Intel Arc A380M vs NVIDIA GeForce RTX 5090 SE Comparison

Head-to-Head Benchmarks

The recorded data contains no benchmark scores for either the Intel Arc A380M or the NVIDIA GeForce RTX 5090 SE. Both GPUs hold an average benchmark score of zero in the database, and no head-to-head benchmark entries exist for this pairing. This absence of measurements means a direct numerical performance comparison cannot be established from the available records.

What the database does show is a massive gap in raw compute specifications. The NVIDIA GeForce RTX 5090 SE delivers 66.94 TFLOPS of FP32 throughput, while the Intel Arc A380M delivers 4.096 TFLOPS. That is a 16.3x difference in single-precision floating-point performance. The RTX 5090 SE also reaches 66.94 TFLOPS in FP16 (1:1 ratio), whereas the Arc A380M reaches 8.192 TFLOPS in FP16 (2:1 ratio). The NVIDIA part maintains full-rate FP16, while the Intel part halves its rate.

Pixel throughput shows a similar disparity. The RTX 5090 SE reaches 380.3 GPixel/s, compared to 64.00 GPixel/s for the Arc A380M, a 5.9x advantage. Texture fill rates are 1,045.9 GTexel/s versus 128.0 GTexel/s, an 8.2x margin. These are compute ceiling figures from the specification sheets, not measured workloads, but they indicate the NVIDIA GPU is in a different performance class entirely.

Memory bandwidth tells the same story. The RTX 5090 SE has 1.34 TB/s of bandwidth across a 384-bit bus with 24 GB of GDDR7 memory. The Arc A380M has 186.0 GB/s across a 96-bit bus with 6 GB of GDDR6 memory. That is roughly a 7.2x bandwidth advantage for the NVIDIA card.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API feature parity exists at the specification level. However, the RTX 5090 SE carries 110 ray tracing cores and 440 tensor cores, while the Arc A380M has 8 ray tracing cores and no listed tensor core count. The NVIDIA GPU also has 14,080 shading units against 1,024 for the Intel part, a 13.75x difference.

The percentile rankings are identical in the database: both sit at the 50th percentile versus all GPUs. With no benchmark scores recorded, this percentile value offers no differentiation between the two.

The Verdict

The database indicates that the NVIDIA GeForce RTX 5090 SE is the higher-performance part by every measurable specification. It has more shading units, more ray tracing cores, more tensor cores, wider memory bus, faster memory, higher clock speeds, and higher fill rates. The RTX 5090 SE also has a higher base clock at 1740 MHz versus 1550 MHz, and a higher boost clock at 2377 MHz versus 2000 MHz.

The Intel Arc A380M is a 35 W MXM module designed for portable devices, with display outputs listed as "Portable Device Dependent." The RTX 5090 SE is a dual-slot desktop card measuring 267 mm in length, 111 mm in height, and 40 mm in width, with a 1x 16-pin power connector and a 900 W suggested power supply. It carries a launch MSRP of 1,499 USD.

The data suggests two different market positions. The Arc A380M fits into compact, low-power portable systems where the 35 W TDP is a defining constraint. The RTX 5090 SE targets high-end desktop systems where the 500 W TDP and dual-slot footprint are acceptable trade-offs for maximum throughput.

From the recorded specifications, the RTX 5090 SE is the clear choice for anyone needing maximum compute and memory performance. The Arc A380M is the only option for portable-device form factors, given its MXM-A (3.1) bus interface and mobile-oriented design. No measured performance data exists in the database to challenge this specification-based assessment.

Architecture Differences

The Intel Arc A380M uses the DG2-128 chip built on the Xe-HPG architecture, part of the Alchemist generation for Arc 3 Mobile. It is fabricated on a 6 nm process at TSMC. The chip contains 7,200 million transistors on a 157 mm² die, producing a transistor density of 45.9M per mm².

The NVIDIA GeForce RTX 5090 SE uses the GB202 chip built on the Blackwell 2.0 architecture, part of the GeForce 50 generation, with the GeForce 40 as its predecessor and GeForce 60 as its successor. It is fabricated on a 5 nm process at TSMC. The chip contains 92,200 million transistors on a 750 mm² die, producing a transistor density of 122.9M per mm².

The transistor density difference is notable: 122.9M per mm² for the NVIDIA chip versus 45.9M per mm² for the Intel chip. The NVIDIA die is also 4.8x larger in area and carries 12.8x more transistors.

Ray tracing implementations differ in scale. The Arc A380M has 8 ray tracing cores, while the RTX 5090 SE has 110. The Intel GPU has no tensor core count listed, while the NVIDIA GPU has 440 tensor cores. Shading unit counts are 1,024 for Intel and 14,080 for NVIDIA.

