jetson Thor T3000 and T2000, set for release in Q1 2027. The T3000 offers 8 Arm Neoverse V3AE CPU cores, 1536…
Lenovo's ThinkStation P3 Ultra SFF Gen 2 mini-PC workstation, reviewed by ServeTheHome, offers a 3.9-liter chassis with Intel Core Ultra 9 285 processor, up to 64GB DDR5-6400 memory, and an NVIDIA RTX…
ASRock Rack unveiled the 2UXGI-THOR, a 2U short-depth edge server based on NVIDIA's IGX Thor industrial SoC, at Computex 2026. The server combines 14 Arm Neoverse-V3AE CPU cores with an NVIDIA Blackwe…
AIC unveiled the F2032-01-G6 JBOF server at Computex, a 2U storage appliance holding 32 PCIe Gen6 E3 SSDs for up to 8PB of capacity, designed for AI key-value caching. The system uses Broadcom's 144-l…
ASUS gave a tour of its thermal testing lab in Taiwan, where it tests AI servers in environmental chambers that simulate years of thermal stress in compressed timeframes. The lab includes a walk-in ch…
Samsung Electronics has begun mass production of the PM1763, its first PCIe 6.0 enterprise SSD designed for AI and HPC servers. The drive delivers sequential read speeds up to 28,400 MB/s and write sp…
IBM is expanding its z17 and LinuxONE 5 mainframe lineups with single-frame and rackmount servers, including the LinuxONE Express, to target customers needing smaller-scale systems. The new hardware, …