AMD Steam Machine GPU vs Intel Arc A570M Comparison

AMD Steam Machine GPU versus Intel Arc A570M: two mobile-oriented graphics solutions that approach the same problem from very different architectural directions. The AMD part, built on Navi 33 with RDNA 3.0, targets a Valve console form factor. The Intel Arc A570M, based on DG2-256 with Xe-HPG, is an Alchemist generation mobile part. The database contains direct benchmark data for the Intel component only, but the recorded specifications and API support allow a detailed comparative analysis.

Head-to-Head Benchmarks

The Intel Arc A570M has one recorded benchmark result in the database: a Geekbench OpenCL score of 58,239. That score places the GPU at the 88th percentile among all GPUs in the database. Its nearest rivals in the rankings are closely clustered: the AMD Radeon RX 6950 XT scores 58,392, a delta of -0.3 percent relative to the Arc A570M, meaning the RX 6950 XT is effectively tied. The AMD Radeon RX 5600 OEM scores 58,085, a delta of +0.3 percent, again a statistical dead heat. The NVIDIA P102-100 scores 58,528, a delta of -0.5 percent. The AMD Radeon PRO V710 scores 58,657, a delta of -0.7 percent. In other words, the Arc A570M sits inside a performance band spanning less than one percent across four rival products, indicating that its compute throughput lands in a very specific tier of the market.

The AMD Steam Machine GPU has no benchmark entries in the database, so its direct measured scores are absent. However, the specification sheet provides a theoretical peak FP32 throughput of 17.56 TFLOPS for the AMD part, compared to 5.325 TFLOPS for the Intel Arc A570M. That is a substantial arithmetic gap: the AMD GPU's FP32 figure is roughly 3.3 times higher than the Intel part's. The AMD GPU also lists FP16 performance at 17.56 TFLOPS with a 1:1 ratio to FP32, while the Intel part lists 10.65 TFLOPS FP16 with a 2:1 ratio. In raw shader math, the AMD part has the decisive advantage. The pixel rate tells a similar story: the AMD Steam Machine GPU outputs 156.8 GPixel/s, the Intel Arc A570M outputs 83.20 GPixel/s. Texture rate follows: 274.4 GTexel/s for AMD versus 166.4 GTexel/s for Intel. Every throughput metric in the specification sheet favors the AMD GPU by a wide margin.

The memory subsystem also diverges. Both cards use 8 GB of GDDR6 on a 128-bit bus, but the AMD part runs memory at 2250 MHz with 18 Gbps effective, producing 288.0 GB/s of bandwidth. The Intel part runs memory at 1750 MHz with 14 Gbps effective, producing 224.0 GB/s. That is a 64 GB/s difference, or roughly 29 percent more bandwidth for the AMD GPU. For texture-heavy workloads and high-resolution frame buffer access, that bandwidth advantage compounds the shader throughput lead.

Where Each One Wins

The AMD Steam Machine GPU wins in every raw throughput category recorded in the database. Its FP32 compute of 17.56 TFLOPS dwarfs the Intel Arc A570M's 5.325 TFLOPS. Its pixel rate of 156.8 GPixel/s versus 83.20 GPixel/s means it can drive more pixels per second through the rasterizer. Its texture rate of 274.4 GTexel/s versus 166.4 GTexel/s allows faster texel fetching and filtering. Memory bandwidth of 288.0 GB/s versus 224.0 GB/s reduces bottlenecks when shaders demand data faster than the bus can deliver. The AMD GPU also has more ray tracing cores: 28 versus 16 for the Intel part. Even the transistor count favors AMD: 13,300 million transistors on a 204 mm² die, versus 11,500 million on a 269 mm² die. The AMD die is smaller and denser, at 65.2M transistors per mm², while the Intel die has a density of 42.8M per mm².

The Intel Arc A570M wins in areas that matter for integration and power envelope. Its TDP is 75 W, which is 35 W lower than the AMD Steam Machine GPU's 110 W. The Intel part is designated as an IGP, meaning it is integrated into a motherboard or system-on-chip package, whereas the AMD part is a standalone GPU with no power connectors listed. The Intel part has a PCIe 4.0 x8 bus interface, while the AMD part lists no bus interface at all. The Intel part also has more shading units (2048 versus 1792) and more texture mapping units (128 versus 112), though those higher counts do not translate into higher throughput because the AMD part runs at much higher clocks. The AMD GPU has a boost clock of 2450 MHz and a base clock of 1720 MHz, while the Intel part boosts to only 1300 MHz and bases at 900 MHz. The clock speed gap explains why the AMD part's lower unit count still produces far higher output rates.

