AMD Instinct MI355X vs Intel Arc A570M Comparison

Where Each One Wins

The AMD Instinct MI355X and Intel Arc A570M occupy completely different segments of the GPU landscape, and the data reflects that split clearly. The MI355X is an accelerator built for compute density, while the Arc A570M is a mobile graphics processor with a conventional feature set. The recorded data shows no shared benchmark results, so the comparison rests on architectural limits and the single available test score.

The Intel Arc A570M has one measured result: a Geekbench OpenCL score of 58,239. That score places it in the 88th percentile of all GPUs in the database, which indicates strong general compute performance for a mobile part. Its nearest rivals in the database are the AMD Radeon RX 6950 XT with an average score of 58,392 (the Arc trails by 0.3%), the AMD Radeon RX 5600 OEM at 58,085 (the Arc leads by 0.3%), the NVIDIA P102-100 at 58,528 (the Arc trails by 0.5%), and the AMD Radeon PRO V710 at 58,657 (the Arc trails by 0.7%). These deltas are narrow, meaning the Arc A570M sits in a tight cluster of comparable GPUs around the 58,000 to 58,700 score range.

The AMD Instinct MI355X has no benchmark entries and no nearest rivals in the database, so its wins are defined by specification dominance rather than measured performance. It uses 16,384 shading units, 1,024 texture mapping units, and 288 GB of HBM3e memory with an 8,192-bit bus. Those figures dwarf the Arc A570M's 2,048 shading units, 128 TMUs, and 8 GB of GDDR6 on a 128-bit interface. Where the Arc A570M wins is in the feature set for consumer-facing workloads: it has 64 ROPs, 16 ray tracing cores, DirectX 12 Ultimate support, OpenGL 4.6, and Vulkan 1.4. The MI355X lists no ROPs, no ray tracing cores, and no graphics API support, with a pixel rate of 0 MPixel/s.

For use cases, the MI355X targets compute-heavy workloads that demand massive memory capacity and bandwidth. The Arc A570M targets portable devices that need rendering, ray tracing, and standard graphics API compatibility. The MI355X also has a much higher thermal envelope at 1400 W, while the Arc A570M draws only 75 W, so the two are not competing for the same chassis or power budget.

Architecture Differences

The MI355X uses the CDNA 4.0 architecture on a 3 nm process from TSMC, with a chip designated MI350 256CU. It integrates 185,000 million transistors on a die size of 2,380 mm², yielding a transistor density of 77.7 million per square millimeter. The Arc A570M uses the Xe-HPG architecture on a 6 nm process, also from TSMC, with a DG2-256 chip. It has 11,500 million transistors on a 269 mm² die, for a density of 42.8 million per square millimeter.

The MI355X belongs to the Instinct (MIx) generation and succeeds the Radeon Instinct line. The Arc A570M belongs to the Alchemist generation under the Arc 5 Mobile series and is currently marked as active in production. The MI355X has no listed production status. The MI355X was released on June 11, 2025, while the Arc A570M was released on July 31, 2023.

The compute architectures differ sharply. The MI355X reports FP32 at 78.64 TFLOPS and FP16 at 78.64 TFLOPS with a 1:1 ratio, meaning it does not gain a throughput advantage on half-precision workloads. The Arc A570M reports FP32 at 5.325 TFLOPS and FP16 at 10.65 TFLOPS with a 2:1 ratio, so it processes half-precision math at twice the rate of full precision. The MI355X has 16,384 shading units and 1,024 TMUs, while the Arc has 2,048 shading units, 128 TMUs, and 64 ROPs. The MI355X lists no ROPs, which aligns with its compute-only design and lack of display outputs.

Memory architecture is another major divergence. The MI355X uses 288 GB of HBM3e on an 8,192-bit bus, delivering 8.19 TB/s of bandwidth. The Arc A570M uses 8 GB of GDDR6 on a 128-bit bus, delivering 224.0 GB/s. The clock behavior also differs: the MI355X has a base clock of 1000 MHz and a boost clock of 2400 MHz, while the Arc runs at 900 MHz base and 1300 MHz boost. The MI355X memory runs at 2000 MHz with 8 Gbps effective, while the Arc memory runs at 1750 MHz with 14 Gbps effective.

The MI355X uses a PCIe 5.0 x16 interface, while the Arc A570M uses PCIe 4.0 x8. The MI355X is an OAM module with no power connectors and no display outputs, requiring a suggested PSU of 1800 W. The Arc A570M is an IGP with portable device dependent outputs and no suggested PSU listed. The MI355X has no graphics API support (DirectX, OpenGL, and Vulkan are all listed as N/A), while the Arc supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Head-to-Head Benchmarks

There are no shared benchmark results in the database for these two GPUs, so a direct score comparison is not possible from the recorded data. The Arc A570M has one measured score, and the MI355X has none. The only quantitative comparison available is between the Arc A570M and its nearest rivals, which shows how the mobile part performs relative to other GPUs in its score range.

The Arc A570M scores 58,239 in Geekbench OpenCL. That is 0.3% below the AMD Radeon RX 6950 XT's 58,392, 0.3% above the AMD Radeon RX 5600 OEM's 58,085, 0.5% below the NVIDIA P102-100's 58,528, and 0.7% below the AMD Radeon PRO V710's 58,657. These results place the Arc A570M in the 88th percentile of all GPUs, which is a strong showing for a mobile processor with a 75 W envelope.

The MI355X cannot be compared through this method because the database contains no benchmark score or nearest rival entries for it. Its specification data indicates a device built for an entirely different workload class. The FP32 throughput of 78.64 TFLOPS and memory bandwidth of 8.19 TB/s are orders of magnitude beyond what the Arc A570M offers, but no measured result exists to quantify that gap in a benchmark sense.

Texture rate provides one specification-level comparison. The MI355X lists a texture rate of 2,457.6 GTexel/s, while the Arc A570M lists 166.4 GTexel/s. Pixel rate is reversed in usefulness: the Arc delivers 83.20 GPixel/s, while the MI355X lists 0 MPixel/s, confirming that the AMD part does not perform rasterization tasks.

FAQ

Q: Which GPU has better compute throughput?

A: The AMD Instinct MI355X lists FP32 at 78.64 TFLOPS and FP16 at 78.64 TFLOPS with a 1:1 ratio. The Intel Arc A570M lists FP32 at 5.325 TFLOPS and FP16 at 10.65 TFLOPS with a 2:1 ratio. The MI355X also has a texture rate of 2,457.6 GTexel/s versus 166.4 GTexel/s for the Arc.

Q: Does the Intel Arc A570M support ray tracing?

A: Yes. The Arc A570M has 16 ray tracing cores and supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The MI355X lists no ray tracing cores and has no graphics API support, with DirectX, OpenGL, and Vulkan all listed as N/A.

Q: How does the Arc A570M compare to its nearest rivals in the database?

A: The Arc A570M scores 58,239 in Geekbench OpenCL. It trails the AMD Radeon RX 6950 XT by 0.3%, leads the AMD Radeon RX 5600 OEM by 0.3%, trails the NVIDIA P102-100 by 0.5%, and trails the AMD Radeon PRO V710 by 0.7%.

Q: What memory configurations do the two GPUs use?

A: The MI355X uses 288 GB of HBM3e on an 8,192-bit bus with 8.19 TB/s bandwidth. The Arc A570M uses 8 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth.

Q: Can the MI355X output video to a display?

A: No. The MI355X lists no display outputs and has a pixel rate of 0 MPixel/s. The Arc A570M lists portable device dependent display outputs and has a pixel rate of 83.20 GPixel/s.

Q: What are the power requirements for each GPU?

A: The MI355X has a TDP of 1400 W and a suggested PSU of 1800 W, and it is an OAM module with no power connectors. The Arc A570M has a TDP of 75 W and is classified as an IGP with no suggested PSU listed.

Specification Differences

The two GPUs differ in nearly every specification field recorded in the database. Process node: the MI355X uses 3 nm from TSMC, while the Arc A570M uses 6 nm from TSMC. Transistor count: 185,000 million for the MI355X versus 11,500 million for the Arc. Die size: 2,380 mm² versus 269 mm². Transistor density: 77.7 million per square millimeter versus 42.8 million per square millimeter.

Base clock: 1000 MHz for the MI355X versus 900 MHz for the Arc. Boost clock: 2400 MHz versus 1300 MHz. Memory clock: 2000 MHz with 8 Gbps effective for the MI355X versus 1750 MHz with 14 Gbps effective for the Arc. Memory size: 288 GB versus 8 GB. Memory type: HBM3e versus GDDR6. Bus width: 8,192 bit versus 128 bit. Bandwidth: 8.19 TB/s versus 224.0 GB/s.

Shading units: 16,384 versus 2,048. TMUs: 1,024 versus 128. ROPs: 0 versus 64. Ray tracing cores: none listed versus 16. Pixel rate: 0 MPixel/s versus 83.20 GPixel/s. Texture rate: 2,457.6 GTexel/s versus 166.4 GTexel/s. FP32: 78.64 TFLOPS versus 5.325 TFLOPS. FP16: 78.64 TFLOPS (1:1) versus 10.65 TFLOPS (2:1).

TDP: 1400 W versus 75 W. Slot width: OAM Module versus IGP. Power connectors: none versus not listed. Suggested PSU: 1800 W versus none listed. Bus interface: PCIe 5.0 x16 versus PCIe 4.0 x8. Display outputs: no outputs versus portable device dependent. Graphics APIs: all N/A versus DirectX 12 Ultimate (12_2), OpenGL 4.6, Vulkan 1.4. Dimensions: 102 mm by 165 mm for the MI355X, no dimensions listed for the Arc. Release date: June 11, 2025 versus July 31, 2023. Production status: none listed versus active.

The Verdict

The database shows two products with no common benchmark ground. The AMD Instinct MI355X is a compute accelerator with massive FP32 throughput, 288 GB of HBM3e memory, and an 8.19 TB/s memory bus, but it lacks display outputs, graphics API support, and ROPs. It is built for environments that do not need rasterization or rendering, and its 1400 W TDP places it in server or accelerator chassis with a suggested 1800 W PSU.

The Intel Arc A570M is a mobile graphics processor with a measured Geekbench OpenCL score of 58,239, placing it in the 88th percentile of all GPUs. It delivers ray tracing support, DirectX 12 Ultimate, and a 75 W TDP, making it suitable for portable devices with display output needs. Its nearest rivals in the database are all within 0.7% of its score, so it performs in line with GPUs like the AMD Radeon RX 6950 XT and the AMD Radeon RX 5600 OEM in OpenCL compute.

The choice between the two depends entirely on workload class. For compute-heavy tasks requiring enormous memory capacity and bandwidth with no display output, the MI355X is the clear pick. For mobile rendering, ray tracing, and standard graphics API workloads, the Arc A570M is the only one of the two that offers those features at all. The data does not support a direct performance comparison, but it does show that these GPUs are not substitutes for one another.