AMD Steam Machine GPU vs Intel Arc A380E Comparison

Head-to-Head Benchmarks

The recorded data shows no direct benchmark matches between the AMD Steam Machine GPU and the Intel Arc A380E in the database. Both parts carry an average benchmark score of zero, and neither has a populated win count in head-to-head comparisons. This absence of measured results means the comparison must be built from the architectural and specification data that is recorded for each part.

What the data does provide is a clear separation in raw compute capability. The AMD Steam Machine GPU delivers 17.56 TFLOPS of FP32 performance, while the Intel Arc A380E delivers 4.096 TFLOPS. That places the AMD part at approximately 4.3 times the FP32 throughput of the Intel part. In FP16 workloads, the AMD part again outputs 17.56 TFLOPS with a 1:1 ratio, whereas the Intel part reaches 8.192 TFLOPS with a 2:1 ratio. The AMD part still leads by a factor of about 2.1 in FP16, but the Intel part's 2:1 shader ratio narrows the gap compared to FP32.

Pixel throughput shows a similar pattern. The AMD Steam Machine GPU records 156.8 GPixel/s against 64.00 GPixel/s for the Intel Arc A380E, a lead of roughly 2.45 times. Texture rate favors the AMD part as well: 274.4 GTexel/s versus 128.0 GTexel/s, which is about 2.14 times higher. These differences indicate that the AMD part can sustain higher fill rates across both pixel and texture stages, which typically translates to stronger performance in resolution-bound and texture-heavy scenes.

Memory bandwidth is another major differentiator. The AMD Steam Machine GPU uses 8 GB of GDDR6 on a 128-bit bus, producing 288.0 GB/s of bandwidth. The Intel Arc A380E uses 6 GB of GDDR6 on a 96-bit bus, producing 186.0 GB/s. The AMD part therefore offers 1.55 times the memory bandwidth, along with 2 GB more capacity. The Intel part operates at a higher memory clock in terms of base frequency (1937 MHz versus 2250 MHz for AMD), but the AMD part's effective data rate of 18 Gbps exceeds Intel's 15.5 Gbps effective rate, and the wider bus delivers the overall bandwidth advantage.

Clock behavior also differs. The AMD part lists a base clock of 1720 MHz, a boost clock of 2450 MHz, and a game clock of 2250 MHz. The Intel part lists a fixed 2000 MHz base and boost with no separate game clock. The AMD part's boost ceiling is 22.5% higher than Intel's fixed clock, and its game clock is 12.5% higher. However, the Intel part starts from a higher base clock, which can matter in power-constrained or thermally constrained scenarios where sustained boost is limited.

Both parts record a percentile versus all GPUs of 50, indicating they sit at the midpoint of the database distribution. With no benchmark scores recorded, this percentile is common to both and does not separate them in measured performance.

FAQ

Q: Which GPU has higher FP32 compute?

A: The AMD Steam Machine GPU records 17.56 TFLOPS of FP32, while the Intel Arc A380E records 4.096 TFLOPS. The AMD part is about 4.3 times higher in this metric.

Q: How do the memory configurations differ?

A: The AMD Steam Machine GPU has 8 GB of GDDR6 on a 128-bit bus with 288.0 GB/s bandwidth. The Intel Arc A380E has 6 GB of GDDR6 on a 96-bit bus with 186.0 GB/s bandwidth. The AMD part has both more capacity and higher bandwidth.

Q: Do both GPUs support the same API feature levels?

A: Yes. Both list DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The API support profiles are identical in the recorded data.

Q: Which GPU has more ray tracing cores?

A: The AMD Steam Machine GPU has 28 ray tracing cores, while the Intel Arc A380E has 8. The AMD part has 3.5 times the ray tracing core count.

Q: What are the power requirements?

A: The AMD Steam Machine GPU has a TDP of 110 W and no power connectors. The Intel Arc A380E has a TDP of 75 W, no power connectors, and a suggested PSU rating of 250 W.

Q: What is the production status of each GPU?

A: The AMD Steam Machine GPU is listed as Active. The Intel Arc A380E is listed as End-of-life, with a predecessor of Xe Graphics and a successor of Battlemage.

Architecture Differences

The two GPUs come from different architectural families. The AMD Steam Machine GPU uses RDNA 3.0 with the Navi 33 chip and the codename Hotpink Bonefish. It belongs to the Console GPU (Valve) generation. The Intel Arc A380E uses Xe-HPG with the DG2-128 chip and belongs to the Alchemist (Arc 3) generation.

