SYSTEM ANALYZER

Rate My PC: AMD Ryzen AI Embedded P164 + AMD Radeon 860M

Get a comprehensive performance analysis of your gaming rig with detailed benchmarks, bottleneck detection, and upgrade recommendations

94 / 100
ULTIMATE READY

Apex Performer

Top 6% of systems. Capable of 4K Ultra gaming and advanced rendering.

4K 60+ FPSVR ReadyRay Tracing

System Balance Analysis

CPU vs GPU performance ratio
Well Balanced
CPU
95%
VS
GPU
93%
PROCESSOR

AMD Ryzen AI Embedded P164

52,901 Benchmark Score
Top 5% Market Ranking
View Full Specs →
GRAPHICS CARD

AMD Radeon 860M

26,401 Benchmark Score
Top 7% Market Ranking
View Full Specs →

Market Position

How your build compares to others
Budget
0-30
Mid-Range
30-60
High-End
60-85
Enthusiast
85-100
Your Build

Game Performance Benchmarks

Real-world 4K FPS in popular titles
View All Games →

Performance Insights

Tips to maximize your system

Optimal Performance

Your system is in the top tier. You can run any modern game at maximum settings.

4K Gaming Ready

Consider a 4K 144Hz monitor to fully utilize your hardware capabilities.

Compatible Games See what you can play Compare CPUs Find upgrades Compare GPUs Find upgrades

Performance Tiers Explained

90-100

Ultimate

4K Ultra gaming, VR ready, ray tracing enabled, professional workloads

4K 60+ FPS VR Ready
70-89

High-End

1440p Ultra or 4K High settings, excellent for modern AAA titles

1440p Ultra 4K High
50-69

Mid-Range

1080p Ultra or 1440p Medium, great value for most gamers

1080p Ultra 1440p Med
30-49

Entry Level

1080p Medium settings, suitable for eSports and older titles

1080p Med eSports
0-29

Legacy

Basic gaming, older titles, consider upgrading for modern games

720p-1080p Low Older Games

The AMD Ryzen AI Embedded P164 and AMD Radeon 860M form a laptop-class pairing (build class: laptop) that sits at the 82nd combined percentile among all CPU+GPU combinations in the database. This is a single-package design meant for thin-and-light systems, built around AMD’s Gorgon Point platform with a 4 nm TSMC process for both the CPU and GPU. There are no measured FPS rows in the data for this exact combination, so all gaming frame-rate discussion below is estimated from the benchmark scores rather than taken from direct testing.

CPU Analysis

The CPU portion of this pairing is an 8-core, 16-thread processor based on the Ryzen AI Embedded generation, which combines Zen 5 and Zen 5c cores. The base clock is 2.00 GHz and the boost clock reaches 5.00 GHz. It draws a 28 W TDP, which places it firmly in the efficient mobile segment. The cache layout is 80 KB L1 per core, 1 MB L2 per core, and 8 MB of shared L3. The memory controller supports DDR5 and LPDDR5X in a dual-channel configuration, with a memory bandwidth of 89.6 GB/s and ECC support enabled.

The PassMark multi-thread score is 25889, and the single-thread score is 4029. These numbers put the CPU at the 91st percentile among all CPUs in the database. The average benchmark score across all CPU tests is 52901. Comparing to nearest rivals, this chip is essentially tied with the AMD Ryzen 5 9500F (avg score 52873, deltaPct 0.1) and the Intel Xeon 634 (avg score 52974, deltaPct -0.1). It sits slightly behind the AMD EPYC 7313P (avg score 53206, deltaPct -0.6) and the AMD Ryzen 9 7900X (avg score 53288, deltaPct -0.7). The differences are within 0.7%, meaning the P164 offers competitive multi-threaded throughput despite its 28 W envelope, likely because the boost clock of 5.00 GHz compensates for the lower TDP in bursty workloads.