The recorded OpenCL benchmark for the Intel Arc A570M shows it performing at a level comparable to desktop GPUs like the RX 6950 XT, a high-end part from a previous generation. That indicates the Intel part, despite its modest 75 W TDP, achieves compute efficiency that places it in elite company according to the database percentile. The AMD Steam Machine GPU, lacking recorded benchmarks, cannot be positioned in the percentile rankings, but its specification sheet suggests it should outperform the Intel part in every measured throughput category if those specs translate to real-world results.

The Verdict

The data indicates a clear split by use case. For applications that depend on raw shader throughput, texture fill, pixel fill, or memory bandwidth, the AMD Steam Machine GPU is the stronger part on paper. Its FP32 throughput is more than triple that of the Intel Arc A570M, its pixel rate is nearly double, its texture rate is about 65 percent higher, and its memory bandwidth is 29 percent higher. Ray tracing hardware is also more abundant on the AMD side, with 28 RT cores versus 16. Anyone prioritizing maximum compute density, high-resolution rendering, or heavy texture work should favor the AMD GPU based solely on the recorded specifications.

For applications that demand low power consumption, compact integration, or a simpler system design, the Intel Arc A570M holds the advantage. Its 75 W TDP versus 110 W means less heat generation and less demand on cooling. Its IGP designation and PCIe 4.0 x8 interface make it suitable for portable devices where discrete power connectors are not available. The Intel part also has a recorded benchmark showing real-world OpenCL performance at the 88th percentile, with nearest rivals all within one percent of its score. That measured result gives the Intel part a level of empirical validation the AMD part lacks in the database.

The verdict rests on whether the buyer trusts the AMD specification sheet or the Intel benchmark result. The specifications suggest the AMD GPU is the faster part by a wide margin, but no measured data confirms it. The Intel part has a confirmed score that places it competitively against high-end desktop GPUs. For a user who values verified performance, the Intel Arc A570M is the safer choice. For a user who values theoretical maximum throughput and has the power budget to accommodate 110 W, the AMD Steam Machine GPU appears superior on every recorded metric.

FAQ

Q: How does the Intel Arc A570M's benchmark score compare to its nearest rivals?

A: The Arc A570M scores 58,239 in Geekbench OpenCL. The AMD Radeon RX 6950 XT scores 58,392, a delta of -0.3 percent. The AMD Radeon RX 5600 OEM scores 58,085, a delta of +0.3 percent. The NVIDIA P102-100 scores 58,528, a delta of -0.5 percent. The AMD Radeon PRO V710 scores 58,657, a delta of -0.7 percent. All four rivals are within one percent of the Arc A570M's score.

Q: Which GPU has higher FP32 compute throughput?

A: The AMD Steam Machine GPU lists FP32 throughput of 17.56 TFLOPS. The Intel Arc A570M lists FP32 throughput of 5.325 TFLOPS. The AMD part is approximately 3.3 times higher.

Q: What are the memory bandwidth figures for both GPUs?

A: The AMD Steam Machine GPU has 8 GB of GDDR6 on a 128-bit bus running at 18 Gbps effective, yielding 288.0 GB/s. The Intel Arc A570M has 8 GB of GDDR6 on a 128-bit bus running at 14 Gbps effective, yielding 224.0 GB/s.

Q: Which GPU has more ray tracing cores?

A: The AMD Steam Machine GPU has 28 ray tracing cores. The Intel Arc A570M has 16 ray tracing cores.

Q: What is the TDP difference between the two GPUs?

A: The AMD Steam Machine GPU has a TDP of 110 W. The Intel Arc A570M has a TDP of 75 W. The Intel part draws 35 W less.

Q: Do both GPUs support the same DirectX and Vulkan versions?

A: Yes. Both list DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 in their API support specifications.

Architecture Differences

The AMD Steam Machine GPU uses the Navi 33 chip built on RDNA 3.0 architecture, with the codename "Hotpink Bonefish." It belongs to the Console GPU (Valve) generation. The chip is manufactured on a 6 nm process at TSMC, containing 13,300 million transistors on a 204 mm² die, giving a transistor density of 65.2M per mm². The architecture uses 1792 shading units, 112 texture mapping units, 64 render output units, and 28 ray tracing cores. It has no tensor cores listed. Clocks are set at 1720 MHz base, 2250 MHz game, and 2450 MHz boost, with memory at 2250 MHz or 18 Gbps effective. The GPU supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Display outputs include one HDMI 2.1a and one DisplayPort 2.1. The physical dimensions are 156 mm in length, 152 mm in height, and 162 mm in width.