Both are built on a 6 nm process at TSMC, but the die characteristics differ substantially. The AMD part integrates 13,300 million transistors on a 204 mm² die, yielding a transistor density of 65.2 million per mm². The Intel part integrates 7,200 million transistors on a 157 mm² die, yielding a transistor density of 45.9 million per mm². The AMD part has roughly 84.7% more transistors and a die that is about 29.9% larger, but it also packs transistors more densely by about 42%.

The compute units differ in scale. The AMD Steam Machine GPU has 1792 shading units, 112 texture mapping units, 64 raster operating units, and 28 ray tracing cores. The Intel Arc A380E has 1024 shading units, 64 TMUs, 32 ROPs, and 8 ray tracing cores. In every one of these categories, the AMD part has more than double the Intel part's count, except for shading units where it has 1.75 times as many.

FP16 handling reveals a notable architectural divergence. The AMD part executes FP16 at the same rate as FP32, listed as 17.56 TFLOPS with a 1:1 ratio. The Intel part executes FP16 at twice its FP32 rate, listed as 8.192 TFLOPS with a 2:1 ratio. This means the Intel architecture dedicates more of its throughput to half-precision work, while the AMD part treats both precision levels equally. In practice, the AMD part still outpaces the Intel part in FP16, but the Intel part's ratio advantage means the gap is smaller than in FP32.

The memory subsystem also reflects different design priorities. The AMD part uses a 128-bit bus with 288.0 GB/s bandwidth and 8 GB capacity. The Intel part uses a 96-bit bus with 186.0 GB/s bandwidth and 6 GB capacity. The AMD part's bus is 33.3% wider, and its bandwidth advantage is 54.8%. The AMD part also runs its memory at a higher effective data rate of 18 Gbps versus 15.5 Gbps for Intel.

Power delivery and physical design differ as well. The AMD part has a TDP of 110 W and no power connectors. The Intel part has a TDP of 75 W, no power connectors, and a suggested PSU rating of 250 W. The Intel part is single-slot, while the AMD part has no recorded slot width. The AMD part measures 156 mm in length, 152 mm in height, and 162 mm in width. The Intel part measures 254 mm in length, 127 mm in height, and 20 mm in width. The Intel part is considerably longer but much thinner.

Display outputs also differ. The AMD Steam Machine GPU provides 1x HDMI 2.1a and 1x DisplayPort 2.1. The Intel Arc A380E provides 4x DisplayPort 2.0. The AMD part offers the newer DisplayPort revision but fewer outputs, while the Intel part offers four outputs but an older DisplayPort revision. The bus interface is not recorded for the AMD part, while the Intel part uses PCIe 4.0 x8.

The Intel part has an explicitly listed predecessor (Xe Graphics) and successor (Battlemage), while the AMD part lists neither. The AMD part is marked as Active production; the Intel part is marked as End-of-life. The AMD part has a release date of June 2026, while the Intel part has a release date of March 2024.

The Verdict

The recorded data points to a clear hierarchy. The AMD Steam Machine GPU leads in every major compute and memory metric: FP32, FP16, pixel rate, texture rate, memory bandwidth, memory capacity, ray tracing cores, shading units, TMUs, and ROPs. It is also the only one of the two that remains in Active production status.

The Intel Arc A380E does hold advantages in a few specific areas. It has a higher base clock (2000 MHz versus 1720 MHz), a lower TDP (75 W versus 110 W), a single-slot form factor, four display outputs instead of two, and a recorded PCIe 4.0 x8 interface. It also carries a suggested PSU rating of 250 W, which is not recorded for the AMD part. These factors make it a more compact and lower-power option on paper.

For users selecting based on raw performance and future availability, the AMD Steam Machine GPU is the stronger choice. Its FP32 output is 4.3 times higher, its bandwidth is 1.55 times higher, and its memory capacity is 2 GB larger. The Active production status also suggests ongoing availability, while the Intel Arc A380E is listed as End-of-life with a successor already named.

The Intel Arc A380E remains relevant only in scenarios where power draw, physical size, or output count take priority. Its 75 W TDP is 31.8% lower than the AMD part's 110 W TDP. Its single-slot design and 20 mm width contrast sharply with the AMD part's 162 mm width. Its four DisplayPort 2.0 outputs exceed the AMD part's two outputs. Those are the only recorded categories where the Intel part wins.

Specification Differences

The two GPUs differ across nearly every recorded specification field.

