The battle of AI acceleration in the data center is, as most readers are aware, insanely competitive, with NVIDIA offering a top-tier software stack. However, AMD has tried in recent years to capture a part of the revenue that hyperscalers and OEMs are willing to spend with its Instinct MI300X accelerator lineup for AI and HPC. Despite having decent hardware, the company is not close to bridging the gap software-wise with its competitor, NVIDIA. According to the latest report from SemiAnalysis, a research and consultancy firm, they have run a five-month experiment using Instinct MI300X for training and benchmark runs. And the findings were surprising: even with better hardware, AMD's software stack, including ROCm, has massively degraded AMD's performance.

"When comparing NVIDIA's GPUs to AMD's MI300X, we found that the potential on paper advantage of the MI300X was not realized due to a lack within AMD public release software stack and the lack of testing from AMD," noted SemiAnalysis, breaking down arguments in the report further, adding that "AMD's software experience is riddled with bugs rendering out of the box training with AMD is impossible. We were hopeful that AMD could emerge as a strong competitor to NVIDIA in training workloads, but, as of today, this is unfortunately not the case. The CUDA moat has yet to be crossed by AMD due to AMD's weaker-than-expected software Quality Assurance (QA) culture and its challenging out-of-the-box experience."

AMD has released the new ROCm 6.3 version which introduces several new features and optimizations, including SGLang integration for accelerated AI inferencing, a re-engineered FlashAttention-2 for optimized AI training and inference, the introduction of multi-node Fast Fourier Transform (FFT), new Fortran compiler, and enhanced computer vision libraries like rocDecode, rocJPEG, and rocAL.

According to AMD, the SGLang, a runtime that is now supported by ROCm 6.3, is purpose-built for optimizing inference on models like LLMs and VLMs on AMD Instinct GPUs, and promises 6x higher throughput and much easier usage thanks to Python-integrated and pre-configured ROCm Docker containers. In addition, the AMD ROCm 6.3 also brings further transformer optimizations with FlashAttention-2, which should bring significant improvements in forward and backward pass compared to FlashAttention-1, a whole new AMD Fortran compiler with direct GPU offloading, backward compatibility, and integration with HIP Kernels and ROCm libraries, a whole new multi-node FFT support in rocFFT, which simplifies multi-node scaling and improved scalability, as well as enhanced computer vision libraries, rocDecode, rocJPEG, and rocAL, for AV1 codec support, GPU-accelerated JPEG decoding, and better audio augmentation.

AMD and Fujitsu Limited today announced that they have signed a memorandum of understanding (MOU) to form a strategic partnership to create computing platforms for AI and high-performance computing (HPC). The partnership, encompassing aspects from technology development to commercialization, will seek to facilitate the creation of open source and energy efficient platforms comprised of advanced processors with superior power performance and highly flexible AI/HPC software and aims to accelerate open-source AI and/or HPC initiatives.

Due to the rapid spread of AI, including generative AI, cloud service providers and end-users are seeking optimized architectures at various price and power per performance configurations. From end-to-end, AMD supports an open ecosystem, and strongly believes in giving customers choice. Fujitsu has worked to develop FUJITSU-MONAKA, a next-generation Arm-based processor that aims to achieve both high performance and low power consumption. With FUJITSU-MONAKA, together with AMD Instinct accelerators, customers have an additional choice to achieve large-scale AI workload processing to whilst attempting to reduce the data center total cost of ownership.

AMD today introduced the Radeon PRO V710, the newest member of AMD's family of visual cloud GPUs. Available today in private preview on Microsoft Azure, the Radeon PRO V710 brings new capabilities to the public cloud. The AMD Radeon PRO V710's 54 Compute Units, along with 28 GB of VRAM, 448 GB/s memory transfer rate, and 54 MB of L3 AMD Infinity Cache technology, support small to medium ML inference workloads and small model training using open-source AMD ROCm software.

With support for hardware virtualization implemented in compliance with the PCI Express SR-IOV standard, instances based on the Radeon PRO V710 can provide robust isolation between multiple virtual machines running on the same physical GPU and between the host and guest environments. The efficient RDNA 3 architecture provides excellent performance per watt, enabling a single slot, passively cooled form factor compliant with the PCIe CEM spec.

AMD today announced that Oracle Cloud Infrastructure (OCI) has chosen AMD Instinct MI300X accelerators with ROCm open software to power its newest OCI Compute Supercluster instance called BM.GPU.MI300X.8. For AI models that can comprise hundreds of billions of parameters, the OCI Supercluster with AMD MI300X supports up to 16,384 GPUs in a single cluster by harnessing the same ultrafast network fabric technology used by other accelerators on OCI. Designed to run demanding AI workloads including large language model (LLM) inference and training that requires high throughput with leading memory capacity and bandwidth, these OCI bare metal instances have already been adopted by companies including Fireworks AI.

"AMD Instinct MI300X and ROCm open software continue to gain momentum as trusted solutions for powering the most critical OCI AI workloads," said Andrew Dieckmann, corporate vice president and general manager, Data Center GPU Business, AMD. "As these solutions expand further into growing AI-intensive markets, the combination will benefit OCI customers with high performance, efficiency, and greater system design flexibility."

The upcoming Strix Point Halo processors from AMD now have a new name - Ryzen AI Max - and come with big promises of impressive power. This rumor, first reported by VideoCardz and originating from Weibo leaker Golden Pig Upgrade, reveals key details about the first three processors in this lineup, along with their specifications.

The leaker claims AMD might roll out a new naming system for these processors branding them as part of the Ryzen AI Max series. These chips will run on the anticipated Strix Halo APU. This series includes three models, with the top-end version boasting up to 16 Zen 5 cores and 40 Compute Units (CUs) for graphics. This setup is expected for the best model contrary to earlier rumors that AMD would drop such a variant. In fact, word has it that at least two of the models in this lineup will come with 40 RDNA 3.5 Compute Units. The leaker also hints that Strix Halo will handle up to 96 GB of video memory suggesting AMD aims to make this processor work with its ROCm (Open Compute Platform) system.

A few days ago, we reported on AMD's newest expansion plans for Serbia. The company opened two new engineering design centers with offices in Belgrade and Nis. We were invited to join the opening ceremony and got an exclusive interview with one of AMD's top executives, Andrej Zdravkovic, who is the senior vice president and Chief Software Officer. Previously, we reported on AMD's transition to become a software company. The company has recently tripled its software engineering workforce and is moving some of its best people to support these teams. AMD's plan is spread over a three to five-year timeframe to improve its software ecosystem, accelerating hardware development to launch new products more frequently and to react to changes in software demand. AMD found that to help these expansion efforts, opening new design centers in Serbia would be very advantageous.

We sat down with Andrej Zdravkovic to discuss the purpose of AMD's establishment in Serbia and the future of some products. Zdravkovic is actually an engineer from Serbia, where he completed his Bachelor's and Master's degrees in electrical engineering from Belgrade University. In 1998, Zdravkovic joined ATI and quickly rose through the ranks, eventually becoming a senior director. During his decade-long tenure, Zdravkovic witnessed a significant industry shift as AMD acquired ATI in 2006. After a brief stint at another company, Zdravkovic returned to AMD in 2015, bringing with him a wealth of experience and a unique perspective on the evolution of the graphics and computing industry.Here is the full interview:

Today, AMD (NASDAQ: AMD) opened a new engineering design center in Serbia, with offices in Belgrade and Nis, strengthening its presence in the Balkans region. The new design center will employ highly skilled software engineers focused on the development of software technologies optimized for AMD leadership compute platforms, including the AMD ROCm software stack for AMD Instinct data center accelerators and AMD Radeon graphics cards. The center was established through an agreement with HTEC, a global technology services company.

"Software plays a critical role in unlocking the capabilities of our leadership AMD hardware. Our new design center will be instrumental in enabling both the design and deployment of future generations of AMD Instinct and Radeon accelerators to help make end-to-end AI solutions more accessible to customers around the world," said Andrej Zdravkovic, senior vice president and chief software officer at AMD. "Our investments in Serbia are a testament to the Balkan region's strong engineering talent, and we are excited to collaborate with HTEC, local universities and the vibrant ecosystem in Belgrade and Nis as we deepen our presence in the region over the coming years."

