With the latest industry boom in AI, the demand for more compute power is greater than ever, and the recent industry forecast predicts that the global GPU market will exceed $98.5 billion in value by the year 2024. This staggering projection, outlined in the 2024 supply-side GPU market summary report by Jon Peddie Research (JPR), shows how far the GPU market has come. Once primarily associated with powering consumer gaming rigs with AMD or NVIDIA inside, GPUs have become a key part of our modern tech stack, worth almost $100 billion in 2024 alone. Nowadays, GPUs are found in many products, from smartphones and vehicles to internet-connected devices and data centers.

"Graphics processor units (GPUs) have become ubiquitous and can be found in almost every industrial, scientific, commercial, and consumer product made today," said Dr. Jon Peddie, founder of JPR. "Some market segments, like AI, have grabbed headlines because of their rapid growth and high average selling price (ASP), but they are low-volume compared to other market segments." The report also shows the wide range of companies that are actively participating in the GPU marketplace, including industry giants like AMD, NVIDIA, and Intel, as well as smaller players from China like Loongson Zhongke, Siroyw, and Lingjiu Micro. Besides the discrete GPU solutions, the GPU IP market is very competitive, and millions of chips are shipped with GPU IP every year. Some revenue estimates of Chinese companies are not public, but JPR is measuring it from the supply chain side, so these estimates are pretty plausible.

A MyDrivers news report suggests that Loongson's LS3C6000 server processor has reached the tape-out phase of development—the article's author appears to be quite excited about this chip's prospects; a performance uptick could position it closer to past generation Intel and AMD parts. The company's proprietary LA664 "LoongArch" instruction set will be deployed on a chip design that accommodates 16 cores with simultaneous multi-threading technology (SMT) and 32 threads. In-house engineers think that the 3C6000 processor series is just as performant as Zen 3 and Tiger Lake (11th-gen Core) architectures, in terms of instructions per clock (IPC).

Loongson has reportedly deployed its Dragon Chain interconnect technology with the 3C6000 generation—the I/O interface is said to be much improved over current 3C5000-based server products. Company engineers have: "solved the bottleneck in the expansion of the number of processor cores. In the future, the company will also seal 32-core processors on the basis of 3C6000. 64-core products are possibly incoming later on." The MyDrivers article proposes that Loongson is targeting growing demand within China's server market, but LS3C6000 remains a "big project" that requires further compatibility and performance optimizations.

China's homegrown Loongson 3A6000 CPU shows promise but still needs to catch up AMD and Intel's latest offerings in real-world performance. According to benchmarks by Chinese tech reviewer Geekerwan, the 3A6000 has instructions per clock (IPC) on par with AMD's Zen 4 architecture and Intel's Raptor Lake. Using the SPEC CPU 2017 processor benchmark, Geekerwan has clocked all the CPUs at 2.5 GHs to compare the raw benchmark results to Zen 4 and Intel's Raptor Lake (Raptor Cove) processors. As a result, the Loongson 3A6000 seemingly matches the latest designs by AMD and Intel in integer results, with integer IPC measured at 4.8, while Zen 4 and Raptor Cove have 5.0 and 4.9, respectively. The floating point performance is still lagging behind a lot, though. This demonstrates that Loongson's CPU design can catching up to global leaders, but still needs further development, especially for floating point arithmetic.

However, the 3A6000 is held back by low clock speeds and limited core counts. With a maximum boost speed of just 2.5 GHz across four CPU cores, the 3A6000 cannot compete with flagship chips like AMD's 16-core Ryzen 9 7950X running at 5.7 GHz. While the 3A6000's IPC is impressive, its raw computing power is a fraction of that of leading x86 CPUs. Loongson must improve manufacturing process technology to increase clock speeds, core counts, and cache size. The 3A6000's strengths highlight Loongson's ambitions: an in-house LoongArch ISA design fabricated on 12 nm achieves competitive IPC to state-of-the-art x86 chips built on more advanced TSMC 5 nm and Intel 7 nm nodes. This shows the potential behind Loongson's engineering. Reports suggest that next-generation Loongson 3A7000 CPUs will use SMIC 7 nm, allowing higher clocks and more cores to better harness the architecture's potential. So, we expect the next generation to set a bar for China's homegrown CPU performance.

The Chinese chipmaker Loongson has launched its newest desktop processors, the 4-core, 8-thread 3A6000 series, based on the company's LoongArch microarchitecture. We have previously reported that the company wants to match Intel's "Willow Cove" and AMD's Zen 3 instruction per clock (IPC) levels with its 3A6000 CPU series, and today we have the first preview of the performance. Powered by the LA664 cores, 3A6000 is built on a 14/12 nm manufacturing process, with clock speeds going from 2.0 to 2.5 GHz and power consumption of up to 50 Watts. It features 256 KB of L2 cache and 16 MB of L3 cache in total.

