China has been investing heavily into homegrown microprocessors for the past few years. Phytium’s D2000 is one example of a homegrown design, and we’ll be taking a close look at it in this article. Phytium D2000 consists of eight FTC663 ARM cores running…

In a previous article, we covered Cyberpunk 2077’s “Overdrive” raytracing mode. Rasterization and raytracing are both parallelizable, but raytracing tends to be less predictable. That makes it difficult for GPUs to bring their full parallel processing power…

Please go through part 1 of our Zen 4 coverage, if you haven’t done so already. This article picks up where the previous one left off. To summarize, Zen 4 has made several moves in the frontend and execution engine meant to increase utilization of existing…

AMD’s K7 Athlon architecture formed the basis of the company’s CPU offerings for around a decade. Athlon did very well against Intel’s P6 based Pentium III. K8 got the basics right, introduced 64-bit support and an integrated memory controller. And remained…

Hardware raytracing acceleration has come a long way since Nvidia’s Turing first introduced the technology. Even with these hardware advances, raytracing is so expensive that most games have stuck to very limited raytracing effects, if raytracing is used…

In late May of 2022, AWS released Graviton 3 to the general public. Graviton 3 was the first ARM CPU to introduce the SVE instruction set to a widely accessible server CPU. Before Graviton 3’s general availability, Neoverse N1 dominated the ARM server landscape.…

ARM Ltd has been dominating the Android world for the better part of the last decade, with their 7-series cores at the forefront of their success. Throughout the late 2010s, the Cortex A73, A75, and A76 steadily iterated on performance while maintaining excellent…

Palm Cove (also commonly known as Cannon Lake) is Intel’s 10 nm die shrink of the Skylake core. In Intel’s “Tick Tock” strategy of alternating major microarchitecture changes and ports to new process nodes, Palm Cove was meant to be the “Tick” following Skylake.…

Intel is known for their high performance cores, which combine large out of order execution engines with high clock speeds to maximize single threaded performance. But Intel also has the “Atom” line of architectures, which are designed to make different power…

We at Chips and Cheese have covered two Chinese CPU architectures: Zhaoxin’s x86 compatible Lujiazui architecture found in the KX-6000 series of CPUs and Phytium’s ARM compatible FT663 architecture found in the D2000 series of CPUs. Zhaoxin was founded in…

The world of semiconductor startups looking to break into the market is huge, either with some large AI training chip, or some super fast small inference device, or perhaps a HPC focused design for one particular problem the world is trying to solve. A number…

Tech enthusiasts probably know ARM as a company that develops reasonably performant CPU architectures with a focus on power efficiency. Product lines like the Cortex A7xx and Cortex X series use well balanced, moderately sized out-of-order execution engines…

Author’s Note: Since the publication of this article, we have since had an interview with Tachyum and nearly all of the architectural analysis done in this article is outdated but it will be kept up for posterity. So please visit the new article for our revised…

Note: Jake has commented that Nvidia’s tools may not show the true BVH structure. That’s a distinct possibility, as the structure implied by Nsight is indeed ridiculously wide. The rest of the article will be left unedited (for now) due to time constraints…

In the world of today’s high performance CPUs, major architectural changes don’t happen often. Iterating off a proven base is safer, cheaper, and faster than attempting to massively rework the basics of how a CPU fetches and executes instructions. But more…

Alder Lake (ADL) is the most exciting Intel launch in more than half a decade. For the first time since Skylake, Intel has launched a competitive desktop microarchitecture. But I’m sure you all know that already from other sites that are able to do launch…

CPU design is hard. You can tell because there aren’t a lot of companies doing it. AMD and Intel are your only choices in the PC scene. In the Android ecosystem, ARM Ltd’s cores dominate. Qualcomm, MediaTek, Samsung and other SoC makers put chips together…

Last year we posted an article about Milan’s V-cache performance where we dived into the bandwidth and latency performance of the then-latest innovation by AMD to increase performance of its CPUs. Now, we have already done an article about Zen 4’s V-Cache…

Compute performance has been held back by memory performance for decades, with DRAM performance falling even further behind with every year. Caches compensate for this by trying to keep frequently used data closer to the CPU core. As DRAM performance became…

Previously, we covered Tesla’s Dojo, an unconventional CPU architecture specifically designed for neural network training. We also looked at AMD’s CDNA2, a GPU architecture focused on high performance compute. Now, we’re going to look at Biren’s BR100, a…