The MLCommons consortium on Wednesday posted MLPerf Inference v4.1 benchmark results for popular AI inferencing accelerators available in the market, across brands that include NVIDIA, AMD, and Intel. AMD's Instinct MI300X accelerators emerged competitive to NVIDIA's "Hopper" H100 series AI GPUs. AMD also used the opportunity to showcase the kind of AI inferencing performance uplifts customers can expect from its next-generation EPYC "Turin" server processors powering these MI300X machines. "Turin" features "Zen 5" CPU cores, sporting a 512-bit FPU datapath, and improved performance in AI-relevant 512-bit SIMD instruction-sets, such as AVX-512, and VNNI. The MI300X, on the other hand, banks on the strengths of its memory sub-system, FP8 data format support, and efficient KV cache management.

The MLPerf Inference v4.1 benchmark focused on the 70 billion-parameter LLaMA2-70B model. AMD's submissions included machines featuring the Instinct MI300X, powered by the current EPYC "Genoa" (Zen 4), and next-gen EPYC "Turin" (Zen 5). The GPUs are backed by AMD's ROCm open-source software stack. The benchmark evaluated inference performance using 24,576 Q&A samples from the OpenORCA dataset, with each sample containing up to 1024 input and output tokens. Two scenarios were assessed: the offline scenario, focusing on batch processing to maximize throughput in tokens per second, and the server scenario, which simulates real-time queries with strict latency limits (TTFT ≤ 2 seconds, TPOT ≤ 200 ms). This lets you see the chip's mettle in both high-throughput and low-latency queries.

Just a few weeks ago, AMD invited us to Barcelona as part of a roundtable, to share their vision for the future of the company, and to get our feedback. On site, were prominent AMD leadership, including Phil Guido, Executive Vice President & Chief Commercial Officer and Jack Huynh, Senior VP & GM, Computing and Graphics Business Group. AMD is making changes in a big way to how they are approaching technology, shifting their focus from hardware development to emphasizing software, APIs, and AI experiences. Software is no longer just a complement to hardware; it's the core of modern technological ecosystems, and AMD is finally aligning its strategy accordingly.

The major difference between AMD and NVIDIA is that AMD is a hardware company that makes software on the side to support its hardware; while NVIDIA is a software company that designs hardware on the side to accelerate its software. This is about to change, as AMD is making a pivot toward software. They believe that they now have the full stack of computing hardware—all the way from CPUs, to AI accelerators, to GPUs, to FPGAs, to data-processing and even server architecture. The only frontier left for AMD is software.

AMD has unveiled the latest release of its open software, AMD ROCm 6.1.3, marking the next step in its strategy to make ROCm software broadly available across its GPU portfolio, including AMD Radeon desktop GPUs. The new release gives developers broader support for Radeon GPUs to run ROCm AI workloads. "The new AMD ROCm release extends functional parity from data center to desktops, enabling AI research and development on readily available and accessible platforms," said Andrej Zdravkovic, senior vice president at AMD.

Key feature enhancements in this release focus on improving compatibility, accessibility, and scalability, and include:

• Multi-GPU support to enable building scalable AI desktops for multi-serving, multi-user solutions.
• Beta-level support for Windows Subsystem for Linux, allowing these solutions to work with ROCm on a Windows OS-based system.
• TensorFlow Framework support offering more choice for AI development.

In addition to the new Zen 5 Ryzen 9000 series desktop CPUs and Ryzen AI 300 series mobile CPUs, as well as the new Ryzen 5000XT series AM4 socket desktop CPUs and updates to the AMD Instinct AI GPU roadmap, AMD rather silently announced the new Radeon PRO W7900 Dual Slot workstation graphics card at the Computex 2024. While not a completely new product, as it is just a model update of the currently available flagship Radeon PRO W7900 workstation graphics card, it is still a rather important update since AMD managed to squeeze it into a dual-slot design, which gives it support for multi-GPU setups.

