The first die shot of AMD's new 4 nm "Strix Point" mobile processor surfaced, thanks to an enthusiast on Chinese social media. "Strix Point" is a significantly larger die than "Phoenix." It measures 12.06 mm x 18.71 mm (L x W), compared to the 9.06 mm x 15.01 mm of "Phoenix." Much of this die size increase comes from the larger CPU, iGPU, and NPU. The process has been improved from TSMC N4 on "Phoenix" and its derivative "Hawk Point," to the newer TSMC N4P node.

Nemez (GPUsAreMagic) annotated the die shot in great detail. The CPU now has 12 cores spread across two CCX, one of which contains four "Zen 5" cores sharing a 16 MB L3 cache; and the other with eight "Zen 5c" cores sharing an 8 MB L3 cache. The two CCXs connect to the rest of the chip over Infinity Fabric. The rather large iGPU takes up the central region of the die. It is based on the RDNA 3.5 graphics architecture, and features 8 workgroup processors (WGPs), or 16 compute units (CU) worth 1,024 stream processors. Other key components include four render backends worth 16 ROPs, and control logic. The GPU has its own 2 MB of L2 cache that cushions transfers to the Infinity Fabric.

Since its reveal last week, we got a slightly more technical deep-dive from AMD on its two upcoming processors—the "Strix Point" silicon powering its Ryzen AI 300 series mobile processors; and the "Granite Ridge" chiplet MCM powering its Ryzen 9000 desktop processors. We present a closer look into the "Strix Point" SoC in this article. It turns out that "Strix Point" takes a significantly different approach to heterogeneous multicore than "Phoenix 2." AMD gave us a close look at how this works. AMD built the "Strix Point" monolithic silicon on the TSMC N4P foundry node, with a die-area of around 232 mm².

The "Strix Point" silicon sees the company's Infinity Fabric interconnect as its omnipresent ether. This is a point-to-point interconnect, unlike the ringbus on some Intel processors. The main compute machinery on the "Strix Point" SoC are its two CPU compute complexes (CCX), each with a 32b (read)/16b (write) per cycle data-path to the fabric. The concept of CCX makes a comeback with "Strix Point" after nearly two generations of "Zen." The first CCX contains the chip's four full-sized "Zen 5" CPU cores, which share a 16 MB L3 cache among themselves. The second CCX contains the chip's eight "Zen 5c" cores that share a smaller 8 MB L3 cache. Each of the 12 cores has a 1 MB dedicated L2 cache.

CPUID this week released the latest version of CPU-Z, and its change-log confirms the core-configurations of upcoming AMD Ryzen AI 300-series "Strix Point" processor SKUs. On paper, "Strix Point" packs a 12-core CPU based on the latest "Zen 5" microarchitecture, but there's more to this number. We've known since June 2024 that the chip has a heterogeneous multicore configuration of four full-sized "Zen 5" cores, and eight compacted "Zen 5c" cores. Only the "Zen 5" cores can reach the maximum boost frequencies rated for the chip, while the "Zen 5c" cores go a few notches above the base frequency, although it's expected that the gap in boost frequencies between the two core types is expected to slightly narrow compared to that between the "Zen 4" and "Zen 4c" cores in chips such as the "Phoenix 2."

The series is led by the AMD Ryzen AI 9 HX 375, an enthusiast segment chip that maxes out all 12 cores on the chip—that's 4x "Zen 5" and 8x "Zen 5c." This model is closely followed by the Ryzen AI 9 365, which AMD marked in its presentations as being simply a 10-core/20-thread chip. We're now learning that it has 4x "Zen 5" and 6x "Zen 5c," meaning that AMD hasn't touched the counts of its faster "Zen 5" cores. It's important to note here that "Zen 5c" is not an E-core. It supports SMT, and at base frequency, it has an identical IPC to "Zen 5." It also supports the entire ISA that "Zen 5" does.

Prices of AMD Ryzen 8000G "Hawk Point" desktop APUs in the Socket AM5 package saw reductions over the week. The Ryzen 7 8700G, the fully unlocked part, is now available for $299, a $30 cut from its launch price of $329. Meanwhile, the Ryzen 5 8600G has now slipped under the $200-mark, with a $199 price-tag. The chip had originally launched at $229. Both these chips feature a 16 TOPS NPU, and are the first desktop processors that are capable of on-chip AI acceleration. Both processors are based on the 4 nm "Hawk Point" monolithic silicon, and feature "Zen 4" CPU cores. The 8700G packs an 8-core/16-thread CPU with an RDNA 3 iGPU that has 12 compute units (CU); while the 8600G is 6-core/12-thread, with an iGPU that has 8 CU.

