SYSTEM ANALYZER

Rate My PC: AMD Ryzen AI Embedded P164 + Intel Arc B390

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

86 / 100
HIGH-END

Power Build

Top 14% of systems. Excellent for 1440p Ultra or 4K High gaming.

1440p Ultra4K High

System Balance Analysis

CPU vs GPU performance ratio
Well Balanced
CPU
95%
VS
GPU
77%
PROCESSOR

AMD Ryzen AI Embedded P164

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

Intel Arc B390

1,482 Benchmark Score
Top 23% 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

Strong Performance

Excellent for 1440p gaming. Most games will run at high/ultra settings smoothly.

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

This is a laptop-class pairing built around AMD’s Ryzen AI Embedded P164 processor and Intel’s Arc B390 integrated graphics. The CPU is a strong performer, sitting at the 91st percentile among all CPUs, while the GPU is a low-tier integrated solution at the 9th percentile. Because the FACT PACK contains no measured FPS rows for this exact combination, all gaming frame rates discussed here are estimates derived from the benchmark scores and percentile positions, not direct measurements.

Gaming Performance — measured FPS by game and resolution from measuredFpsUltraByGame (or, if dataIsMeasured is false, frame expectations qualitatively from the benchmark scores and say the figures are estimates)

The FACT PACK includes no measured FPS data for this CPU+GPU pairing — the `measuredFpsUltraByGame` field is empty, and the `dataIsMeasured` flag is false. Therefore, every gaming figure in this section is an estimate based on the benchmark scores, not a measured result. The Intel Arc B390’s only benchmark score is 1482 in 3DMark Steel Nomad DX12, which places it at the 9th percentile among all GPUs. That percentile suggests a very low-end graphics solution, one that sits near the bottom of the performance stack.

For context, the Arc B390’s nearest rivals in the benchmark database are the NVIDIA GeForce GT 520MX (1463 score, 1.3% slower), the NVIDIA GeForce 800M (1460, 1.5% slower), the NVIDIA GeForce GT 625 OEM (1446, 2.5% slower), and the NVIDIA GeForce GT 710 (1443, 2.7% slower). These are all legacy or entry-level mobile GPUs, which tells you the Arc B390 is not designed for modern gaming at high settings. At 1080p with ultra settings, the estimated frame rates for demanding titles would be in the single digits to low teens, if the game runs at all. Esports titles like older or lighter games might reach playable frame rates, but only at lower resolutions and reduced graphical settings.

The CPU side does not rescue the gaming experience. While the Ryzen AI Embedded P164 scores well in CPU benchmarks — the passmark_multithread score is 25889 and the passmark_single_thread score is 4029 — the GPU is the bottleneck for gaming. A CPU with a 91st percentile ranking cannot compensate for a GPU at the 9th percentile in frame rate generation. The estimated FPS scaling with resolution is also poor: at 1440p or 4K, the integrated GPU would likely struggle to maintain even 30 FPS in most modern games, regardless of CPU headroom. The data implies this is a productivity-first machine, not a gaming rig.

Usage Scenarios

High-refresh gaming: Not viable. The Arc B390’s 9th percentile GPU ranking and 1482 Steel Nomad score indicate that even a 60 Hz display would be a challenge in most titles. High-refresh (120 Hz or above) gaming is out of reach for this pairing, as the GPU lacks the raw throughput to push frame rates beyond what the CPU can feed it — and the CPU is not the limiting factor here.

Streaming: The CPU’s 8 cores and 16 threads, with a multithread score of 25889, could handle software encoding for a stream at modest settings. However, the GPU’s low performance means the game itself would run poorly, making streaming a poor experience. The passmark_data_encryption score of 16055 suggests encryption workloads are handled reasonably, but that does not translate to smooth gameplay while broadcasting.

Video editing: The CPU is the strong point. With a floating point math score of 55799 and an integer math score of 87940, the Ryzen AI Embedded P164 can handle video encoding and decoding tasks competently. The integrated Radeon 880M graphics (from the CPU’s iGPU) might assist with some acceleration, but the Arc B390’s low tier means GPU-accelerated effects or rendering would be slow. The 89.6 GB/s memory bandwidth helps with large video files, but the system shared GPU memory means the CPU and GPU compete for the same bandwidth.