As said, the AMD Radeon PRO W7900 Dual Slot still uses the same Navi 31 GPU with 96 Compute Units (CUs), 96 Ray Accelerators, 192 AI Accelerators, and 6144 Stream Processors, as well as 48 GB of GDDR6 ECC memory on a 384-bit memory interface, giving it maximum memory bandwidth of 864 GB/s. It still needs 2x8-pin PCIe power connectors and has a Total Board Power (TBP) of 295 W. The card still comes with three DisplayPort 2.1 and one Enhanced Mini DisplayPort 1.2 outputs. What makes the new Radeon PRO W7900 Dual Slot special is the fact that AMD managed to get it down to a dual-slot design, even with the same blower-fan cooler. Unfortunately, it is not clear if the fan or its profiles are different, but it does make it suitable to be used in multi-GPU configurations.

AMD has quietly added some interesting codenames to its ROCm hardware support list. The biggest surprise is the appearance of "RDNA 4" and "Navi 44" codenames, hinting at a potential successor to the current RDNA 3 GPU architecture powering AMD's Radeon RX 7000 series graphics cards. The upcoming Radeon RX 8000 series could see Navi 44 SKU with a codename "gfx1200". While details are scarce, the inclusion of RDNA 4 and Navi 44 in the ROCm list suggests AMD is working on a new GPU microarchitecture that could bring significant performance and efficiency gains. While RDNA 4 may be destined for future Radeon gaming GPUs, in the data center GPU compute market, AMD is preparing a CDNA 4 based successors to the MI300 series. However, it appears that we haven't seen all the MI300 variants first. Equally intriguing is the "MI300X1" codename, which appears to reference an upcoming AI-focused accelerator from AMD.

While we wait for more information, we can't decipher whether the Navi 44 GPU SKU is for the high-end or low-end segment. If previous generations are for reference, then the Navi 44 SKU would target the low end of the GPU performance spectrum. The previous generation RDNA 3 had Navi 33 as an entry-level model, whereas the RDNA 2 had a Navi 24 SKU for entry-level GPUs. We have reported on RDNA 4 merely being a "bug correction" generation to fix the perf/Watt curve and offer better efficiency overall. What happens finally, we have to wait and see. AMD could announce more details in its upcoming Computex keynote.

Today at Microsoft Build, AMD (NASDAQ: AMD) showcased its latest end-to-end compute and software capabilities for Microsoft customers and developers. By using AMD solutions such as AMD Instinct MI300X accelerators, ROCm open software, Ryzen AI processors and software, and Alveo MA35D media accelerators, Microsoft is able to provide a powerful suite of tools for AI-based deployments across numerous markets. The new Microsoft Azure ND MI300X virtual machines (VMs) are now generally available, giving customers like Hugging Face, access to impressive performance and efficiency for their most demanding AI workloads.

"The AMD Instinct MI300X and ROCm software stack is powering the Azure OpenAI Chat GPT 3.5 and 4 services, which are some of the world's most demanding AI workloads," said Victor Peng, president, AMD. "With the general availability of the new VMs from Azure, AI customers have broader access to MI300X to deliver high-performance and efficient solutions for AI applications."

AMD earlier this month released documentation for the Micro Engine Scheduler (MES) firmware of its RDNA 3 GPUs. The MES is a hardware component that distributes graphics processing and general-purpose compute workloads among the main number-crunching machinery of the AMD GPU—the shader engines, which contain the compute units (CU), the indivisible SIMD muscle of the GPU with programmable shaders and certain kinds of specialized hardware, such as the AI Accelerator and Ray Accelerator. The MES is driven by a programmable firmware, which is what AMD released developer documentation of.

The decision to release MES documentation probably comes from the very top of AMD corporate management. In March, a controversy erupted when Tiny Corp, builders of AI compute servers and workstations, complained of issues testing the Radeon RX 7900 XTX graphics card with a ROCm compute stack, prompting a response from no less than CEO Dr Lisa Su. There were then calls to open-source the firmware, which AMD didn't agree to, probably since it treads on their core GPU hardware IP; but the company did the next best thing, by releasing detailed developer documentation for the MES firmware.

