GPU

Chinese web giants go on $5B Nvidia shopping spree to fuel AI ambitions

In the ML arms race, GPUs are the ammunition

AI + ML11 Aug 2023 | 4

Nvidia gives Grace Hopper superchip an HBM3e upgrade – sometime next year

641GB of total memory ought to be enough for anybody (and their LLM)

AI + ML09 Aug 2023 | 4

Biden urged to completely cripple AI chips to China

Give them Z80s, Joe, and tell 'em to like it

AI + ML28 Jul 2023 | 53

Intel: Here, have some AI reference kits ... now please buy our silicon

With 34 designs to pick from, you can choose your own ML adventure

AI + ML25 Jul 2023 | 4

Samsung makes big promises about GDDR7 RAM

Too bad GPU slingers keep shrinking the memory bus

Storage20 Jul 2023 | 3

Intel woos China with nerfed Habana Gaudi2 AI chips

Not even Uncle Sam can stand between x86 titan and its profits

AI + ML13 Jul 2023 | 4

Washington plans to block Chinese access to AI cloud services

Can't buy advanced GPUs... and might be blocked from renting them soon

PaaS + IaaS05 Jul 2023 | 6

Cisco challenges Broadcom, Nvidia with 51.2Tbit switch ASIC of its own

Chip promises denser, greener networks – at least compared to the fire-breathing GPUs they connect

Networks22 Jun 2023 |

AMD's latest Epycs are bristling with cores, stacked to the gills with cache

Zen giant's Instinct MI300 APUs, GPUs not quite ready for limelight

Systems13 Jun 2023 |

What to expect from AMD's June datacenter, AI shindig

Comment Could it be a cloudy Epyc, or a datacenter APU, maybe another cache-stacked X-chip?

Systems01 Jun 2023 |

Nvidia creates open server spec to house its own chips – and the occasional x86

Computex Taiwan's big OEMs are all-in on plan to build servers that won't cook when running AI

Systems29 May 2023 | 3

Look mom, no InifiniBand: Nvidia’s DGX GH200 glues 256 superchips with NVLink

Computex Unless you need more nodes

HPC29 May 2023 | 3

AMD undercuts Nvidia's 4060 launch with a $269 GPU

Maybe the years of accelerators being hard to find and harder to pay for are behind us?

Personal Tech25 May 2023 | 17

AMD scours parts bin for old CPUs, GPUs to put in Chromebooks

Do you really need the latest and greatest cores to doomscroll the web?

Personal Tech23 May 2023 | 7

Intel abandons XPU plan to cram CPU, GPU, memory into one package

ISC AMD now has clear runway to conquer datacenter APU market

Systems22 May 2023 | 7

Nvidia GPUs fly out of the fabs – and right back into them

Comment Let's use AI to make better chips for AI, what could go wrong?

Systems20 May 2023 | 3

Nvidia's RTX 4060 and 4060TI are actually priced like mid-tier cards

Maybe Jensen finally got the memo about the whole GPU shortage being over

Systems19 May 2023 | 15

With AI hype driving up server GPU prices, will cloud costs rise next? We reckon so

Register Kettle And what next for cooling, datacenter placement, and more – tune in and find out direct from our vultures

AI + ML11 May 2023 | 1

Are accelerators the cure to video's power problem or just an excuse to peddle GPUs?

Analysis You could just watch less TikTok or Twitch, maybe go outside

Energy Efficient Datacenters13 Apr 2023 | 17

Why we think Intel may be gearing up to push its GPU Max chips into China

x86 giant cancels mid-tier processor, plans to relaunch nerfed parts for 'different markets'

Systems11 Apr 2023 | 2

Nvidia CEO promises sustainability salvation in the cult of accelerated computing

GTC Not quite as dramatic as AMD's Lisa Su and her visions of nuclear-powered supercomputers

Systems21 Mar 2023 | 1

Nvidia's generative AI inferencing card is just two H100s glued together

GTC Don’t need a 700W fire-breathing GPU? It also launched an itty-bitty AI chip too

Systems21 Mar 2023 | 2

Chinese biz banned from buying US tech rent it instead

Clouds reportedly offering surprisingly cheap access to blockaded comrades

PaaS + IaaS10 Mar 2023 | 7

AMD flips the bird at Intel as it glides past in CPU-GPU stakes

CTO warns chips and process technology must be designed together more closely thanks to Moore's Law

Systems09 Mar 2023 | 4

Intel buries news of GPU cuts and delays in low-key Friday post

Falcon Shore will be late. Rialto Bridge and Lancaster Sound cancelled. Will Chipzilla ever nail its XPU plan?