3D rendering: The Arc B390’s 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 performance are modest numbers for compute, but the 9th percentile ranking suggests real-world rendering workloads would be slow. The CPU’s 8 cores and 16 threads would help with CPU-based rendering, but most modern renderers leverage the GPU heavily. The 12 RT cores and 48 TMUs are present, but at this performance tier, they are not enough for professional 3D work.

Software development: This is a strong scenario for the CPU. The passmark_extended_instructions score of 24193 and the random string sorting score of 34801 indicate good handling of code compilation and data processing tasks. The 16 threads provide parallel compilation capability, and the 91st CPU percentile means the processor is faster than most alternatives. The GPU’s weakness is irrelevant for most development tasks, unless the work involves GPU compute or gaming development.

Student and office work: Excellent fit. The CPU’s single-thread score of 4029 ensures snappy response in office applications, spreadsheets, and web browsing. The low TDP of 28 W for the CPU and 80 W for the GPU means the laptop-class build should run cool and quiet, which is desirable for a study or office environment. The GPU is sufficient for basic display output and 2D acceleration, though any 3D work would be slow.

CPU Analysis

The AMD Ryzen AI Embedded P164 is an 8-core, 16-thread processor from the Gorgon Point codename, belonging to the Ryzen AI Embedded generation that uses Zen 5 / Zen 5c cores. It is manufactured on a 4 nm process at TSMC, with a die size of 233 mm². The base clock is 2.00 GHz, and the boost clock reaches 5.00 GHz — a 2.5x multiplier between base and boost, which indicates strong single-thread burst capability when thermal headroom allows.

The cache hierarchy is notable: 80 KB of L1 per core, 1 MB of L2 per core, and 8 MB of L3 shared. That 8 MB L3 is modest compared to desktop Ryzen parts, but the CPU’s benchmark scores show it does not hold the processor back in most tasks. The passmark_multithread score of 25889 and passmark_single_thread score of 4029 both place the CPU at the 91st percentile among all CPUs. The nearest rivals reinforce this: the AMD Ryzen 5 9500F scores 52873 (0.1% slower), the Intel Xeon 634 scores 52974 (0.1% faster), the AMD EPYC 7313P scores 53206 (0.6% faster), and the AMD Ryzen 9 7900X scores 53288 (0.7% faster). These deltas are tiny, meaning the P164 is essentially on par with a desktop Ryzen 9 7900X in average benchmark score — a remarkable result for a 28 W mobile part.

The memory controller supports DDR5 and LPDDR5X in dual-channel mode, with a bandwidth of 89.6 GB/s. ECC memory support is present, which is unusual for a consumer-oriented part and suggests an embedded or workstation focus. The PCIe interface is Gen 4 with 16 lanes from the CPU, which is sufficient for one full-speed GPU or multiple NVMe drives. The integrated Radeon 880M graphics provide a fallback display output, though the system pairs it with the Intel Arc B390.

The floating point math score of 55799 and integer math score of 87940 indicate balanced compute performance. The passmark_find_prime_numbers score of 71 is low, which is typical for a workload that stresses cache and branch prediction — this CPU’s 8 MB L3 may be a limiting factor there. The passmark_physics score of 1210 is modest, suggesting the CPU is not optimized for physics simulation in gaming, which aligns with the GPU bottleneck.

Balance and Bottleneck

The balance in this pairing is heavily skewed toward the CPU. The Ryzen AI Embedded P164 sits at the 91st CPU percentile, while the Intel Arc B390 sits at the 9th GPU percentile. That is a 82-percentile gap, which is enormous. In any workload that involves both CPU and GPU — gaming, video encoding with GPU acceleration, or 3D rendering — the GPU will be the bottleneck by a wide margin.

The CPU’s passmark_multithread score of 25889 is more than 17 times the GPU’s 3DMark Steel Nomad score of 1482, which illustrates the performance disparity. For gaming, the FPS will be determined almost entirely by the GPU’s capability, not the CPU. The CPU can feed frames far faster than the GPU can render them, so any frame rate estimate is capped by the GPU’s 9th percentile performance.

The memory bandwidth of 89.6 GB/s is shared between the CPU and the GPU, since the Arc B390 uses system shared memory. This means GPU workloads compete with CPU workloads for the same memory bandwidth, further limiting the GPU’s effective performance. The CPU’s strong single-thread score of 4029 means it will not stall waiting for data, but the GPU’s low shading unit count (1536) and 24 ROPs will cap output.