While several hardware partners are announcing new Loongson-powered solutions, ASUS China's "Uncle Tony" managed to get his hands on one of them and overclocker the CPU to 2.63 GHz on air cooling. In overclocking tests using liquid nitrogen cooling, a 3A6000 processor reached 3.0 GHz, though there are indications that there is still overhead. In standard out-of-the-box configuration, the 3A6000 performs similarly to Intel's Core i3-10100 four-core CPU, an achievement for Loongson but still behind Intel's latest offerings that clock nearly twice as high. This rapid development of Loongson IP has led to a massive performance increase, matching the IPC of modern CPUs. We are still left to see more information about these 3A6000 series SKUs; however, early benchmarks suggest a significant improvement. You can see the CPU benchmarks below, which include UnixBench and SPEC CPU 2006.

Chinese company Loongson, specializing in creating processors for usage in mainland China, has been steadily working on enabling its next-generation Loongson 3A6000 CPUs. Aiming to provide the performance level of Intel Willow Cove and AMD Zen 3, these new CPUs will use Loongson's custom LoongArch Instruction Set Architecture (ISA) with a new set of 64-bit superscalar LA664 cores. Today, thanks to the report from Phoronix, we find out that Loongson has submitted some Linux patches that enable the upcoming 3A6000 CPUs to work with Linux-based operating systems at launch. Interestingly, as the new CPU generation gets closer to launch, more Linux kernel patches begin to surface.

Today's kernel patches focus on supporting the hardware page table walker (PTW). As PTW can handle all fast paths of TLBI/TLBL/TLBS/TLBM exceptions by hardware, software only needs to handle slow paths such as page faults. Additionally, in the past, LoongArch utilized "dbar 0" as a complete barrier for all operations. However, this full completion barrier severely impacted performance. As a result, Loongson-3A6000 and subsequent processors have introduced various alternative hints. Loongson plans to ship samples to select customers in the first half of 2023, so we could see more information surfacing soon.

Amid the push for technology independence, Chinese companies are pushing out more products to satisfy the need for the rapidly soaring demand for domestic data processing silicon. Today, we have information that Chinese Loongson has launched a 3D5000 CPU with as many as 32 cores. Utilizing chiplet technology, the 3D5000 represents a combination of two 16-core 3C5000 processors based on LA464 cores, based on LoongArch ISA that follows the combination of RISC and MIPS ISA design principles. The new chip features 64 MB of L3 cache, supports eight-channel DDR4-3200 ECC memory achieving 50 GB/s, and has five HyperTransport (HT) 3.0 interfaces. The TDP configuration of the chip is officially 300 Watts; however, normal operation is usually at around 150 Watts, with LA464 cores running at 2 GHz.

Scaling of the new chip goes beyond the chiplet, and pours over into system, as 3D5000 supports 2P and 4P configurations, where a single motherboard can become a system of up to 128 cores. To connect them, Loongson uses a 7A2000 bridge chip that is reportedly 400% faster than the previous solution, although we have no information about the last chip bridge. Based on the LGA-4129 package, the chip size is 75.4x58.5×6.5 mm. Regarding performance, Loongson compares it to the average Arm chip that goes into smartphones and claims that its designs are up to four times faster. In SPEC2006, performance reaches 425 points, while maintaining a single TeraFLOP at dual-precision 64-bit format. On the other hand, the processor was built for security, as the chip has a custom hardware-baked security to prevent Spectre and Meltdown, has an on-package Trusted Platform Module (TPM), and has a secret China-made security algorithm with an embedded custom security module that does encryption and decryption at 5 Gbps.

Chinese processor designers need help creating a leading-edge design that satisfies their needs, with the imposed sanctions and restrictions of Western countries. However, designers are using creative ways to make a server processor to fulfill their needs. According to the latest Sina report, Chinese company Loongson has developed a 32-core processor using chiplet technology. Previously, the company announced its 16-core 3C5000 processor based on LA464 cores, which utilize LoongArch ISA. Loongson used chiplet technology to fuse two 3C5000 processors into a single-socket solution called 3D5000, which features 32 LA464 cores to create a higher-performing design. Based on the LGA-4129 package, the chip size is 75.4x58.5×6.5 mm.

The company claims that the typical power consumption is rated for 130 Watts at 2.0 GHz or 170 Watts at 2.2 GHz, with TDP power consumption not exceeding 300 Watts at 2.2 GHz even with peaks. The performance of the new 3D5000 processor, measured using SPEC2006, is 400 points and 800 points for single-socket and dual-socket servers, respectively. The four-socket server is expected to reach 1600 points in the same benchmark, so scaling is advertised as linear. Loongson hopes to provide samples to industry partners in the first half of 2023 with an unknown price tag.

Chinese PC and server processor designer Loongson claims that its upcoming processor microarchitecture will offer an IPC that matches that of the AMD "Zen 3" (or slightly faster than Intel "Willow Cove."). The Godson 3A6000 processors are based on the LA664 microarchitecture, which Loongson has compared with off-the-shelf AMD Ryzen 5 5600G and Intel Core i7-1165G7 processors, on several cross-platform benchmarks, and claimed to have obtained comparable single-threaded performance.

The LA664 microarchitecture is based on Loongson's in-house ISA, and unlike Zhaoxin processors, aren't x86-64 compatible. Loongson processors are generally bought in bulk by the Chinese government and military, to run servers and workstations that are completely devoid of foreign hardware, for security reasons. The custom machine architecture is paired with a compatible *nix operating system that's equally built from the ground-up. 2023 will see Loongson launch 3A6000 processor as a multi-chip module with 32 CPU cores.