Looking at individual workload scores: integer math scores 87940, floating-point math scores 55799, extended instructions (SIMD) score 24193, and data compression scores 327891. The data encryption score is 16055, random string sorting is 34801, and find prime numbers is 71. The physics score is 1210. The single-thread score of 4029 indicates strong per-core performance, which is critical for lightly threaded applications like web browsing, office documents, and many legacy games. The multi-thread score of 25889 shows that the 16 threads are well utilized in parallel workloads such as video encoding or compilation.

For real workloads, the data suggests this CPU can handle a wide range of tasks. The high data compression score (327891) points to strong performance in file archiving and database operations. The integer math score (87940) is relevant for spreadsheet calculations, scripting, and general productivity. The floating-point score (55799) supports scientific computing and 3D rendering tasks. The extended instruction score (24193) indicates good SIMD throughput for media processing. The encryption score (16055) is moderate, suggesting hardware acceleration is present but not top-tier. Overall, the CPU is a well-rounded mobile processor that performs near desktop-class parts from the previous generation, as evidenced by its near-tie with the Ryzen 9 7900X in average score.

GPU Analysis

The GPU side is the AMD Radeon 860M, an integrated graphics processor based on RDNA 3.5 architecture, from the Navi III IGP generation (Strix Point Mobile). It is built on the same 4 nm TSMC process as the CPU. The chip is named Krackan Point. The GPU has 512 shading units, 32 texture mapping units (TMUs), and 16 render output units (ROPs). It includes 8 ray tracing cores but no dedicated tensor cores. The base clock is 600 MHz, and the boost clock is 3000 MHz. Memory is system-shared, meaning the GPU uses the same DDR5 or LPDDR5X memory as the CPU, with bandwidth that is system dependent. The pixel rate is 48.00 GPixel/s, and the texture rate is 96.00 GTexel/s. FP32 performance is 3.072 TFLOPS, with FP16 also at 3.072 TFLOPS (1:1 ratio). The GPU TDP is 15 W, and it connects via PCIe 4.0 x8. The bus interface is PCIe 4.0 x8, and display outputs are portable device dependent.

The Geekbench OpenCL score is 22759, and the Geekbench Vulkan score is 30043. The average benchmark score is 26401, placing the GPU at the 72nd percentile among all GPUs. The nearest rivals are the NVIDIA GeForce MX550 (avg score 26421, deltaPct -0.1), NVIDIA GeForce RTX 5060 (avg score 26331, deltaPct 0.3), AMD Radeon RX 5700 XT 50th Anniversary (avg score 26553, deltaPct -0.6), and NVIDIA RTX A4000 (avg score 26683, deltaPct -1.1). The Radeon 860M is within 1.1% of all these parts, which is remarkable for an integrated GPU. The RTX 5060 is a discrete laptop GPU, and the fact that the 860M trades blows with it in synthetic benchmarks indicates the integrated part is very efficient for its power envelope.

The Vulkan score of 30043 is notably higher than the OpenCL score of 22759, suggesting the GPU drivers and architecture are particularly well-optimized for Vulkan-based workloads. This is beneficial for modern games that use Vulkan, as well as for compute tasks that leverage Vulkan compute. The 8 RT cores provide ray tracing capability, though the low FP32 throughput (3.072 TFLOPS) means ray tracing will be limited to lighter effects. The 512 shading units at 3000 MHz boost clock deliver decent rasterization performance for 1080p gaming at medium settings, but the 15 W TDP and shared memory bandwidth will constrain performance in memory-heavy scenes.

For rendering workloads, the FP32 number of 3.072 TFLOPS is the key metric. This is sufficient for basic 3D modeling and rendering previews, but not for final-frame production rendering. The texture rate of 96.00 GTexel/s and pixel rate of 48.00 GPixel/s indicate the GPU can fill frames at 1080p with moderate texture detail. The lack of tensor cores means no dedicated AI acceleration for features like DLSS, though FSR (which is not mentioned in the data) could be used as a software alternative. The 8 RT cores enable some ray-traced effects, but the performance will be modest.