On-Prem06 Mar 2023 | 12

After roasting Nvidia for overheating issues AMD now has its own

Perhaps make sure your own products are working properly before razzing your rival's

Systems05 Jan 2023 | 20

Nvidia revives canceled RTX 4080 as 'new' 12GB RTX 4070 TI

Hopefully it comes with a 'new' competitive price, too

Personal Tech30 Dec 2022 | 25

GPUs dodge price hike as US extends China tariff deadline beyond 2022

Happy New Year! Concession is made on GPUs and other parts

Systems19 Dec 2022 |

Samsung slaps processing-in-memory chips onto GPUs for first-of-its-kind supercomputer

Korean tech giant claims big performance, energy efficiency gains with memory tech

HPC13 Dec 2022 | 10

Intel aims for lower-power GPUs as Nvidia pushes pricey energy guzzlers

GPU boss vows 'dramatic shift in the PC graphics landscape' with next-gen CPU

Systems12 Dec 2022 | 6

Creator of spec for melting RTX 4090 cables urges Nvidia, others to 'ensure user safety'

Testing is your responsibility, not ours, says PCI-SIG

Systems02 Dec 2022 | 22

GPU shipments saw biggest nosedive since noughties recession

A sign of the computer industry’s sad state, but at least there’s supply!

Systems23 Nov 2022 | 13

Nvidia faces lawsuit for melting RTX 4090 cables as AMD has a laugh

Law firm wants class-action status, says issue poses 'serious electrical and fire hazard'

Systems18 Nov 2022 | 59

Nvidia's datacenter growth can't save it from gaming GPU woes

CEO says new RTX 4090 cards off to a 'great start' despite melting cable issues

Systems17 Nov 2022 | 16

Cerebras's supercomputer has more cores than world's fastest iron – with a big catch

Better for AI, but Frontier's still top of the heap

HPC15 Nov 2022 | 6

Nvidia bundles enterprise AI software with incoming H100 systems

GPU maker wants more of your money with next wave of servers

Systems14 Nov 2022 |

Intel takes on AMD and Nvidia with mad 'Max' chips for HPC

x86 giant goes all-in with high-bandwidth memory

Systems09 Nov 2022 | 13

Nvidia RTX 4090: So hot they're melting power cables

Flaming 'eck!

Personal Tech25 Oct 2022 | 93

Nvidia admits mistake, 'unlaunches' 12GB RTX 4080

The cheapest 40-series card now starts at [checks notes] $1,199

Personal Tech14 Oct 2022 | 21

The new GPU world order is beginning to take shape

Comment As Nvidia hikes prices, Intel is only too happy to profit from your discontent, and AMD remains a wild card

Personal Tech11 Oct 2022 | 53

Ethereum Merge signals end of GPU shortage, but not necessarily high prices

Analysis What a mine field

Personal Tech24 Sep 2022 | 12

Nvidia unveils RTX 4090 – but it's the 4080 to watch out for

GTC And don't forget AMD's RDNA 3 GPUs are right around the corner

Personal Tech20 Sep 2022 | 15

Nvidia claims 'record performance' for Hopper MLPerf debut

H100 Tensor Core GPU leaves A100 in the dust, but company says previous gen has improved too

HPC09 Sep 2022 |

Nvidia will unveil next-gen GPU architecture in September

But graphics giant foresees revenues falling even further in the next quarter as gamer GPU sales drop

Systems25 Aug 2022 | 20

Intel aims Flex datacenter GPUs at video, game streaming

Hot Chips Chipzilla's story Arc continues

Personal Tech24 Aug 2022 |

Intel set to squeeze the flops out of Ponte Vecchio GPU

Hot Chips Now this x86 giant just needs to ship a compatible CPU

Systems23 Aug 2022 | 5

AMD has a lot riding on its 5nm Ryzen 7000 CPUs. And so here begins the hype

You'll need a new motherboard, RAM, beefier PSU. But hey, at least GPUs are cheap again

Personal Tech16 Aug 2022 | 16

Intel challenges Nvidia, AMD with trio of workstation GPUs

For those that just can't wait for AV1 encoding

Systems09 Aug 2022 | 13

Too little, too late: Intel's legacy is eroding

Comment Can Pat stop the rot – or is the chip giant facing a Kodak moment?

Systems05 Aug 2022 | 90

Nvidia releases first Jetson AGX Orin module for production deployment

More expensive than a Pi but with a lot more oomph, platform to be embedded in devices at the edge

Systems04 Aug 2022 | 2

Nvidia gets down with low code in AI Enterprise update

GPU giant promises to make ML accessible to even the most modest biz

AI + ML26 Jul 2022 |

You can liquid cool this Linux laptop to let the GPU soar

Or to make the fans shut up. Either way, you won’t be moving much with this setup

Personal Tech18 Jul 2022 | 36

Intel’s first discrete GPUs won't be a home run

Comment High-end Arc A750 will compete with *checks notes* a GeForce RTX 3060

Personal Tech18 Jul 2022 | 35

Intel axes Nvidia-powered NUC X15 laptops for Arc GPU reseller push

Soon enough, you won't have to turn to a large PC vendor to buy an Arc laptop

Personal Tech13 Jul 2022 | 3

The return of GPUs on sale may be tech world's monkey's paw of 2022

Comment Improved supply is welcome – too bad it may be the harbinger of a cooling economy

Personal Tech07 Jul 2022 | 14

Meta: We need 5x more GPUs to combat TikTok, stat

Comment And 30% fewer new engineers this year

AI + ML30 Jun 2022 | 30