Future TechnologyHardware
Cornelis put processors inside the network to stop GPUs sitting idle
Cornelis Networks raised 205 million dollars for Active Compute Fabric, embedding RISC-V cores in NICs and switches to cut GPU time spent waiting on ...
ComputingCornelis put processors inside the network to stop GPUs sitting idle
Cornelis Networks raised 205 million dollars for Active Compute Fabric, embedding RISC-V cores in NICs and switches to cut GPU time spent waiting on ...
ComputingScientists generate quantum entanglement from ordinary sunlight
Max Planck researchers proved sunlight can create entangled photon pairs at 94% fidelity, challenging the assumption that lasers are required for ...
ComputingY Combinator's Summer 2026 Demo Day: Floating Reactors and Brain Chips Made the Shortlist
Y Combinator's Summer 2026 Demo Day is done, and VCs are naming floating nuclear reactors and brain chips as the pitches that actually got them out of ...
ComputingNvidia built a laptop chip with an Arm CPU, Blackwell GPU, and 128GB of RAM
RTX Spark pairs 20 Arm cores with a Blackwell-class GPU and up to 128GB unified memory at 80W. First laptops ship this autumn from six OEMs.
ComputingQualcomm handed Amazon a 4 billion dollar warrant to win one customer
Qualcomm and Amazon signed a multi generation AWS inference silicon deal worth up to 60 billion dollars, and Qualcomm granted Amazon warrants for 25 ...
ComputingArm's Neural Rendering Tech Could Finally Make Mobile Gaming Look Good
Arm's new Mali G2-Ultra NX graphics chip brings neural rendering to mobile for the first time, debuting in the Xiaomi 18 Fold launched in China this ...
ComputingArm's biggest GPU redesign in seven generations shipped first in China
The Mali G2-Ultra NX brings neural rendering to mobile, and its first shipping device is the Xiaomi 18 Fold. What the matrix accelerator does, and ...
ComputingNintendo Switch 2 Costs $50 More, and Memory Chips Are Why
Nintendo's Switch 2 hit $499.99 on 1 September as a 41 percent jump in memory costs outpaced the price rise, and Japan sales fell 87 percent the same ...
ComputingDeepSeek Orders 160,000 Huawei Chips for a Site That Cannot Be Filled Yet
DeepSeek's Huawei Ascend data center order runs to 160,000 accelerators in Inner Mongolia, and memory supply, not export controls, sets the real ...
ComputingNvidia Expands DLSS 5 to Older GPUs but Takes Control Away From Gamers
Nvidia is bringing DLSS 5 to older RTX 40 and 30 series GPUs, which sounds great until you read the fine print. Gamers will not have full control over ...
ComputingIntel Crescent Island Specs: 480GB Of LPDDR5X On One Air Cooled Card
Intel Crescent Island specs from Hot Chips 2026: 32 Xe3P cores, up to 480GB of LPDDR5X, 350W and air cooling. Here is why Intel skipped HBM4 memory ...
ComputingNVIDIA Vera Rubin Is Here and the Numbers Are Striking
NVIDIA's Vera Rubin architecture has moved from announcement to production ramp, and the early performance claims being shared with partners paint a.
ComputingNvidia Agrees to Buy Hugging Face for 12.9 Billion Dollars
The Nvidia Hugging Face acquisition is reportedly agreed at 12.9 billion dollars but not yet signed. Here is what it changes if you run open models ...
ComputingNvidia Killed Rubin CPX and Paid 20 Billion Dollars for SRAM Instead
Nvidia cancelled Rubin CPX and replaced it with a Groq 3 LPX rack after a 20 billion dollar licensing deal, conceding SRAM wins the inference half.
ComputingVera Rubin NVL72 Is Ramping Fast and the Partners Running It Are Already Claiming Record Efficiency
NVIDIA's Vera Rubin architecture has moved from announcement to serious production scale faster than almost anyone predicted, and the partners ...
ComputingAMD's Radeon RX 9070 GRE Trims VRAM To Chase A Wider Market
AMD has launched the Radeon RX 9070 GRE globally, a trimmed-memory variant of the RX 9070 aimed at expanding its reach in the mid-range rather than ...
ComputingNVIDIA's Vera Rubin Is Already at Scale, and the Cost Numbers Are Striking
NVIDIA's Vera Rubin platform is ramping faster than anyone in the industry expected, and the performance numbers coming out of early deployments are ...
ComputingNVIDIA Vera Rubin Is Here and It Is Already Running at Scale
There is a moment in any hardware generation where the product stops being a press release and starts being real infrastructure.
ComputingNvidia's H200 Reached China and HBM Memory Prices Jumped 20 Percent
Nvidia H200 China export approval pushed HBM3E prices up nearly 20 percent for 2026. Six memory stacks per GPU explain the whole move.