Things get interesting with the Ryzen 5 8500G, which is now down to $159 from its launch price of $179. This new price makes the processor competitive with the 13th Gen Core i3 and the lower end of the Core i5 lineup. Unlike the other two 8000G series chips, the 8500G lacks an NPU, and is based on the 4 nm "Phoenix 2" silicon that has two "Zen 4" and four "Zen 4c" CPU cores for a 6-core/12-thread CPU configuration. Both kinds of cores share a 16 MB L3 cache. It has a heavily cut-down RDNA 3 iGPU with just 4 CU. The Ryzen 8000G desktop APU series only features PCIe Gen 4 (no Gen 5), which may not mean much for today's discrete GPUs, but limit your SSD upgrade path to Gen 4 (Gen 5 SSDs will be limited to 7 GB/s).

AMD formally launched the Ryzen 7 8700F and Ryzen 5 8400F Socket AM5 desktop processors. These are variants based on the Ryzen 8000-series desktop APUs, but with their integrated graphics disabled. The 8700F may lack integrated graphics, but includes the Ryzen AI NPU, with up to 16 AI TOPS performance. The 8400F lacks an NPU. Much like the 8700G, the 8700F packs an 8-core/16-thread CPU based on the current "Zen 4" architecture, but with a 100 MHz lower maximum boost frequency of 5.00 GHz. The TDP is the same, at 65 W, and the retail package includes a Wraith Stealth cooler.

The Ryzen 5 8400F is a 6-core/12-thread processor, but much like the 8500G, it is based on the "Phoenix 2" silicon, which has two "Zen 4" cores that can achieve the maximum 4.70 GHz boost frequency for this chip, and four "Zen 4c" that boost lower. Both kinds of cores feature an identical IPC and ISA, and so AMD Chipset Software uses UEFI CPPC preferred cores software flags to prioritize workload to the "Zen 4" cores. AMD in its launch presentation claims that the 8700F should offer competitive gaming and productivity performance to an Intel Core i5-14400F, and that the 8400F should offer gaming performance in the league of an i5-13400F. The company is pricing the 8700F at $269, or $60 cheaper than the 8700G; while the 8400F is priced at $169, or $10 less than the 8500G.

AMD is indeed bringing the Ryzen 7 8700F and Ryzen 5 8400F desktop processors to the retail PIB channel. Both these processors are based on the 4 nm "Hawk Point" or "Phoenix 2" silicon, but with their iGPU disabled, hence the "F" in the model name. Company slides related to the two were leaked to the web. The processors feature CPU cores based on the "Zen 4" microarchitecture, and are built in the Socket AM5 package.

The Ryzen 7 8700F features the 8-core/16-thread "Zen 4" CPU that the 8700G, but with lower CPU clock speeds of up to 5.00 GHz boost (compared to up to 5.10 GHz for the 8700G). Although its iGPU is disabled, its NPU isn't. The Ryzen AI NPU offers 16 AI TOPS performance. The processor retains the 65 W TDP of the 8700G. Moving on to the 8400G, and here we see the processor being based on the "Phoenix 2" silicon, with 6 CPU cores. Two of these are "Zen 4," and can reach the processor's 4.70 GHz maximum boost frequency; while the other four are "Zen 4c," and operate at lower clock speeds. The chip physically lacks an NPU, and its iGPU is disabled. It still has 65 W TDP to feed its CPU cores. In their retail packages, both processors include a Wraith Stealth cooling solution that's meant for 65 W TDP processors.

AMD is reportedly planning to launch the Ryzen 7 8700F and Ryzen 5 8400F Socket AM5 desktop processors for a global launch, in the retail channel, as boxed processors. The two chips had launched earlier this month in the Chinese retail market. The 8700F reportedly comes with an OPN of 100-100001590BOX, while the 8400F is marked 100-100001591BOX. The "F" in both SKUs denotes a lack of integrated graphics. The Ryzen 7 8700F is an 8-core/16-thread processor based on the 4 nm "Hawk Point" silicon, while the 8400F is a 6-core/12-thread processor based on "Phoenix 2," which offers two "Zen 4" cores that run at higher clock speeds, and four "Zen 4c" cores that run at lower speeds.