In CPU-only workloads like software compilation or data compression, the balance is fine — the CPU is the star. But in any mixed workload, the GPU drags the system down. The combined percentile of 50 reflects this: the system is average overall because it pairs a top-tier CPU with a bottom-tier GPU, averaging out to the middle.

GPU Analysis

The Intel Arc B390 is an integrated graphics solution based on the Xe3-LPG architecture, part of the Arc Graphics-M generation for Panther Lake. It is manufactured on Intel’s 3 nm process. The GPU has 1536 shading units, 48 texture mapping units, and 24 raster output units — these are low counts for a modern GPU, which is why the performance is at the 9th percentile.

The clock speeds are 300 MHz base and 2500 MHz boost. The pixel rate is 60.00 GPixel/s, and the texture rate is 120.0 GTexel/s. The FP32 performance is 7.680 TFLOPS, and the FP16 performance is 15.36 TFLOPS (2:1 ratio). These numbers are not terrible on paper for an integrated GPU, but the 3DMark Steel Nomad DX12 score of 1482 puts it in the same league as NVIDIA’s GT 520MX and GT 710, which are over a decade old.

The memory is system shared, with no dedicated VRAM. The memory type, bus width, and bandwidth are all listed as “System Shared” or “System Dependent,” meaning the GPU borrows from the CPU’s DDR5 or LPDDR5X pool. The 89.6 GB/s memory bandwidth is the ceiling, but it is shared with the CPU, so actual GPU bandwidth will be lower. The 12 RT cores support ray tracing, but at this performance level, ray tracing would be unusable in real games. The GPU supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so feature support is modern, but the hardware is too weak to exploit those features at playable frame rates.

The TDP is 80 W, which is high for an integrated GPU and suggests the system may draw significant power under load. The display outputs are listed as “Portable Device Dependent,” meaning the laptop manufacturer determines what ports are available. The bus interface is IGP, confirming it is integrated into the processor package.

Who Should Build It

This pairing is for users who need strong CPU performance in a laptop form factor but do not need GPU acceleration. The target user is a software developer, data analyst, or office worker who runs CPU-intensive applications like code compilation, spreadsheet modeling, or database queries. The CPU’s 91st percentile ranking ensures these tasks are handled quickly, and the 16 threads support parallel workloads.

Content creators who work primarily with CPU-based tools — such as audio encoding or server-side video processing — would also benefit, given the CPU’s floating point score of 55799 and encryption score of 16055. However, any creator relying on GPU acceleration for effects, rendering, or gaming will be disappointed. The GPU is not suitable for modern 3D games at any resolution above low settings, and even then, only older or less demanding titles would run acceptably.

Students and office workers are ideal users. The low CPU TDP of 28 W means long battery life potential, and the GPU is sufficient for web browsing, document editing, and video playback. Small business workstations that run custom software with heavy single-threaded or multithreaded CPU demands would perform well, provided the software does not require GPU acceleration. The ECC memory support adds reliability for data-critical workloads.

Gamers should avoid this build entirely. The 9th GPU percentile means even a 720p low-setting experience would be marginal. The system is not designed for gaming, and the data confirms that.

Upgrade Path and Platform

The CPU uses AMD Socket FP8, which is a mobile socket — upgrades would require a new motherboard or laptop, not a simple CPU swap. The memory support includes DDR5 and LPDDR5X in dual-channel mode with ECC capability, so a user could upgrade RAM capacity, but the bandwidth ceiling of 89.6 GB/s remains fixed. The PCIe interface is Gen 4 with 16 lanes from the CPU, which allows for fast NVMe storage or an external GPU enclosure, though the laptop form factor limits practical expansion.

The GPU is integrated, so there is no discrete GPU upgrade path within the same chassis. The suggested PSU field is null, and the GPU TDP is 80 W, so the power delivery is designed for that integrated solution. The CPU TDP is 28 W, and combined, the CPU and GPU draw 108 W under load, which is manageable for a laptop power brick. A sensible next upgrade would be to move to a system with a discrete GPU if gaming or GPU compute becomes a requirement, but this would mean replacing the entire platform, not upgrading components.