Usage Scenarios

High-refresh gaming: At 1080p with low to medium settings, the Radeon 860M’s benchmark scores (Geekbench Vulkan 30043, OpenCL 22759) suggest it can drive frame rates in the range of 60-90 FPS for esports titles, but this is an estimate since no measured FPS data exists for this pairing. The CPU’s single-thread score of 4029 and multi-thread score of 25889 ensure that the processor will not bottleneck the GPU in most games, but the shared memory bandwidth of 89.6 GB/s may limit higher refresh rates.

Streaming: The CPU’s 16 threads handle encoding and gameplay simultaneously. The data encryption score of 16055 and extended instructions score of 24193 indicate the processor can manage software encoding at reasonable bitrates, though dedicated hardware encoders (not specified in the data) might be absent. The 8-core/16-thread design allows for game capture and encoding on separate threads, and the 28 W TDP keeps thermals manageable during extended streaming sessions.

Video editing: The multi-thread score of 25889 and floating-point score of 55799 support timeline scrubbing, effect rendering, and export tasks. The data compression score of 327891 is particularly relevant for video codecs that use compression. The GPU’s 3.072 TFLOPS FP32 performance accelerates effects that use GPU acceleration, though 4K editing will be constrained by the shared memory bandwidth.

3D rendering: CPU-based rendering benefits from the 16 threads and the floating-point score of 55799, which is competitive with desktop parts like the Ryzen 9 7900X (deltaPct -0.7). GPU-based rendering using OpenCL (score 22759) will be slower but usable for previews. The 8 RT cores provide some ray-traced acceleration, but the 3.072 TFLOPS limit means final renders will be slow for complex scenes.

Software development: The integer math score of 87940 and single-thread score of 4029 indicate fast compilation for single-threaded build steps, while the multi-thread score of 25889 helps with parallel builds. The random string sorting score of 34801 suggests good performance for text processing and code analysis tools. The 16 threads allow for running virtual machines or containers alongside an IDE.

Student and office work: The single-thread score of 4029 ensures snappy responses in word processors, spreadsheets, and web browsers. The CPU’s 28 W TDP and the GPU’s 15 W TDP mean long battery life in laptop form (though exact battery figures are not in the data). The ECC memory support is a bonus for data integrity in spreadsheet models or database work.

Balance and Bottleneck

The CPU and GPU are well balanced for a laptop-class system. The CPU sits at the 91st percentile, while the GPU is at the 72nd percentile. This disparity means the CPU is significantly stronger relative to its peers than the GPU is. In CPU-bound workloads like data compression (327891), encryption (16055), and integer math (87940), the processor will be the primary driver. In GPU-bound workloads like 3D rendering or gaming, the Radeon 860M will be the limiting factor, as its FP32 throughput of 3.072 TFLOPS is modest.

The combined percentile of 82 reflects this balance: the system is more capable than the GPU alone suggests, but not as strong as the CPU alone would imply. The nearest GPU rivals include the discrete NVIDIA MX550 and RTX 5060, with the 860M essentially tied with them (deltas of -0.1% and 0.3%, respectively). This indicates that the integrated GPU is not a weak point relative to entry-level discrete parts, but it is nowhere near the performance of higher-end discrete GPUs.

The memory bandwidth of 89.6 GB/s is shared between CPU and GPU, which can create a bottleneck in graphics-heavy tasks. When the GPU needs to access textures or geometry data, it competes with CPU memory operations. The dual-channel memory bus helps, but the bandwidth is fixed. In gaming, this means that scenes with large textures or complex geometry may see frame pacing issues as the GPU waits for data. In CPU-heavy parallel workloads, the same bandwidth is sufficient, as evidenced by the multi-thread score of 25889.

The FPS scaling, while not measured, can be inferred from the GPU’s benchmark scores. The Vulkan score of 30043 is higher than the OpenCL score of 22759, suggesting that Vulkan-based games will perform better than OpenGL or DirectX 11 titles. The 8 RT cores provide ray tracing capability, but the 3.072 TFLOPS FP32 rate means that enabling ray tracing will significantly reduce frame rates, potentially halving them in demanding scenes.