The lack of an iGPU isn't the only thing differentiating the 8700F from the 8700G, the new chip even comes with slightly lower CPU clock speeds—100 MHz lower base and maximum boost frequencies. The 8700F CPU runs at a base frequency of 4.10 GHz, with 5.00 GHz maximum boost, when compared to the 4.20/5.10 GHz speeds of the 8700G. The 8400F, on the other hand, runs at 4.20 GHz base frequency, and a 4.70 GHz maximum boost frequency that applies to at least its two "Zen 4" cores; its four "Zen 4c" cores run at lower frequencies. There is no word on pricing. One reason you could want an 8700F over something like a 7700 would be its appetite for memory overclocking, if you can overlook the lack of integrated graphics, a smaller L3 cache, and most importantly, the lack of PCIe Gen 5, and four fewer PCIe lanes.

AMD's next generation Ryzen mobile processor family is undergoing a significant re-positioning of IP within its product stack, as the company introduces the new "elite experience" segment. The "Fire Range" mobile processor is a direct successor to "Dragon Range" MCM, with two 8-core "Zen 5" chiplets. It is essentially a BGA package of the desktop "Granite Ridge" processor, and comes with up to 16 "Zen 5" cores, for flagship gaming notebooks and mobile workstations. A segment below the current "Dragon Range" is the current "Hawk Point" silicon, driving premium experiences. There is a rather large CPU performance gap between the two, as would be the case between the upcoming "Fire Range" and "Kraken Point," which is why AMD is creating the "elite experience" segment, and filling it with "Strix Halo" and "Strix Point," which will square off against Core Ultra 7 and Core Ultra 9 processors, as well as certain HX-segment 14th Gen Core mobile processors. "Strix Point" has a significant core-count increase to 12, along with a large iGPU. We've extensively covered "Strix Point" in our older article, but now we have more information on the elusive "Kraken Point."

"Kraken Point" is codename for AMD's next-generation monolithic mobile processor silicon being designed to power Ryzen processor SKUs competing against the bulk of Intel Core Ultra 5 and Core Ultra 7 SKUs. This chip will be built on a refined 4 nm EUV node by TSMC, and will be monolithic. Its most interesting aspect is the CPU complex. It reportedly features a combination of four regular "Zen 5" cores, and four "Zen 5c" low power cores. All eight cores will likely share a single CCX, which means they share a common L3 cache, which enables easy movement of threads between the two kinds of cores, without having to make round-trips to the DRAM.

GIGABYTE released UEFI firmware (BIOS) updates for its Socket AM5 motherboards encapsulating the AMD AGESA ComboAM5 PI 1.1.0.1a microcode. This latest version of AGESA has sparked speculation that some of AMD's upcoming Ryzen 8000G desktop APUs are in fact based on the newer "Hawk Point" silicon, and not "Phoenix." AMD released its Ryzen 8040 series "Hawk Point" mobile processors earlier this month, with a faster NPU that results in an up to 40% increase in AI interference performance over that of "Phoenix." "Hawk Point" is essentially identical to "Phoenix," including its first generation XDNA architecture based NPU, however the NPU's clock speed has been dialed up. If AMD is building some of its Ryzen 8000G desktop APU models on "Hawk Point" instead of "Phoenix," then we have our first solid hint that AMD is bringing Ryzen AI to the desktop platform, and that the Ryzen 8000G will end up being the first desktop processors with an NPU.

AMD is expected to be building at least two APU models based on the "Hawk Point" silicon, the Ryzen 7 8700G, and the Ryzen 5 8600G. The lower models, namely the 8500G and Ryzen 3 8300G, are expected to be based on the smaller "Phoenix 2" silicon, with a hybrid CPU that combines two "Zen 4" cores with up to four "Zen 4c" cores. The "Zen 4c" cores may feature an identical instruction set architecture (ISA) and IPC to the regular "Zen 4" cores, but have tighter Vcore limits, and operate at lower clock speeds. This makes the two available "Zen 4" cores the de facto "performance" cores, and AMD flags them as UEFI CPPC "preferred cores," ensuring the OS guides a bulk of its processing traffic to them. Both "Phoenix" and "Hawk Point" feature an identical CPU setup, with up to eight "Zen 4" cores.