The socket being FP8 means the CPU is soldered or embedded, so the platform’s upgrade path is essentially zero. Users should consider the system as a fixed configuration. The only meaningful upgrade would be more system memory, which would benefit both the CPU and the shared GPU memory pool.

FAQ

Q: Does this system have any measured gaming frame rate data?

A: No. The FACT PACK contains no measured FPS rows for this CPU+GPU combination, and the dataIsMeasured flag is false. All gaming performance discussions are estimates based on benchmark scores.

Q: How does the CPU compare to its nearest rivals?

A: The Ryzen AI Embedded P164 has an average benchmark score of 52901, which is 0.1% faster than the AMD Ryzen 5 9500F (52873), 0.1% slower than the Intel Xeon 634 (52974), 0.6% slower than the AMD EPYC 7313P (53206), and 0.7% slower than the AMD Ryzen 9 7900X (53288).

Q: What is the GPU’s performance tier?

A: The Intel Arc B390 is at the 9th percentile among all GPUs, with a 3DMark Steel Nomad DX12 score of 1482. Its nearest rivals are the NVIDIA GeForce GT 520MX (1463, 1.3% slower) and the NVIDIA GeForce 800M (1460, 1.5% slower).

Q: Can this system handle video editing?

A: The CPU can handle CPU-based video encoding well, with a multithread score of 25889 and floating point score of 55799. However, GPU-accelerated effects would be slow due to the GPU’s 9th percentile ranking.

Q: What memory does the CPU support?

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

Q: Is the GPU suitable for ray tracing?

A: The GPU has 12 RT cores and supports DirectX 12 Ultimate, but its 9th percentile performance means ray tracing would be unusable in real games.

Q: What is the combined system percentile?

A: The combined percentile for this CPU+GPU pairing is 50, which puts it in the middle of all systems, reflecting the CPU’s high performance and the GPU’s low performance.

Benchmark Performance

The CPU’s average benchmark score is 52901, with a percentile rank of 91 among all CPUs. The individual PassMark scores break down as follows: data compression (327891), data encryption (16055), extended instructions (24193), find prime numbers (71), floating point math (55799), integer math (87940), multithread (25889), physics (1210), random string sorting (34801), and single-thread (4029). The single-thread score appears twice in the data, confirming it at 4029.

The GPU’s average benchmark score is 1482, based on a single 3DMark Steel Nomad DX12 test. The GPU’s percentile is 9, placing it in the bottom decile of all GPUs. Its nearest rivals are all NVIDIA legacy parts, with the GT 520MX at 1463 (1.3% slower), the GeForce 800M at 1460 (1.5% slower), the GT 625 OEM at 1446 (2.5% slower), and the GT 710 at 1443 (2.7% slower).

The combined picture is one of extreme asymmetry. The CPU outperforms 91% of all CPUs, while the GPU outperforms only 9% of all GPUs. The combined percentile of 50 is the mathematical midpoint, but it does not reflect the user experience: in CPU-heavy tasks, the system feels fast; in GPU-heavy tasks, it feels like a decade-old machine. The data suggests the CPU is the reason to buy this system, and the GPU is a necessary compromise for the laptop form factor.

Build Overview

This is a laptop-class build (buildClass: “laptop”) pairing the AMD Ryzen AI Embedded P164 with the Intel Arc B390 integrated graphics. The CPU is a mobile processor with an embedded focus, indicated by the Gorgon Point codename and the Ryzen AI Embedded generation. The GPU is an integrated part of the Panther Lake platform, using Intel’s Xe3-LPG architecture.

The overall tier from the percentiles is mixed: the CPU is in the top 9% of all CPUs, the GPU is in the bottom 9% of all GPUs, and the combined percentile is exactly 50. This places the system in the middle tier overall, but the experience varies wildly by workload. For productivity, it is a high-end system; for gaming or GPU compute, it is entry-level at best.

The CPU’s 8 cores and 16 threads, boost clock of 5.00 GHz, and 91st percentile ranking make it a serious processor for a laptop. The GPU’s 1536 shading units, 2500 MHz boost clock, and 9th percentile ranking make it a display adapter more than a gaming GPU. This is a system for users who prioritize CPU throughput and are willing to accept minimal graphics capability. The data is clear: buy this for the processor, not the graphics.