The Intel Arc A570M uses the DG2-256 chip built on Xe-HPG architecture, belonging to the Alchemist (Arc 5 Mobile) generation. It is also manufactured on a 6 nm process at TSMC, containing 11,500 million transistors on a 269 mm² die, giving a transistor density of 42.8M per mm². The architecture uses 2048 shading units, 128 texture mapping units, 64 render output units, and 16 ray tracing cores. No tensor cores are listed. Clocks are set at 900 MHz base and 1300 MHz boost, with memory at 1750 MHz or 14 Gbps effective. The GPU supports the same API set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The display outputs are listed as "Portable Device Dependent," and the slot width is designated as IGP. The bus interface is PCIe 4.0 x8.

Key architectural differences include the transistor density, where AMD packs 65.2M transistors per mm² versus Intel's 42.8M per mm². The AMD chip is smaller at 204 mm² versus 269 mm², yet contains more transistors. The AMD part has fewer shading units but runs at much higher clocks, which explains its higher throughput. The AMD part has more ray tracing cores (28 versus 16). The FP16 execution ratio differs: AMD runs FP16 at 1:1 with FP32, while Intel runs FP16 at 2:1, meaning the Intel part processes FP16 at twice the rate of FP32. The AMD part has no power connectors listed, while the Intel part has no power connector data at all but is an IGP. The AMD part has explicit physical dimensions, while the Intel part has none listed.

Specification Differences

The two GPUs differ in several recorded specification fields. The AMD Steam Machine GPU uses the Navi 33 chip with RDNA 3.0 architecture and the codename "Hotpink Bonefish," while the Intel Arc A570M uses the DG2-256 chip with Xe-HPG architecture and no codename listed. The AMD part belongs to the Console GPU (Valve) generation, while the Intel part belongs to the Alchemist (Arc 5 Mobile) generation. Transistor count differs: 13,300 million for AMD versus 11,500 million for Intel. Die size differs: 204 mm² for AMD versus 269 mm² for Intel. Transistor density differs: 65.2M per mm² for AMD versus 42.8M per mm² for Intel.

Clock speeds differ substantially. The AMD part has a base clock of 1720 MHz, a game clock of 2250 MHz, a boost clock of 2450 MHz, and a memory clock of 2250 MHz with 18 Gbps effective. The Intel part has a base clock of 900 MHz, no game clock listed, a boost clock of 1300 MHz, and a memory clock of 1750 MHz with 14 Gbps effective. Memory bandwidth differs: 288.0 GB/s for AMD versus 224.0 GB/s for Intel. Shading units differ: 1792 for AMD versus 2048 for Intel. Texture mapping units differ: 112 for AMD versus 128 for Intel. Render output units are the same at 64 for both. Ray tracing cores differ: 28 for AMD versus 16 for Intel.

Pixel rate differs: 156.8 GPixel/s for AMD versus 83.20 GPixel/s for Intel. Texture rate differs: 274.4 GTexel/s for AMD versus 166.4 GTexel/s for Intel. FP32 throughput differs: 17.56 TFLOPS for AMD versus 5.325 TFLOPS for Intel. FP16 throughput differs: 17.56 TFLOPS (1:1) for AMD versus 10.65 TFLOPS (2:1) for Intel. TDP differs: 110 W for AMD versus 75 W for Intel. The Intel part has a slot width of IGP, while the AMD part has no slot width listed. The Intel part has a bus interface of PCIe 4.0 x8, while the AMD part has no bus interface listed. The AMD part lists power connectors as "None," while the Intel part has no power connector data. Display outputs differ: AMD lists one HDMI 2.1a and one DisplayPort 2.1, while Intel lists "Portable Device Dependent." Physical dimensions exist for AMD (156 mm length, 152 mm height, 162 mm width) but not for Intel. Release dates differ: AMD released on 2026-06-28, Intel released on 2023-07-31. The Intel part has an average benchmark score of 58,239 and sits at the 88th percentile, while the AMD part has no benchmark score and sits at the 50th percentile.