Upgrade Path and Platform

The CPU uses AMD Socket FP8, which is a mobile (laptop) socket. This means the CPU is soldered and not upgradeable in most systems. The memory support is DDR5 and LPDDR5X, with dual-channel configuration and ECC capability. The PCIe interface is Gen 4 with 16 lanes (CPU only), while the GPU uses PCIe 4.0 x8. These are modern standards that allow for fast NVMe SSDs and external GPU enclosures, though the laptop form factor limits physical expansion.

The CPU TDP is 28 W, and the GPU TDP is 15 W, totaling 43 W for the combined package. The suggested PSU is null in the data, but the low TDP means a standard laptop power adapter is sufficient. There are no power connectors for the GPU (it is an IGP), and the slot width is IGP, meaning no discrete GPU installation is possible beyond what the laptop manufacturer provides.

A sensible next upgrade would be to increase system memory, since the GPU uses system-shared memory. Upgrading from slower DDR5 to faster LPDDR5X could improve GPU performance, as the bandwidth is system dependent. Adding more memory (e.g., 32 GB or 64 GB) would also allow the GPU to allocate more VRAM for textures, though the data does not specify maximum memory capacity. The PCIe Gen 4 x8 interface for the GPU is sufficient for the integrated graphics, and an eGPU enclosure would be the only way to add a discrete GPU, but the laptop chassis must support Thunderbolt or USB4 (not specified in the data).

The production status is Active for both CPU and GPU, indicating ongoing availability. The release dates are 2026-03-08 for the CPU and 2025-02-28 for the GPU, so this is a current-generation pairing. The socket FP8 is used across the Ryzen AI Embedded lineup, so future CPU upgrades are theoretically possible if the motherboard/BIOS supports them, but laptop designs typically lock the CPU.

Who Should Build It

This pairing targets users who need a compact, power-efficient laptop that can handle both productivity and light gaming. The 91st CPU percentile and 72nd GPU percentile suggest a system for students and office workers who occasionally game or do light creative work. The CPU’s 16 threads and high single-thread score (4029) make it ideal for developers who compile code and run virtual machines, while the GPU’s performance (Vulkan 30043) supports casual gaming at 1080p.

Content creators who work with 1080p video editing or 2D graphics will find the CPU’s multi-thread score (25889) and the GPU’s OpenCL score (22759) adequate for short projects. 3D artists doing basic modeling will appreciate the CPU’s floating-point performance (55799), but should not expect to render complex scenes quickly given the GPU’s 3.072 TFLOPS limit. Gamers at 1080p with medium settings are the target audience for the GPU, and the CPU will not bottleneck them in most titles.

Small business workstations benefit from the ECC memory support and the CPU’s data compression score (327891), which aids in database operations. The 28 W CPU TDP and 15 W GPU TDP mean the system runs cool and quiet, suitable for open-office environments. The 4 nm process node from TSMC ensures good energy efficiency, though the exact battery life is not specified in the data.

FAQ

Q: What is the combined performance tier of this CPU+GPU pairing?

A: The combined percentile is 82, meaning it outperforms 82% of all CPU+GPU combinations in the database. The CPU alone is at the 91st percentile, while the GPU is at the 72nd percentile.

Q: How does the CPU compare to the AMD Ryzen 9 7900X?

A: The Ryzen AI Embedded P164 has an average benchmark score of 52901, which is 0.7% lower than the Ryzen 9 7900X’s score of 53288. The difference is negligible, indicating the mobile chip matches a desktop part from the same generation.

Q: What is the GPU’s ray tracing capability?

A: The Radeon 860M has 8 ray tracing cores and supports DirectX 12 Ultimate (12_2). The FP32 performance is 3.072 TFLOPS, so ray tracing is available but will be limited to lighter effects in games.

Q: Does the GPU have dedicated VRAM?

A: No, the memory size, type, and bus width are all listed as “System Shared.” The GPU uses the same DDR5 or LPDDR5X memory as the CPU, with bandwidth that is system dependent.

Q: What is the difference between OpenCL and Vulkan performance?

A: The Geekbench Vulkan score is 30043, while the OpenCL score is 22759. The Vulkan score is about 32% higher, indicating better optimization for Vulkan-based games and compute workloads.

Q: Is the CPU overclockable?

