- Nvidia Blackwell variants comparison table https://www.tomshardware.com/pc-components/gpus/nvidias-next-gen-ai-gpu-revealed-blackwell-b200-gpu-delivers-up-to-20-petaflops-of-compute-and-massive-improvements-over-hopper-h100 24 comments hardware
Linking pages
- RTX off, AI on: Jensen says we'll see fully AI-generated games in 5-10 years | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/rtx-off-ai-on-jensen-says-well-see-fully-ai-generated-games-in-5-10-years 1375 comments
- US govt's CHIPS Act gives Intel $8.5 billion in funding and a 25% tax credit on $100 billion in investments | Tom's Hardware https://www.tomshardware.com/pc-components/cpus/us-govts-chips-act-gives-intel-dollar85-billion-in-funding-and-a-25-tax-credit-on-dollar100-billion-in-investments 312 comments
- Leaker claims Nvidia plans to launch RTX 5080 before RTX 5090 — which would make perfect sense for a dual-die monster GPU | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/leaker-claims-nvidia-plans-to-launch-rtx-5080-before-rtx-5090-which-would-make-perfect-sense-for-a-dual-die-monster-gpu 283 comments
- Next-gen GPUs likely arriving in late 2024 with GDDR7 memory — Samsung and SK hynix chips showed chips at GTC | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/next-gen-gpus-likely-arriving-in-late-2024-with-gddr7-memory-samsung-and-sk-hynix-chips-showed-chips-at-gtc 244 comments
- Nvidia criticizes AI PCs, says Microsoft's 45 TOPS requirement is only good enough for 'basic' AI tasks | Tom's Hardware https://www.tomshardware.com/tech-industry/artificial-intelligence/nvidia-criticizes-ai-pcs-says-microsofts-45-tops-requirement-is-only-good-enough-for-basic-ai-tasks 205 comments
- Nvidia's next-gen Blackwell AI Superchips could cost up to $70,000 — fully-equipped server racks reportedly range up to $3,000,000 or more | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/nvidias-next-gen-blackwell-ai-gpus-to-cost-up-to-dollar70000-fully-equipped-servers-range-up-to-dollar3000000-report 145 comments
- Nvidia's Jensen Huang says Blackwell GPU to cost $30,000 - $40,000, later clarifies that pricing will vary as they won't sell just the chip | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/nvidias-jensen-huang-says-blackwell-gpu-to-cost-dollar30000-dollar40000-later-clarifies-that-pricing-will-vary-as-they-wont-sell-just-the-chip 69 comments
- TSMC to build massive chips twice the size of today's largest — chips will use thousands of watts of power | Tom's Hardware https://www.tomshardware.com/tech-industry/tsmc-to-build-massive-chips-twice-the-size-of-todays-largest-that-draw-thousands-of-watts-of-power-120x120mm-chips-with-12-hbm4e-stacks-in-2027 47 comments
- Leaker suggests that Nvidia's Blackwell gaming graphics processer, GB202 to use the same technology as GB200 | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/leaker-suggests-that-nvidias-blackwell-gaming-graphics-processer-gb202-to-use-the-same-technology-as-gb200 39 comments
- Jim Keller suggests Nvidia should have used Ethernet to stitch together Blackwell GPUs — Nvidia could have saved billions | Tom's Hardware https://www.tomshardware.com/tech-industry/artificial-intelligence/jim-keller-suggests-nvidia-should-have-used-ethernet-to-stitch-together-blackwell-gpus 28 comments
- Samsung denies report citing HBM quality issues, asserts its HBM memory works just fine | Tom's Hardware https://www.tomshardware.com/tech-industry/samsung-denies-report-citing-hbm-quality-issues-asserts-its-hbm-memory-works-just-fine 15 comments
- Researchers 3D print wood objects from sawdust ink – texture, appearance, and smell similar to the real thing | Tom's Hardware https://www.tomshardware.com/3d-printing/researchers-3d-print-wood-objects-from-sawdust-ink-texture-appearance-and-smell-similar-to-the-real-thing 7 comments