Here is our first look at the higher end of AMD's Ryzen 8000G series Socket AM5 desktop APU lineup. The company is planning to bring its 4 nm "Phoenix" and "Phoenix 2" monolithic silicon to the socketed desktop platform, to cover two distinct markets. Models based on the larger "Phoenix" silicon cater to the market that wants a sufficiently powerful CPU, but with a powerful iGPU that's fit for entry-level gaming, or graphics-intensive productivity tasks; whereas the smaller "Phoenix 2" silicon ties up the lower end of AMD's AM5 desktop processor stack, as it probably has a lower bill of materials than a "Raphael" multi-chip module.

The lineup is led by the Ryzen 7 8700G, a direct successor to the Ryzen 7 5700G "Cezanne." This chip gets the full 8-core/16-thread "Zen 4" CPU, along with its 16 MB shared L3 cache; and the full featured Radeon 780M iGPU with its 12 compute units worth 768 stream processors. The CPU features a maximum boost frequency of 4.20 GHz. This is followed by the Ryzen 5 8600G, which is based on the same "Phoenix" silicon as the 8700G, but with 6 out of 8 "Zen 4" cores enabled, and a maximum CPU boost frequency of 4.35 GHz, and the 16 MB L3 cache left untouched. It's likely that the Radeon 780M is unchanged from the 8700G.Update 13:59 UTC: A CPU-Z screenshot of the Ryzen 7 8700G surfaced, which confirms that it features the maxed out Radeon 780M iGPU

ASUS began rolling out beta UEFI firmware updates for its Socket AM5 motherboards that contain the latest AMD AGESA 1.1.0.1 microcode. If you recall, ASRock had recently released its own firmware updates last month that feature AGESA 1.1.0.0. This would be the first widely released firmware from ASUS to support the upcoming Ryzen 8000G "Phoenix" and "Phoenix 2" desktop APUs; and the 4th AGESA release to do so. Version ComboAM5PI 1.1.0.1 contains a newer version of the system management unit (SMU) for "Phoenix" and "Phoenix 2," with SMU version 76.75.0, compared to version 76.72.0 with the older ComboAM5PI 1.1.0.0 that ASRock released in November.

The UEFI firmware updates by ASUS containing AGESA ComboAM5PI 1.1.0.1 are only being released for AMD B650/E and X670/E chipset motherboards, and only spanning the company's ROG, ROG Strix, TUF Gaming, and ProArt product lines, we haven't come across one for the Prime series, yet. It's important to reiterate here, that these are beta updates, and those with Ryzen 7000 "Raphael" processors don't stand to benefit from them, as the SMU for "Raphael" hasn't changed since ComboAM5PI 1.0.8.0. Check for the firmware updates in the Support section of the product pages of your motherboard on the ASUS website.

AMD is giving final touches to its first APUs for the Socket AM5 desktop platform. A report by Sakhtafzar Magazine suggests that the company could give processor models in the series Ryzen 8000G numbering, instead of the previously thought 7000G series. The company is preparing as many as 14 processor models spanning the 4 nm "Phoenix" and "Phoenix 2" monolithic dies. Both chips combine "Zen 4" CPU cores with an iGPU based on the RDNA 3 graphics architecture. While the current Ryzen 7000 series "Raphael" desktop processors feature integrated graphics, AMD doesn't consider them APUs, as their iGPU are just about enough for non-gaming desktop use cases. APUs are designed for entry-level gaming.

The "Phoenix" silicon has up to 8 "Zen 4" CPU cores, and an iGPU with up to 12 RDNA3 compute units. This chip is powering the Ryzen 5 8600G, Ryzen 7 8700G, their PRO variants, and their respective "GE" (energy efficient) sub-variants. The "Phoenix 2" silicon barely qualifies as an APU, as its iGPU only has 4 RDNA3 compute units (compared to the 2 RDNA2 CUs on the "Raphael" iGPU. It also has a maximum CPU core count of 6, from which two are "Zen 4" cores that can sustain higher boost frequency bins, and four are "Zen 4c" cores which run at lower clock speeds (albeit with an identical IPC and ISA). AMD is using "Phoenix 2" on the desktop platform to carve out several sub-$150 class processor models across the Ryzen 5 and Ryzen 3 brands; a package with a monolithic "Phoenix 2" die probably has a lower bill of materials (BOM) than a "Raphael" multi-chip module.