NVIDIA's Compute Unified Device Architecture (CUDA) has long been the de facto standard programming interface for developing GPU-accelerated software. Over the years, NVIDIA has built an entire ecosystem around CUDA, cementing its position as the leading GPU computing and AI manufacturer. However, rivals AMD and Intel have been trying to make inroads with their own open API offerings—ROCm from AMD and oneAPI from Intel. The idea was that developers could more easily run existing CUDA code on non-NVIDIA GPUs by providing open access through translation layers. Developers had created projects like ZLUDA to translate CUDA to ROCm, and Intel's CUDA to SYCL aimed to do the same for oneAPI. However, with the release of CUDA 11.5, NVIDIA appears to have cracked down on these translation efforts by modifying its terms of use, according to developer Longhorn on X.

"You may not reverse engineer, decompile or disassemble any portion of the output generated using Software elements for the purpose of translating such output artifacts to target a non-NVIDIA platform," says the CUDA 11.5 terms of service document. The changes don't seem to be technical in nature but rather licensing restrictions. The impact remains to be seen, depending on how much code still requires translation versus running natively on each vendor's API. While CUDA gave NVIDIA a unique selling point, its supremacy has diminished as more libraries work across hardware. Still, the move could slow the adoption of AMD and Intel offerings by making it harder for developers to port existing CUDA applications. As GPU-accelerated computing grows in fields like AI, the battle for developer mindshare between NVIDIA, AMD, and Intel is heating up.

The latest version of AMD's open-source GPU compute stack, ROCm, is due for launch soon according to a Phoronix article—chief author, Michael Larabel, has been poring over Team Red's public GitHub repositories over the past couple of days. AMD ROCm version 6.0 was released last December—bringing official support for the AMD Instinct MI300A/MI300X, alongside PyTorch improvements, expanded AI libraries, and many other upgrades and optimizations. The v6.0 milestone placed Team Red in a more competitive position next to NVIDIA's very mature CUDA software layer. A mid-February 2024 update added support for Radeon PRO W7800 and RX 7900 GRE GPUs, as well as ONNX Runtime.

Larabel believes that "ROCm 6.1" is in for an imminent release, given his tracking of increased activity on publicly visible developer platforms: "For MIPOpen 3.1 with ROCm 6.1 there's been many additions including new solvers, an AI-based parameter prediction model for the conv_hip_igemm_group_fwd_xdlops solver, numerous fixes, and other updates. AMD MIGraphX will see an important update with ROCm 6.1. For the next ROCm release, MIGraphX 2.9 brings FP8 support, support for more operators, documentation examples for Whisper / Llama-2 / Stable Diffusion 2.1, new ONNX examples, BLAS auto-tuning for GEMMs, and initial code for MIGraphX running on Microsoft Windows." The change-logs/documentation updates also point to several HIPIFY for ROCm 6.1 improvements—including the addition of CUDA 12.3.2 support.

Building on our previously announced support of the AMD Radeon RX 7900 XT, XTX and Radeon PRO W7900 GPUs with AMD ROCm 5.7 and PyTorch, we are now expanding our client-based ML Development offering, both from the hardware and software side with AMD ROCm 6.0. Firstly, AI researchers and ML engineers can now also develop on Radeon PRO W7800 and on Radeon RX 7900 GRE GPUs. With support for such a broad product portfolio, AMD is helping the AI community to get access to desktop graphics cards at even more price points and at different performance levels.

Furthermore, we are complementing our solution stack with support for ONNX Runtime. ONNX, short for Open Neural Network Exchange, is an intermediary Machine Learning framework used to convert AI models between different ML frameworks. As a result, users can now perform inference on a wider range of source data on local AMD hardware. This also adds INT8 via MIGraphX—AMD's own graph inference engine—to the available data types (including FP32 and FP16). With AMD ROCm 6.0, we are continuing our support for the PyTorch framework bringing mixed precision with FP32/FP16 to Machine Learning training workflows.

