Monday, July 22nd 2024
AMD "Strix Halo" Processor Boosts up to 5.35 GHz, Geekbenched
AMD's upcoming "Strix Halo" mobile processor that features up to 16 "Zen 5" CPU cores and a powerful iGPU with 40 compute units, is beginning to surface in online benchmark databases. We've gone into the juicy technical bits about the processor in our older articles, but put simply, it is a powerful mobile processor meant to square off against the likes of the Apple M3 Pro and M3 Max. A chiplet-based processor, much like the upcoming "Granite Ridge" desktop processor and "Fire Range" mobile processor, "Strix Halo" features up to 16 full-sized "Zen 5" cores, as it uses up to two of the same "Eldora" CCDs as them; but wired to a large I/O die that contains the oversized iGPU, and an NPU, besides the memory controllers. The iGPU has 40 compute units (2,560 stream processors), and is based on the RDNA 3.5 graphics architecture, while the NPU is the same 50 TOPS-class unit carried over from "Strix Point."
A prototype HP laptop powered by a "Strix Halo" processor that uses a single 8-core "Zen 5" CCD, was spied on the web. This chip has eight full-sized "Zen 5" cores that share a 32 MB L3 cache. The iGPU on the I/O die has its own 32 MB Infinity Cache memory that cushions memory transfers. In our older reports, we speculated as to what the memory interface of "Strix Halo" would be. It turns out that the chip exclusively features a 256-bit wide LPDDR5X memory interface, which is double the bus width of "Strix Point." This is essentially what a "quad-channel DDR5" memory interface would be, and AMD is using a memory speed standard of at least LPDDR5X-8000. From the machine's point of view, this would be just a couple of hardwired LPDDR5X chips, or a pair of LPCAMM 2 modules. Back to the benchmarks, and we are shown a single-thread CPU score of 2099 to 2177 points, and a multithreaded score ranging between 5477 points to 13993 points. The laptop was tested with an unknown version and distribution of Linux. The CPU cores are shown boosting up to 5.35 GHz.
Sources:
Geekbench database, Notebookcheck, Videocardz
A prototype HP laptop powered by a "Strix Halo" processor that uses a single 8-core "Zen 5" CCD, was spied on the web. This chip has eight full-sized "Zen 5" cores that share a 32 MB L3 cache. The iGPU on the I/O die has its own 32 MB Infinity Cache memory that cushions memory transfers. In our older reports, we speculated as to what the memory interface of "Strix Halo" would be. It turns out that the chip exclusively features a 256-bit wide LPDDR5X memory interface, which is double the bus width of "Strix Point." This is essentially what a "quad-channel DDR5" memory interface would be, and AMD is using a memory speed standard of at least LPDDR5X-8000. From the machine's point of view, this would be just a couple of hardwired LPDDR5X chips, or a pair of LPCAMM 2 modules. Back to the benchmarks, and we are shown a single-thread CPU score of 2099 to 2177 points, and a multithreaded score ranging between 5477 points to 13993 points. The laptop was tested with an unknown version and distribution of Linux. The CPU cores are shown boosting up to 5.35 GHz.
20 Comments on AMD "Strix Halo" Processor Boosts up to 5.35 GHz, Geekbenched
Core i9 14900HX 32 mobile threads 55-150W ~$600
Geforce 4070 36 mobile CUs 35-120W ~$600
LPDDR5X 8000 128 GB 5-10W ~$300
Total watts: 90 - 280W
Total price: $1500
versus
Strix Halo, 32 mobile threads, 40 CUs, 128 GB 256 bit LPDDR5X 8000, 70-130W
AMD Ryzen 9050 "Strix Halo" specs leaked: 16 Zen5 cores and 40 RDNA3.5 CUs, LP5x-8000 memory and 32MB MALL cache - VideoCardz.com
Depending on the configuration, Strix Halo can be anywhere from the same to half the power at the same CPU and GPU performance. The combined CPU/GPU/RAM with lower power helps with more room for larger battery on top of chip power savings. The part only needs to be $1000 or less for it to be a more cost-effective solution as well.
Also a typical gaming laptop is going to have something more like an 8-core CPU and a big dGPU. This is also similar to what a lot of gaming desktops have. If we just want an APU for a gaming laptop which doesn't need a dGPU, then I think 16 CPU cores is going to add more cost than value.
chipsdies?I asked ChatGPT for lulz, this was the response:
AMD APUs (Accelerated Processing Units) can run higher frequency memory (RAM) than their desktop, non-APU counterparts primarily due to the integration of the GPU within the APU itself. Here are the key reasons for this difference:
- Integrated Graphics Performance:
- APUs combine CPU and GPU cores on a single chip. The integrated GPU in an APU relies heavily on system RAM for graphics memory since it doesn't have dedicated VRAM like discrete graphics cards.
- Higher memory frequency increases the bandwidth available to the integrated GPU, which significantly improves graphics performance. Therefore, AMD designs APUs to support higher memory frequencies to maximize the integrated GPU's potential.
- Optimized Memory Controller:
- AMD APUs are designed with a memory controller that can handle higher memory frequencies more effectively. This is because the performance of the integrated GPU is directly tied to the memory bandwidth, necessitating a more robust and capable memory controller.
- Unified Memory Architecture:
- The APU's architecture integrates both CPU and GPU in such a way that they share the same memory pool. To ensure both the CPU and GPU can operate efficiently, especially for graphical tasks, the memory controller is optimized to support higher speed memory.
- Market Positioning:
- APUs are often targeted at users who need decent graphics performance without a discrete GPU, such as in budget gaming or multimedia PCs. Supporting higher frequency RAM helps APUs deliver better overall system performance in these scenarios, making them more attractive to consumers.
- Efficiency and Performance Balance:
- Higher frequency memory improves data transfer rates between the CPU/GPU and memory, leading to better overall system responsiveness and performance. For APUs, this balance is crucial because it allows both the CPU and GPU parts to operate efficiently, especially in memory-intensive tasks like gaming and video editing.
In contrast, desktop non-APU CPUs typically rely on discrete GPUs for graphics tasks. These discrete GPUs have their own dedicated high-speed VRAM, making the system less dependent on the frequency of the system RAM. Therefore, the memory controller in non-APU CPUs isn't necessarily optimized for higher frequency RAM to the same extent as in APUs.Still makes no sense if you have a memory controller on the APU that can run higher memory frequency, surely they would integrate that into the regular desktop counterparts, AMD allow PBO, CO, Overclocking etc as they know there is a market for all of those things as well as higher RAM frequency.
ChatGPT? chat a lot of shit more like it :slap::roll: