AMD Ryzen Z2 Extreme GPU vs Intel Arc Pro B370 Comparison

The Verdict

The data available in the database presents a unique comparison scenario. The AMD Ryzen Z2 Extreme GPU has recorded benchmark results, specifically a 3DMark Steel Nomad DX12 score of 516. This score places it at the 1st percentile of all GPUs, indicating it is at the very bottom of the performance spectrum. The Intel Arc Pro B370, by contrast, has no recorded benchmark scores in the database, leaving its average benchmark score at 0 and its percentile at 50. This absence of data for the Intel part is the defining feature of this comparison.

For the AMD Ryzen Z2 Extreme, the recorded data shows it performs within a narrow band of older, low-end hardware. It is 3.4% behind the Intel HD Graphics P4000 and 3.7% behind the AMD Radeon HD 6870. It does hold a 6.6% lead over the AMD Radeon HD 6750M, but it trails the AMD Radeon HD 6770M by 9.3%. The data indicates that the Ryzen Z2 Extreme is positioned for basic graphical tasks, not for demanding gaming or professional workloads.

The Intel Arc Pro B370, on the other hand, is an active product with a 50th percentile ranking, but the database has no benchmark measurements to support this ranking. The analysis must therefore rely on its architectural and specification differences. The verdict is that the Intel Arc Pro B370 is likely the more capable part for tasks requiring high compute throughput, given its higher FP32 and FP16 performance figures. The AMD Ryzen Z2 Extreme, with its single recorded score, appears to be a low-power solution for embedded or console-like applications where the 28 W TDP and integrated design are primary considerations. The data suggests a clear split: the AMD part is for a specific, low-power segment, while the Intel part is a more general-purpose, albeit unmeasured, option.

FAQ

Q: Which GPU has a higher recorded benchmark score?

A: The AMD Ryzen Z2 Extreme GPU has a recorded 3DMark Steel Nomad DX12 score of 516. The Intel Arc Pro B370 does not have any recorded benchmark scores in the database.

Q: How does the AMD Ryzen Z2 Extreme compare to its nearest rivals?

A: The data shows it is 3.4% slower than the Intel HD Graphics P4000 and 3.7% slower than the AMD Radeon HD 6870. It is 6.6% faster than the AMD Radeon HD 6750M but 9.3% slower than the AMD Radeon HD 6770M.

Q: What are the TDP differences between the two GPUs?

A: The AMD Ryzen Z2 Extreme has a TDP of 28 W, while the Intel Arc Pro B370 has a TDP of 25 W.

Q: What is the difference in memory configuration?

A: The AMD Ryzen Z2 Extreme uses 16 GB of LPDDR5X memory with a 128-bit bus, providing 128.0 GB/s of bandwidth. The Intel Arc Pro B370 uses "System Shared" memory, with its bandwidth described as "System Dependent."

Q: Which GPU has a higher FP32 performance in TFLOPS?

A: The Intel Arc Pro B370 has a higher FP32 performance at 6.144 TFLOPS, compared to the AMD Ryzen Z2 Extreme's 5.530 TFLOPS.

Q: Are there any differences in the production process?

A: Yes, the AMD Ryzen Z2 Extreme is manufactured by TSMC on a 4 nm process. The Intel Arc Pro B370 is manufactured by Intel on a 3 nm process.

Architecture Differences

The architectural divide between these two GPUs is substantial. The AMD Ryzen Z2 Extreme is built on the RDNA 3.5 architecture, part of the "Strix Point" chip, and is classified as a Console GPU. It uses a 4 nm process from TSMC and contains 34,000 million transistors on a 233 mm² die, resulting in a transistor density of 145.9M per mm². Its shading units are 1024, with 64 texture mapping units and 48 raster operations units. It also has 16 ray tracing cores. The architecture is designed to deliver 5.530 TFLOPS of FP32 performance and the same 5.530 TFLOPS for FP16, indicating a 1:1 ratio. This suggests a focus on general compute where FP16 is not prioritized for acceleration.

The Intel Arc Pro B370 uses the Xe3-LPG architecture, based on the "Panther Lake" chip, and is classified as an Arc Graphics-WM part. It is built on a 3 nm process by Intel, though its transistor count and die size are listed as unknown. It has a different core configuration with 1280 shading units, 40 TMUs, and only 20 ROPs. Its ray tracing core count is 10. This architecture produces 6.144 TFLOPS of FP32 performance but a much higher 12.29 TFLOPS of FP16 performance, reflecting a 2:1 ratio. The Intel architecture clearly emphasizes FP16 throughput, which is a common trait for AI and compute-intensive tasks. The difference in ROP count is significant: AMD has 48, while Intel has 20. The data indicates the AMD part is designed for pixel throughput, given its 129.6 GPixel/s rate, while the Intel part is more compute-oriented, with a lower 48.00 GPixel/s rate.

Specification Differences

The specification sheets for these two products diverge in nearly every measurable field. The process node is a clear difference: AMD uses a 4 nm TSMC process, while Intel uses a 3 nm Intel process. The clock speeds differ, with the AMD part having a base clock of 800 MHz and a boost of 2700 MHz. The Intel part has a much lower base clock of 300 MHz but a boost of 2400 MHz. Memory is a major point of separation. The AMD Ryzen Z2 Extreme has a dedicated 16 GB LPDDR5X memory pool with a 128-bit bus and a fixed bandwidth of 128.0 GB/s. The Intel Arc Pro B370 relies on "System Shared" memory, meaning its performance is dependent on the host system's memory configuration.

The core counts also differ: AMD has 1024 shading units, 64 TMUs, and 48 ROPs, while Intel has 1280 shading units, 40 TMUs, and 20 ROPs. The compute rates reflect these configurations. AMD's pixel rate is 129.6 GPixel/s and its texture rate is 172.8 GTexel/s. Intel's pixel rate is 48.00 GPixel/s and its texture rate is 96.00 GTexel/s. Power consumption is close but not identical: the AMD part is rated at 28 W, and the Intel part is rated at 25 W. The Intel part is classified as an IGP with a bus interface of "IGP," while the AMD part has no listed bus interface. Display outputs also differ: the AMD part has a single USB Type-C output, while the Intel part's outputs are "Portable Device Dependent." Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between the AMD Ryzen Z2 Extreme and the Intel Arc Pro B370. The only recorded benchmark is for the AMD part: a 3DMark Steel Nomad DX12 score of 516. This score is the sole quantitative data point for performance comparison. The Intel Arc Pro B370 has no benchmark scores, so a direct comparison of measured performance is impossible.

Given this lack of head-to-head data, the analysis must interpret the available numbers. The AMD Ryzen Z2 Extreme's score of 516 places it in the 1st percentile of all GPUs. Its nearest rivals are all legacy parts. It is 3.4% behind the Intel HD Graphics P4000's average score of 534 and 3.7% behind the AMD Radeon HD 6870's 536. It is 6.6% ahead of the AMD Radeon HD 6750M's score of 484 but 9.3% behind the AMD Radeon HD 6770M's score of 569. This data suggests the AMD part's performance is anchored to this low-performance tier.

The Intel Arc Pro B370 has an average benchmark score of 0, but its percentile ranking is 50. This indicates that the database expects it to perform at the median level of all GPUs, but no measurement is present to confirm this. The specification data suggests a higher compute capability: 6.144 TFLOPS FP32 is 11.1% higher than the AMD part's 5.530 TFLOPS. The FP16 difference is even more pronounced, with the Intel part at 12.29 TFLOPS, which is 122.2% higher than the AMD part's 5.530 TFLOPS. The data implies that in raw compute tasks, the Intel part would be significantly faster, but this is not verified by a benchmark score.

Where Each One Wins

The AMD Ryzen Z2 Extreme wins in scenarios that its measured data supports. Its 3DMark Steel Nomad DX12 score of 516, while low, is a real, recorded result. This indicates it can run DirectX 12 workloads, albeit at a basic level. Its higher pixel rate of 129.6 GPixel/s, compared to Intel's 48.00 GPixel/s, suggests it is more efficient at rasterizing simple scenes, making it suitable for lightweight 2D interfaces or basic video output. Its 16 GB of dedicated LPDDR5X memory with a fixed 128.0 GB/s bandwidth provides a predictable memory environment, which is beneficial for embedded systems where consistency is key. Its 28 W TDP is slightly higher than Intel's 25 W, but it is still a low-power part. The single USB Type-C display output is a specific, simple interface for portable devices.

The Intel Arc Pro B370 wins in theoretical compute and feature set. Its FP32 performance of 6.144 TFLOPS is higher, and its FP16 performance of 12.29 TFLOPS is dramatically higher, indicating a clear advantage in AI inference or compute shaders that use FP16. Its 1280 shading units, while paired with fewer ROPs, provide a larger pool of compute elements. The 3 nm process node from Intel indicates a more modern manufacturing technology. The "System Shared" memory model means it can access a potentially large pool of system memory, though this is system-dependent. Its classification as an IGP and its 50th percentile ranking suggest it is intended for a broader range of integrated graphics tasks in portable devices. The data shows the AMD part is a specialized, low-power GPU with a confirmed, if minimal, performance level, while the Intel part is a more powerful compute-oriented IGP whose performance is yet to be measured in the database.