hbm2

HBM2 vs. GDDR6: New Video Compares, Contrasts Memory Types

HBM2 vs. GDDR6: New Video Compares, Contrasts Memory Types

Curious about how GDDR6 differs from or is similar to HBM2 and how the two compare? We've got you covered. The post HBM2 vs. GDDR6: New Video Compares, Contrasts Memory Types appeared first on
Samsung Flashbolt HBM2 Is 33 Percent Faster, Doubles Capacity

Samsung Flashbolt HBM2 Is 33 Percent Faster, Doubles Capacity

Samsung has announced HBM2e Flashbolt memory, with 33 percent higher performance and double the memory density. The post Samsung Flashbolt HBM2 Is 33 Percent Faster, Doubles Capacity appeared first
JEDEC Extends HBM2 Standard to 24GB, 307GB/s Bandwidth Per Stack

JEDEC Extends HBM2 Standard to 24GB, 307GB/s Bandwidth Per Stack

JEDEC has updated the HBM2 standard for higher transfer speeds and increased density. The post JEDEC Extends HBM2 Standard to 24GB, 307GB/s Bandwidth Per Stack appeared first on ExtremeTech.
Samsung Claims It Could Double HBM2 Manufacturing, Fail to Meet Demand

Samsung Claims It Could Double HBM2 Manufacturing, Fail to Meet Demand

Samsung claims HBM2 demand is so phenomenal, it could double production without manufacturing enough. That's not actually great news, depending on how you look at the situation. The post Samsung
AMD Demos 7nm Vega for Machine Intelligence at Computex

AMD Demos 7nm Vega for Machine Intelligence at Computex

AMD's new Vega 7nm machine intelligence solution is debuting ahead of schedule. The post AMD Demos 7nm Vega for Machine Intelligence at Computex appeared first on ExtremeTech.
Nvidia’s Titan V Accused of Returning Wrong Answers in Simulations

Nvidia’s Titan V Accused of Returning Wrong Answers in Simulations

Nvidia's Titan V may return incorrect answers in certain types of high-performance computing simulations, but it isn't entirely clear if the card really can't do math or if something else is awry. The
Massdrop: Nvidia Expects GPU Prices to Rise Through Q3 2018

Massdrop: Nvidia Expects GPU Prices to Rise Through Q3 2018

Hardware community Massdrop is predicting GPU prices will remain high through Q3 of this year. Here's hoping they're wrong. The post Massdrop: Nvidia Expects GPU Prices to Rise Through Q3 2018
Samsung Now Producing 16Gbit GDDR6 for Upcoming GPUs

Samsung Now Producing 16Gbit GDDR6 for Upcoming GPUs

Samsung is ramping up production of GDDR6 with an 18Gbit clock and a new process node. The post Samsung Now Producing 16Gbit GDDR6 for Upcoming GPUs appeared first on ExtremeTech.
Samsung Announces High-Speed HBM2 Breakthrough, Codenamed Aquabolt

Samsung Announces High-Speed HBM2 Breakthrough, Codenamed Aquabolt

Samsung has found a way to turn up the speed on HBM2 dramatically without needing a voltage increase. Could this be the turning point for the standard? The post Samsung Announces High-Speed HBM2
Intel Launches AMD Radeon-Powered CPUs

Intel Launches AMD Radeon-Powered CPUs

Intel's new Radeon+Kaby Lake hybrid CPUs are headed for store shelves. Here's how the SKUs break down and what you need to know. The post Intel Launches AMD Radeon-Powered CPUs appeared first on
AMD’s Next-Generation Navi GPU Could Ship by Late 2018

AMD’s Next-Generation Navi GPU Could Ship by Late 2018

AMD's already moving past Vega. The company's next-gen Navi GPU has tipped up in online driver remarks and could be headed for a launch in Q3 2018. Here's what we know. The post AMD’s Next-Generation
Intel’s new Stratix 10 MX FPGA Taps HBM2 For Massive Memory Bandwidth

Intel’s new Stratix 10 MX FPGA Taps HBM2 For Massive Memory Bandwidth

Intel's new Stratix 10 MX family launched today, with the first-ever implementation of HBM2. The post Intel’s new Stratix 10 MX FPGA Taps HBM2 For Massive Memory Bandwidth appeared first on
Mega Memory: Crucial Introduces Massive 128GB LRDIMMs

Mega Memory: Crucial Introduces Massive 128GB LRDIMMs

Crucial has announced a new 128GB DDR4 LRDIMM that packs an enormous amount of RAM into a single module. The post Mega Memory: Crucial Introduces Massive 128GB LRDIMMs appeared first on ExtremeTech.
Details Leak on Intel’s Upcoming Radeon-Powered Hades Canyon NUC

Details Leak on Intel’s Upcoming Radeon-Powered Hades Canyon NUC

Intel's new Radeon-powered NUCs are looking seriously impressive. The post Details Leak on Intel’s Upcoming Radeon-Powered Hades Canyon NUC appeared first on ExtremeTech.
Radeon Exec Raja Koduri Has Left AMD

Radeon Exec Raja Koduri Has Left AMD

Raja Koduri led AMD's GPU design efforts for several years, but he's bowing out now that Vega is in-market. Lisa Su will lead the business unit temporarily. The post Radeon Exec Raja Koduri Has Left

Intel and AMD Team up to Create a New Laptop Chip with Integrated GPU and Memory

Intel and Rival have long been rivals in the processor market. However, both these companies are now working together for improved laptop chips. Since most OEMs pair Intel’s Core H-series of mobile
Custom AMD Vega Boards Reportedly Delayed By Technical Issues

Custom AMD Vega Boards Reportedly Delayed By Technical Issues

Board partners are reportedly having yield and design issues with AMD's Vega that could delay the launch of custom GPUs. The post Custom AMD Vega Boards Reportedly Delayed By Technical Issues appeared
Tantalizing Rumors Leak Ahead of AMD’s Vega Launch

Tantalizing Rumors Leak Ahead of AMD’s Vega Launch

New information about AMD's RX Vega has leaked, including onboard VRAM, product SKUs, and TDP ratings. The post Tantalizing Rumors Leak Ahead of AMD’s Vega Launch appeared first on ExtremeTech.
Early AMD Radeon Vega Frontier Edition Benchmarks Surface

Early AMD Radeon Vega Frontier Edition Benchmarks Surface

Early benchmarks on AMD's Vega Frontier Edition are beginning to show up, but it's still early for firm conclusions about the GPU's performance relative to its Nvidia counterparts. The post Early AMD
Samsung Wants to Lead the Foundry Business to 4nm and Beyond

Samsung Wants to Lead the Foundry Business to 4nm and Beyond

Samsung has announced its own plans for foundry tech ramp-ups and rollouts, beginning immediately and stretching over the next four years. From EUV and fully-depleted silicon to HBM2 and new packaging