ComputingSamsung Raised Chip Prices by 15 Percent, and China Is Paying the Most
Samsung chip price increase 2026: 4nm, 5nm and 8nm nodes all rose by up to 15 percent, and Chinese designers are absorbing the steepest hikes.
ComputingGoogle's Pixel 11 line lands with Tensor G6, the first 2nm phone chip
Google's Pixel 11 series launched 12 August 2026 with the first 2nm smartphone chip. Prices, specs and the honest take.
ComputingNvidia squeezes a data centre chip into a laptop with RTX Spark
Nvidia's RTX Spark Superchip fuses a Grace CPU with a Blackwell GPU for laptops arriving fall 2026.
ComputingA quantum computer just modelled how a fusion plant would refuel itself
Quantum computing and fusion tritium research collided this month. IBM, Oak Ridge and the Cleveland Clinic ran the first known fusion materials ...
ComputingNVIDIA's Vera Rubin Is Already Delivering the Lowest Token Costs in the Industry
When NVIDIA announced the Vera Rubin architecture, the promise was straightforward: more performance per watt at a lower cost per token than anything ...
ComputingNVIDIA Vera Rubin Is Here and Already Running at Scale With CoreWeave and Google
NVIDIA's Vera Rubin architecture has gone from announcement to gigascale production in striking time, with NVL72 racks already running at CoreWeave ...
ComputingGoogle Pixel 11 Launches Today with the First 2nm Chip in Any Smartphone
Google's Made by Google 2026 event reveals the Pixel 11 lineup with the Tensor G6, the first 2nm processor in a shipping smartphone.
ComputingAWS unveils Graviton5 as cloud giants pull silicon in-house
AWS revealed Graviton5, its next-gen Arm data-centre CPU, while Qualcomm paired with Meta. The hyperscaler custom-chip land grab continues.
ComputingNVIDIA Vera Rubin NVL72 Ramps Up at CoreWeave and Google
NVIDIA's next-generation Vera Rubin architecture is no longer a roadmap slide.
ComputingNVIDIA's Vera Rubin Is Shipping, and the Performance Per Watt Numbers Are Striking
NVIDIA's next chip generation is no longer a roadmap slide.
ComputingNVIDIA's Vera Rubin Is in Full Production and Partners Are Racing to Scale
NVIDIA's Vera Rubin architecture has moved from announcement to full production, and the numbers coming out of early partner deployments are ...
ComputingNVIDIA Vera Rubin Is Now Genuinely in Production and the Performance Numbers Are Real
NVIDIA's Vera Rubin architecture has moved from announcement to actual production deployment, and the performance-per-watt numbers being quoted are.
ComputingNVIDIA Vera Rubin Is Now in Full Production, and the Token Cost Numbers Are Striking
NVIDIA's Vera Rubin architecture has moved from announcement to full-scale production, and the company is making a pointed argument: this is now the ...
ComputingIntel Ships the First High-Volume Chips Made on High-NA EUV
Intel is the first chipmaker to ship high-volume chips made on a High-NA EUV machine, beating TSMC and Samsung to its 18A node. Here is why it ...
ComputingQuantum Error Correction Can Now Continuously Recalibrate Processors
Quantum computing has a noise problem, and it has always been a significant one.
ComputingSamsung's Q2 Earnings Guidance Points to a Chip Recovery That Is Actually Happening
Samsung Electronics has released its earnings guidance for the second quarter of 2026, and the figures are worth paying attention to even before the ...
ComputingSouth Korea is spending $880 billion on chips, AI, and robots over the next decade
South Korea committed $880 billion to semiconductors, AI, and robotics in the largest single-country chip investment in history. Here is what it ...
ComputingA humanoid robot company is about to go public
Agility Robotics, maker of the Digit warehouse robot, is heading to public markets via a SPAC at a $2.5bn valuation, backed by Amazon, Nvidia and ...
ComputingIBM crams 100 billion transistors onto one chip
IBM's NanoStack architecture puts 100 billion transistors on a single chip with 50% more performance and 70% less energy, via vertical stacking.
ComputingIntel's 18A-P node hits a milestone, with Apple and Google reportedly circling
The advanced process enters risk production, and a tie-up with Taiwan's UMC takes aim at TSMC's foundry lead.
ComputingNvidia just walked into the PC chip market, and Intel should be worried
The RTX Spark Superchip puts a 20-core CPU and a Blackwell GPU on one piece of silicon. It lands in laptops this autumn.
ComputingQuantum computers just got dramatically more reliable, and almost nobody noticed
Microsoft reports a 1,000x reliability jump in its Majorana qubits, while error correction across the industry moves from lab trick to engineering ...