AMD has quietly funded an effort over the past two years to enable binary compatibility for NVIDIA CUDA applications on their ROCm stack. This allows CUDA software to run on AMD Radeon GPUs without adapting the source code. The project responsible is ZLUDA, which was initially developed to provide CUDA support on Intel graphics. The developer behind ZLUDA, Andrzej Janik, was contracted by AMD in 2022 to adapt his project for use on Radeon GPUs with HIP/ROCm. He spent two years bringing functional CUDA support to AMD's platform, allowing many real-world CUDA workloads to run without modification. AMD decided not to productize this effort for unknown reasons but did open-source it once funding ended per their agreement. Over at Phoronix, there were several benchmarks testing AMD's ZLUDA implementation over a wide variety of benchmarks.

Benchmarks found that proprietary CUDA renderers and software worked on Radeon GPUs out-of-the-box with the drop-in ZLUDA library replacements. CUDA-optimized Blender 4.0 rendering now runs faster on AMD Radeon GPUs than the native ROCm/HIP port, reducing render times by around 10-20%, depending on the scene. The implementation is surprisingly robust, considering it was a single-developer project. However, there are some limitations—OptiX and PTX assembly codes still need to be fully supported. Overall, though, testing showed very promising results. Over the generic OpenCL runtimes in Geekbench, CUDA-optimized binaries produce up to 75% better results. With the ZLUDA libraries handling API translation, unmodified CUDA binaries can now run directly on top of ROCm and Radeon GPUs. Strangely, the ZLUDA port targets AMD ROCm 5.7, not the newest 6.x versions. Only time will tell if AMD continues investing in this approach to simplify porting of CUDA software. However, the open-sourced project now enables anyone to contribute and help improve compatibility. For a complete review, check out Phoronix tests.

References to GFX1150 & GFX1151 targets have been spotted again—this time in a ROCm Github repository—by renowned hardware sleuth; Kepler_L2. These references were first spotted last summer, in an AMDGPU LLVM backend/compiler (reported by Phoronix)—industry experts immediately linked these target codes to next generation "Strix" APU families. The latest leak provides confirmation that the GFX1150 ID is tied to "Strix Point 1," while GFX1151 is an internal IP for "Strix Point Halo," or simply "Strix Halo." The freshly published ROCm Github's commit is titled: "Strix Halo Support and Strix support in staging," which corroborates previous rumors regarding Team Red's engineers being deep into development of Zen 5 (and RDNA 3.5)-based accelerated processing units.

AMD has published several processor product roadmaps with references to "Strix Point" next-gen APUs, with a targeted 2024 launch window. Their December 2023 "Advancing AI Event" confirmed that the "Strix Point" mobile family will sport "XDNA 2" NPUs—previous generation "Phoenix" and recently released "Hawk Point" processors are on the first iteration of XDNA (a spatial dataflow NPU architecture). It is speculated that a typical "Strix Point" laptop processor will pack 12 Zen 5 CPU cores and 16 RDNA 3.5 GPU cores. Team Red has kept quiet about "Strix Halo" (also known as "Sarlak") when conducting public-facing presentations—a loose 2025 launch window is being touted by the rumor mill. The most advanced examples could feature up to 16 Zen 5 CPU cores and 40 RDNA 3.5 GPU cores.

LaminiAI appears to be one of AMD's first customers to receive a bulk order of Instinct MI300X GPUs—late last week, Sharon Zhou (CEO and co-founder) posted about the "next batch of LaminiAI LLM Pods" up and running with Team Red's cutting-edge CDNA 3 series accelerators inside. Her short post on social media stated: "rocm-smi...like freshly baked bread, 8x MI300X is online—if you're building on open LLMs and you're blocked on compute, lmk. Everyone should have access to this wizard technology called LLMs."

An attached screenshot of a ROCm System Management Interface (ROCm SMI) session showcases an individual Pod configuration sporting eight Instinct MI300X GPUs. According to official blog entries, LaminiAI has utilized bog-standard MI300 accelerators since 2023, so it is not surprising to see their partnership continue to grow with AMD. Industry predictions have the Instinct MI300X and MI300A models placed as great alternatives to NVIDIA's dominant H100 "Hopper" series—AMD stock is climbing due to encouraging financial analyst estimations.