- Dell will have an eight-way Nvidia Blackwell server with liquid cooling — coming later this year | Tom's Hardware https://www.tomshardware.com/tech-industry/artificial-intelligence/dell-will-have-an-eight-way-nvidia-blackwell-server-with-liquid-cooling-coming-later-this-year 6 comments
- Deep dives into AMD Zen 5, Nvidia Blackwell, and Intel Lunar Lake architectures coming at Hot Chips 2024 | Tom's Hardware https://www.tomshardware.com/tech-industry/deep-dives-into-amd-zen-5-nvidia-blackwell-and-intel-lunar-lake-architectures-coming-at-hot-chips-2024 3 comments
- AMD shows off DX12-related rendering advances that make game engines more efficient and less dependent on the CPU -- demo shows a 64% improvement | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/amd-shows-off-dx12-related-rendering-advances-that-make-game-engines-more-efficient-and-less-dependent-on-the-cpu 0 comments
- AI startup Extropic emerges from stealth with superconducting processors it boldly claims will beat GPUs, CPUs, and TPUs | Tom's Hardware https://www.tomshardware.com/tech-industry/artificial-intelligence/ai-startup-extropic-emerges-from-stealth-with-superconducting-processors-it-boldly-claims-will-beat-gpus-cpus-and-tpus 0 comments
- Custom virtual pinball machine packs Raspberry Pi Pico's RP2040 and a full PC | Tom's Hardware https://www.tomshardware.com/raspberry-pi/custom-virtual-pinball-machine-packs-raspberry-pi-picos-rp2040-and-a-full-pc 0 comments
- Intel expects paltry $500 million in Gaudi 3 AI sales for the rest of the year — Nvidia to rake in $40 billion for data center AI this year | Tom's Hardware https://www.tomshardware.com/tech-industry/artificial-intelligence/intel-expects-dollar500-million-in-gaudi-3-ai-sales-for-the-rest-of-the-year-nvidia-to-rake-in-dollar40-billion-for-data-center-ai-this-year 0 comments
- Nvidia's unannounced R100 AI GPUs reportedly coming in late 2025 — 'Vera Rubin' multi-chip designs using 3nm and CoWoS-L | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/nvidias-unannounced-r100-ai-gpus-reportedly-coming-in-late-2025-vera-rubin-multi-chip-designs-using-3nm-and-cowos-l 0 comments
Linked pages
- China's Zhaoxin KX-7000 CPU doubles performance of prior-gen chip, still trails 6-year-old AMD and Intel processors | Tom's Hardware https://www.tomshardware.com/pc-components/cpus/chinas-zhaoxin-kx-7000-cpu-doubles-performance-of-prior-gen-chip-still-trails-6-year-old-amd-and-intel-processors 244 comments
- Jensen Huang says even free AI chips from his competitors can't beat Nvidia's GPUs | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/jensen-huang-says-even-free-ai-chips-from-his-competitors-cant-beat-nvidias-gpus 224 comments
- Nvidia provides the first public view of its fastest AI supercomputer — Eos is powered by 4,608 H100 GPUs, tuned for generative AI | Tom's Hardware https://www.tomshardware.com/tech-industry/artificial-intelligence/nvidia-provides-the-first-public-view-of-its-fastest-ai-supercomputer-eos-is-powered-by-4608-h100-gpus-tuned-for-generative-ai 115 comments
- Intel CEO says Nvidia’s AI dominance is pure luck — Nvidia VP fires back, says Intel lacked vision and execution | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/intel-ceo-says-nvidias-ai-dominance-is-pure-luck-nvidia-vp-fires-back-says-intel-lacked-vision-and-execution 98 comments
- Modern web bloat means some pages load 21MB of data - entry-level phones can't run some simple web pages, and some sites are harder to render than PUBG | Tom's Hardware https://www.tomshardware.com/tech-industry/modern-web-bloat-means-some-entry-level-phones-cant-run-simple-web-pages-and-load-times-are-high-for-pcs-some-sites-run-worse-than-pubg 14 comments
- Despite U.S. sanctions, researchers in China can still access high-end Nvidia GPUs for AI | Tom's Hardware https://www.tomshardware.com/pc-components/gpus/despite-us-sanctions-researchers-in-china-can-still-access-high-end-nvidia-gpus-for-ai 0 comments
- Blackwell Architecture for Generative AI | NVIDIA https://www.nvidia.com/en-us/data-center/technologies/blackwell-architecture/ 0 comments