AMD's "Phoenix" monolithic processor silicon drives the company's Ryzen 7040 series mobile processor lineup, and possible some of its upcoming Ryzen 7000G desktop processor models. It is the first chip from the AMD camp to feature an AI accelerator, besides up to 8 "Zen 4" CPU cores, and a large iGPU based on the latest RDNA3 graphics architecture, with up to 12 compute units, the latest display I/O and media acceleration capabilities. Over the course of its lifecycle, AMD realized that it can't use the nearly 200 mm² silicon built on the expensive 4 nm node to power lower-end processor SKUs, and so developed the smaller 137 mm² "Phoenix 2" silicon that lacks the AI accelerator, has a smaller iGPU with just 4 compute units, and a unique hybrid CPU with 2 "Zen 4" and 4 "Zen 4c" cores. We're now hearing that the company is designing even more derivatives.

The PCI ID Repository discovered two new IDs believed to reference the iGPU models of "Phoenix 3" and "Phoenix 4" chips. At this point we have no clue what the two chips could be, and what the mixture of their CPU, iGPU, and AI accelerator components could be, especially given that AMD is able to carve out Ryzen 3 SKUs from "Phoenix 2." We speculate that "Phoenix 3" and "Phoenix 4" could reference rebranding such as "Escher," although it could even be entirely new chips with different combinations of "Zen 4" and "Zen 4c" cores.

ASRock began rolling out UEFI firmware updates for its Socket AM5 motherboards that encapsulate AMD AGESA 1.1.0.0 ComboAM5PI microcode. This would be the second release of AGESA to support AMD's upcoming Ryzen 7000G "Phoenix" and "Phoenix 2" desktop APUs that the company reportedly plans to launch later this year. The AGESA 1.1.0.0 microcode comes with the SMU version 76.72.0 for "Phoenix" and "Phoenix 2," and continues with version 84.79.223 for "Raphael" and "Raphael-X" processors.

Unlike several past generations of Ryzen branded desktop APUs that only had 2-3 processor models in the retail channel, AMD is reportedly planning a slightly bigger lineup of APUs for the Socket AM5 platform, consisting of Ryzen 3, Ryzen 5, and possibly Ryzen 7 processor models, and their Ryzen PRO variants. The Ryzen 3 and Ryzen 5 models are expected to be based on the "Phoenix 2" silicon that has a combination of two "Zen 4" and four "Zen 4c" CPU cores and an iGPU with 4 compute units; while it is rumored that at least one Ryzen 5 and Ryzen 7 processor model will be built on "Phoenix," which has up to eight "Zen 4" cores, and a large iGPU with up to 12 compute units. So far we haven't seen reports of AMD bringing Ryzen AI to the desktop platform.

AMD today launched its first client processors that feature the compact "Zen 4c" CPU cores, with the Ryzen 5 7545U and Ryzen 3 7440U mobile processors for thin-and-light notebooks. The "Zen 4c" CPU core is a compacted version of the "Zen 4" core without the subtraction of any hardware components, but rather a high density arrangement of them on the 4 nm silicon. A "Zen 4c" core is around 35% smaller in area on the die than a regular "Zen 4" core. Since none of its components is removed, the core features an identical IPC (single thread performance) to "Zen 4," as well as an identical ISA (instruction set). "Zen 4c" also supports SMT or 2 threads per core. The trade-off here is that "Zen 4c" cores are generally clocked lower than "Zen 4" cores, as they can operate at lower core voltages. This doesn't, however, make the "Zen 4c" comparable to an E-core by Intel's definition, these cores are still part of the same CPU clock speed band as the "Zen 4" cores, at least in the processors that's being launched today.

The Ryzen 5 7545U and Ryzen 3 7440U mobile processors formally debut the new 4 nm "Phoenix 2" monolithic silicon. This chip is AMD's first hybrid processor, in that it has a mixture of two regular "Zen 4" cores, and four compact "Zen 4c" cores. The six cores share an impressive 16 MB of L3 cache. All six cores feature 1 MB of dedicated L2 cache. There is no complex hardware-based scheduler involved, but a software based solution that's deployed by AMD's Chipset Software, which tells the Windows scheduler to see the "Zen 4" cores as UEFI CPPC "preferred cores," and prioritize traffic to them, as they can hold on to higher boost frequency bins. The "Phoenix 2" silicon inherits much of the on-die power-management feature-set from the "Phoenix" and "Rembrandt" chips, and so are capable of a high degree of power savings with underutilized CPU cores and iGPU compute units.