Generative AI (GenAI) is the decade's most promising accelerator for innovation with 78% of IT decision makers reporting they're largely excited for the potential GenAI can have on their organizations.¹ Most see GenAI as a means to provide productivity gains, streamline processes and achieve cost savings. Harnessing this technology is critical to ensure organizations can compete in this new digital era.

Dell Technologies and AMD are coming together to unveil an expansion to the Dell Generative AI Solutions portfolio, continuing the work of accelerating advanced workloads and offering businesses more choice to continue their unique GenAI journeys. This new technology highlights a pivotal role played by open ecosystems and silicon diversity in empowering customers with simple, trusted and tailored solutions to bring AI to their data.

Today at the "Advancing AI" event, AMD was joined by industry leaders including Microsoft, Meta, Oracle, Dell Technologies, HPE, Lenovo, Supermicro, Arista, Broadcom and Cisco to showcase how these companies are working with AMD to deliver advanced AI solutions spanning from cloud to enterprise and PCs. AMD launched multiple new products at the event, including the AMD Instinct MI300 Series data center AI accelerators, ROCm 6 open software stack with significant optimizations and new features supporting Large Language Models (LLMs) and Ryzen 8040 Series processors with Ryzen AI.

"AI is the future of computing and AMD is uniquely positioned to power the end-to-end infrastructure that will define this AI era, from massive cloud installations to enterprise clusters and AI-enabled intelligent embedded devices and PCs," said AMD Chair and CEO Dr. Lisa Su. "We are seeing very strong demand for our new Instinct MI300 GPUs, which are the highest-performance accelerators in the world for generative AI. We are also building significant momentum for our data center AI solutions with the largest cloud companies, the industry's top server providers, and the most innovative AI startups ꟷ who we are working closely with to rapidly bring Instinct MI300 solutions to market that will dramatically accelerate the pace of innovation across the entire AI ecosystem."

Today, AMD announced the availability of the AMD Instinct MI300X accelerators - with industry leading memory bandwidth for generative AI and leadership performance for large language model (LLM) training and inferencing - as well as the AMD Instinct MI300A accelerated processing unit (APU) - combining the latest AMD CDNA 3 architecture and "Zen 4" CPUs to deliver breakthrough performance for HPC and AI workloads.

"AMD Instinct MI300 Series accelerators are designed with our most advanced technologies, delivering leadership performance, and will be in large scale cloud and enterprise deployments," said Victor Peng, president, AMD. "By leveraging our leadership hardware, software and open ecosystem approach, cloud providers, OEMs and ODMs are bringing to market technologies that empower enterprises to adopt and deploy AI-powered solutions."

AMD is working hard on delivering next-generation products, and today, its Linux team has submitted a few interesting patches that made a subtle appearance through recent GitHub patches for GFX12 targets, as reported by Phoronix. These patches have introduced two new discrete GPUs into the LLVM compiler for Linux, fueling speculation that these will be the first iterations of the RDNA4 graphics architecture, potentially being a part of the Radeon RX 8000 series of desktop graphics cards. The naming scheme for these new targets, GFX1200 and GFX1201, suggests a continuation of AMD's logical progression through graphics architectures, considering the company's history of associating RDNA1 with GFX10 and following suit with subsequent generations, like RDNA2 was GFX10.2 and RDNA3 was GFX11.

The development of these new GPUs is still in the early stages, indicated by the lack of detailed information about the upcoming graphics ISA or its features within the patches. Currently, the new GFX12 targets are set to be treated akin to GFX11 as the patch notes that "For now they behave identically to GFX11," implying that AMD is keeping the specifics under wraps until closer to release. The patch that defines target names and ELF numbers for new GFX12 targets GFX1200 and GFX1201 is needed in order to enable timely support for AMD ROCm compute stack, the AMDVLK Vulkan driver, and the RadeonSI Gallium3D driver.