← All Posts

AMD Working To 'Push Rust Deep into the GPU Stack'

The Hot Take: Intersting move, I haven't looked into how low level Rust gets compared to C++. Something I need to do I guess.

Phoronix reports: AMD is building out what they are describing as an "elite" team of developers for driving Rust code "deep into the GPU stack" from firmware to drivers, shader compilers, and other GPU software in Rust. AMD Senior Fellow Harsh Meno posted this week to LinkedIn about this new effort... And note this AMD job posting that's active for hiring a software development engineer to work on Rust code... "We are building next-generation systems software for AMD GPUs with Rust as a core technical direction. The…

Read the full article

AMD Is Reportedly Targeting 3.1 To 3.4 GHz Frequency For RDNA 5, Nearly 14% Above Radeon RX 9070 XT

The Hot Take: AMD going to make a push for more than mid-range?

New leak points towards noticeably higher frequencies for AMD's next-generation graphics architecture. AMD RDNA 5 GPUs Could Target Up To 3.4 GHz Clock Speeds, Putting the Architecture up to 14% Ahead of RX 9070 XT's Boost Clock AMD's next-generation graphics architecture, RDNA 5, is still far away from the official launch, but we already have some early leaks pointing to the architecture's capabilities. As you might know, the RDNA 5 architecture is going to power AMD's next-gen graphics stack, including dedicated graphics cards and iGPUs on…

Read the full article

AMD Says A Hybrid-Bonded 3D DRAM Is 17x More Energy Efficient Than An HBM Stack That Relies On Microbumps, But Thermal Hurdles Block Commercialization

The Hot Take: Suddenly we explain this to the world, is this to head off all the questions on where the DRAM supply is going?

The silicon industry has arrived at a consensus that the HBM pathway to unlock incremental AI compute is stalling, especially as converting silicon wafers into an HBM stack yields far less usable capacity than commodity DRAM, prompting the wider industry to start experimenting with SRAM-only decode, Processor-In-Memory (PIM) within LPDDR, CXL pooling, and 3D DRAM. Of course, it is the 3D DRAM architecture that is considered somewhat of a panacea at the moment, as highlighted by AMD's recent admission as to its phenomenal energy efficiency.…

Read the full article

Just one instruction on AMD's 2015-era CPUs gets you access to Platform Security Processor, microcode, and System Management Interface — exploit for 15h and 16h chip families cracks open secret memory areas

The Hot Take: d0h!

Many cybersecurity exploits have been deemed The One Ring To Rule Them All, but that moniker is rarely as true as a literal bit that disables the memory mapping on some AMD CPUs, granting access to normally inaccessible areas. With just one instruction, you can access off-limits software like Platform Security Processor (PSP) where the fTPM runs, the System Management Mode (SMM), microcode patch RAM, and other various sundries — in other words, full hardware-level control.The exploit is called Skitter Creek Bath Salts (Skitter), and was…

Read the full article

AMD acquires AI chip startup Taalas to boost inference performance by etching models into silicon

The Hot Take: That sounds alot like an ASIC...

In AMD’s latest bid to upset Nvidia's dominance in AI hardware, the House of Zen has acquired AI chip company Taalas, which bakes model weights directly into silicon in a process that promises to boost inference performance by an order of magnitude or more. The deal, announced at market close on Thursday, appears to be framed in much the same context as Nvidia’s $20 billion licensing deal with Groq last December: make high-performance ā€œpremiumā€ inference services prized for AI agents, like code assistants, faster and cheaper to run. AMD didn’t…

Read the full article

AMD waits for Nvidia before joining the GPU mugging

The Hot Take: So when is there going to be a price fixing class action for GPUs?

AMD is reportedly preparing to jack up graphics card prices after waiting for Nvidia to blink first. According to PC Gamer the word comes from industry watcher Harukaze5719 who reckons AMD was holding fire until Nvidia pushed up its own prices. ā€œThis was to avoid the risk of declining product competitiveness and market share loss from a hasty price adjustment during a period of demand pressure,ā€ Harukaze5719 wrote on X. AMD has already warned manufacturers about a price rise of ā€œat least 10 per centā€ across all products.Ā The increase is…

Read the full article

Intel knows it needs to ā€˜leapfrog’ ARM and AMD, says CEO Lip-Bu Tan

The Hot Take: I don't think so much ARM as AMD.

Intel CEO Lip-Bu Tan has acknowledged that the semiconductor giant must catch up to rivals AMD and Arm, and said it now assumes edge AI and robotics will be a business as big as PCs. Tan made those remarks during Intel’s Q2 earnings call, which saw the company report $16.1 billion revenue – a 25 percent year-on-year increase. ā€œQ2 was another quarter of solid execution,ā€ the CEO said. ā€œRevenue, gross margin, and earnings per share were above our guidance. This marks the seventh consecutive quarter of exceeding our financial expectations.ā€ Yet…

Read the full article

Intel and AMD lock in year-long CPU deals with Chinese AI firms as prices surge 40%

The Hot Take: Well there goes CPU stocks.

Intel and AMD are signing long term agreements with Chinese data center firms to provide them with CPUs for AI computing, says a report from Reuters. CPUs in AI computing rose to prominence earlier this year after agentic AI demand reshaped the market. Agentic computing places a greater emphasis on CPUs, and according to the sources, the deals are motivated by the rapid price rise due to high demand. AMD & Intel Set To Cover A Year's Worth Of CPU Supplies To Chinese AI Data Centers, Says Report The surge in AI demand for CPUs has also led…

Read the full article

AMD Is Reportedly Pricing Its Helios Rack 40% Above NVIDIA’s Second-Gen Rubin, Confident That Customers Will Pay The Premium

The Hot Take: Will have to take this with a bit rock of salt until we see the benches and real world performance. Just a price grab or actual performance?

AMD is apparently no longer satisfied with being perceived as a perennial underdog, and is reportedly choosing to make a bold statement by pricing its Helios rackscale solution at a hefty premium to NVIDIA's Rubin. What's more, AMD has reportedly managed to rope in Microsoft as the product's first confirmed client, demonstrating the utility that Helios offers even at its supposedly elevated price point. Futurum believes AMD will price Helios at $5 million to $5.5 million per rack, versus an expected retail price of $3.5 million to $4 million…

Read the full article

Intel Posts Initial GCC Compiler Patches For AI Compute Extensions "ACE"

The Hot Take: I really wonder if this will deflate the Ai bubble even a little bit.

The x86 Ecosystem Advisory Group led by Intel and AMD recently firmed up the AI Compute Extensions (ACE) specification for optimizing x86 for AI computation tasks around matrix multiplication and the like for machine learning workloads. The cross-vendor ACE extension is ultimately a successor to Intel's Advanced Matrix Extensions (AMX). Posted to the GCC mailing list today by Intel engineers are the initial patches in preparing the compiler support for ACE...

Read the full article