• Chip: AMD uses Navi 33; Intel uses DG2-128.
• Architecture: AMD uses RDNA 3.0; Intel uses Xe-HPG.
• Codename: AMD has Hotpink Bonefish; Intel has none recorded.
• Generation: AMD is Console GPU (Valve); Intel is Alchemist (Arc 3).
• Transistors: AMD has 13,300 million; Intel has 7,200 million.
• Die size: AMD is 204 mm²; Intel is 157 mm².
• Transistor density: AMD is 65.2M / mm²; Intel is 45.9M / mm².
• Base clock: AMD is 1720 MHz; Intel is 2000 MHz.
• Boost clock: AMD is 2450 MHz; Intel is 2000 MHz.
• Game clock: AMD is 2250 MHz; Intel has none recorded.
• Memory clock: AMD is 2250 MHz (18 Gbps effective); Intel is 1937 MHz (15.5 Gbps effective).
• Memory size: AMD is 8 GB; Intel is 6 GB.
• Memory bus: AMD is 128 bit; Intel is 96 bit.
• Memory bandwidth: AMD is 288.0 GB/s; Intel is 186.0 GB/s.
• Shading units: AMD has 1792; Intel has 1024.
• TMUs: AMD has 112; Intel has 64.
• ROPs: AMD has 64; Intel has 32.
• Ray tracing cores: AMD has 28; Intel has 8.
• Pixel rate: AMD is 156.8 GPixel/s; Intel is 64.00 GPixel/s.
• Texture rate: AMD is 274.4 GTexel/s; Intel is 128.0 GTexel/s.
• FP32: AMD is 17.56 TFLOPS; Intel is 4.096 TFLOPS.
• FP16: AMD is 17.56 TFLOPS (1:1); Intel is 8.192 TFLOPS (2:1).
• TDP: AMD is 110 W; Intel is 75 W.
• Slot width: AMD has none recorded; Intel is single-slot.
• Suggested PSU: AMD has none recorded; Intel is 250 W.
• Bus interface: AMD has none recorded; Intel is PCIe 4.0 x8.
• Display outputs: AMD has 1x HDMI 2.1a and 1x DisplayPort 2.1; Intel has 4x DisplayPort 2.0.
• Dimensions: AMD is 156 mm length, 152 mm height, 162 mm width; Intel is 254 mm length, 127 mm height, 20 mm width.
• Production status: AMD is Active; Intel is End-of-life.
• Release date: AMD is June 2026; Intel is March 2024.
• Predecessor: AMD has none recorded; Intel is Xe Graphics.
• Successor: AMD has none recorded; Intel is Battlemage.

Where Each One Wins

The AMD Steam Machine GPU wins in all performance-oriented categories. Its FP32 output of 17.56 TFLOPS is 4.3 times the Intel part's 4.096 TFLOPS, making it the clear choice for compute-heavy workloads that rely on single-precision floating point. Its FP16 output of 17.56 TFLOPS also exceeds the Intel part's 8.192 TFLOPS, even though the Intel part runs FP16 at a 2:1 ratio. Its pixel rate of 156.8 GPixel/s and texture rate of 274.4 GTexel/s both more than double the Intel part's corresponding rates, indicating stronger performance in fill-limited rendering. Its 28 ray tracing cores versus 8 give it a substantial edge in ray-traced workloads. Its 288.0 GB/s bandwidth and 8 GB capacity provide both higher throughput and more headroom for large textures and assets.

The Intel Arc A380E wins in efficiency and physical integration. Its 75 W TDP is lower than the AMD part's 110 W TDP, which can translate to simpler cooling requirements and lower system-level power draw. Its single-slot design and 20 mm width make it suitable for space-constrained chassis, while the AMD part's 162 mm width suggests a bulkier footprint. Its four DisplayPort 2.0 outputs support multi-display configurations beyond the AMD part's two outputs. Its base clock of 2000 MHz is higher than the AMD part's 1720 MHz, which may help in short-duration workloads that do not sustain boost. Its PCIe 4.0 x8 interface is explicitly recorded, while the AMD part has no recorded bus interface. Its suggested PSU rating of 250 W provides a clear power supply guideline, though the AMD part has none recorded.

The production status split is decisive for long-term planning. The AMD part is Active and released in June 2026. The Intel part is End-of-life and released in March 2024, with a successor already identified. The database shows no benchmark scores for either part, so these conclusions rest on the specification-level data. Within that data, the AMD Steam Machine GPU dominates every compute, memory, and rendering metric, while the Intel Arc A380E offers advantages in power, size, and display output count.