A: No, the multiplier is locked (multiplierUnlocked: false). The base clock is 2.00 GHz and boost clock is 5.00 GHz, but these are fixed by the manufacturer.

Q: What memory types are supported?

A: The CPU supports DDR5 and LPDDR5X in a dual-channel configuration, with a memory bandwidth of 89.6 GB/s. ECC memory is also supported.

Build Overview

This is a laptop-class build (build class: laptop) combining the AMD Ryzen AI Embedded P164 CPU with the AMD Radeon 860M integrated GPU. The CPU is an 8-core/16-thread part from the Gorgon Point platform, based on Zen 5 / Zen 5c architecture on a 4 nm TSMC process. The GPU is an RDNA 3.5 integrated graphics solution with 512 shading units and 8 ray tracing cores. The combined system sits at the 82nd percentile, with the CPU at the 91st percentile and the GPU at the 72nd percentile. This is a mid-to-high-tier mobile platform for productivity and light gaming, not for high-end 3D rendering or 4K gaming.

Benchmark Performance

The CPU’s average benchmark score is 52901, which places it at the 91st percentile among all CPUs. The multi-thread score is 25889, and the single-thread score is 4029. The GPU’s average benchmark score is 26401, at the 72nd percentile among all GPUs. The Geekbench OpenCL score is 22759, and the Vulkan score is 30043. The combined percentile is 82.

The nearest CPU rivals include the Ryzen 5 9500F (avg 52873, delta 0.1%), Intel Xeon 634 (avg 52974, delta -0.1%), EPYC 7313P (avg 53206, delta -0.6%), and Ryzen 9 7900X (avg 53288, delta -0.7%). The CPU is essentially tied with all four, with deltas under 1%. The nearest GPU rivals are the NVIDIA MX550 (avg 26421, delta -0.1%), RTX 5060 (avg 26331, delta 0.3%), RX 5700 XT 50th Anniversary (avg 26553, delta -0.6%), and RTX A4000 (avg 26683, delta -1.1%). The GPU also trades blows with these discrete parts, which is impressive for an integrated solution.

The combined picture is a system where the CPU is significantly stronger than the GPU relative to their respective peers. The CPU’s 91st percentile versus the GPU’s 72nd percentile means the processor will rarely be the bottleneck; instead, the GPU will limit graphics-heavy workloads. The 82nd combined percentile reflects this, showing a system that is well above average for overall performance but not top-tier.

Gaming Performance

There are no measured FPS rows for this exact combination in the data (measuredFpsUltraByGame is empty, and dataIsMeasured is false). Therefore, all gaming frame-rate expectations are estimates derived from the benchmark scores, not direct measurements.

Based on the GPU’s Vulkan score of 30043 and OpenCL score of 22759, the Radeon 860M should handle 1080p gaming at low to medium settings in most modern titles. Esports games like Counter-Strike 2 or Valorant (not named in the data, but implied by the performance class) would likely run at high frame rates given the single-thread score of 4029 on the CPU. The 8 RT cores enable ray tracing, but the 3.072 TFLOPS FP32 throughput means enabling ray tracing will likely reduce frame rates by a significant margin, possibly to below 30 FPS in demanding titles.

For the CPU, the multi-thread score of 25889 ensures that games using more than 4 cores will not be CPU-limited. The data compression score of 327891 and integer math score of 87940 indicate fast level loading and physics calculations. However, the shared memory bandwidth of 89.6 GB/s is the likely bottleneck in gaming, as the GPU and CPU compete for the same memory bus. In scenes with high texture detail or many on-screen objects, the frame rate may dip due to memory latency rather than raw compute limits.

The nearest GPU rival, the NVIDIA GeForce RTX 5060 (avg score 26331, delta 0.3%), is a discrete laptop GPU. The fact that the 860M is within 0.3% of it suggests that this integrated GPU can match entry-level discrete parts in synthetic benchmarks, but in real gaming, the discrete GPU’s dedicated VRAM and higher power budget may give it an edge. Users should expect playable 1080p gaming on medium settings, with lower settings required for ray-traced titles.