Memory architecture differs fundamentally. The Arc A380M uses 6 GB of GDDR6 on a 96-bit bus. The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus. The NVIDIA part's memory clock is listed at 1750 MHz with 28 Gbps effective data rate; the Intel part's memory clock is 1937 MHz with 15.5 Gbps effective. Despite the lower physical clock, the wider bus and newer memory type give the NVIDIA card its 1.34 TB/s bandwidth.

FP16 processing also differs. The Arc A380M computes FP16 at a 2:1 ratio relative to FP32, meaning half rate. The RTX 5090 SE computes FP16 at a 1:1 ratio, meaning full rate. This makes the NVIDIA part more efficient for workloads that mix FP32 and FP16 operations.

Specification Differences

The two GPUs differ across nearly every recorded specification field.

Process node: 6 nm for Intel, 5 nm for NVIDIA, both at TSMC.

Transistors: 7,200 million for Intel, 92,200 million for NVIDIA.

Die size: 157 mm² for Intel, 750 mm² for NVIDIA.

Transistor density: 45.9M per mm² for Intel, 122.9M per mm² for NVIDIA.

Base clock: 1550 MHz for Intel, 1740 MHz for NVIDIA.

Boost clock: 2000 MHz for Intel, 2377 MHz for NVIDIA.

Memory: 6 GB GDDR6 at 186.0 GB/s for Intel; 24 GB GDDR7 at 1.34 TB/s for NVIDIA.

Memory bus: 96-bit for Intel, 384-bit for NVIDIA.

Memory clock: 1937 MHz (15.5 Gbps effective) for Intel; 1750 MHz (28 Gbps effective) for NVIDIA.

Shading units: 1,024 for Intel, 14,080 for NVIDIA.

TMUs: 64 for Intel, 440 for NVIDIA.

ROPs: 32 for Intel, 160 for NVIDIA.

Ray tracing cores: 8 for Intel, 110 for NVIDIA.

Tensor cores: not listed for Intel, 440 for NVIDIA.

Pixel rate: 64.00 GPixel/s for Intel, 380.3 GPixel/s for NVIDIA.

Texture rate: 128.0 GTexel/s for Intel, 1,045.9 GTexel/s for NVIDIA.

FP32: 4.096 TFLOPS for Intel, 66.94 TFLOPS for NVIDIA.

FP16: 8.192 TFLOPS (2:1) for Intel, 66.94 TFLOPS (1:1) for NVIDIA.

TDP: 35 W for Intel, 500 W for NVIDIA.

Slot width: MXM Module for Intel, Dual-slot for NVIDIA.

Power connectors: not listed for Intel, 1x 16-pin for NVIDIA.

Suggested PSU: not listed for Intel, 900 W for NVIDIA.

Bus interface: MXM-A (3.1) for Intel, PCIe 5.0 x16 for NVIDIA.

Display outputs: Portable Device Dependent for Intel; 1x HDMI 2.1b and 3x DisplayPort 2.1b for NVIDIA.

Dimensions: not listed for Intel; 267 mm length, 111 mm height, 40 mm width for NVIDIA.

Release date: 2023-01-23 for Intel, 2025-12-31 for NVIDIA.

Launch MSRP: not listed for Intel, 1,499 USD for NVIDIA.

Both share identical API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both are marked as Active in production status.

FAQ

Q: Which GPU has higher FP32 performance?

A: The NVIDIA GeForce RTX 5090 SE delivers 66.94 TFLOPS of FP32, which is 16.3x higher than the Intel Arc A380M's 4.096 TFLOPS.

Q: How do the memory subsystems compare?

A: The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus with 1.34 TB/s bandwidth. The Arc A380M uses 6 GB of GDDR6 on a 96-bit bus with 186.0 GB/s bandwidth.

Q: What is the TDP difference?

A: The Intel Arc A380M has a 35 W TDP. The NVIDIA GeForce RTX 5090 SE has a 500 W TDP and a 900 W suggested power supply.

Q: Which GPU has more ray tracing cores?

A: The RTX 5090 SE has 110 ray tracing cores. The Arc A380M has 8 ray tracing cores.

Q: What are the physical form factors?

A: The Arc A380M is an MXM Module using the MXM-A (3.1) bus interface with display outputs listed as Portable Device Dependent. The RTX 5090 SE is a dual-slot card measuring 267 mm by 111 mm by 40 mm, using PCIe 5.0 x16 with 1x HDMI 2.1b and 3x DisplayPort 2.1b outputs.

Q: When were both GPUs released?

A: The Intel Arc A380M has a release date of 2023-01-23. The NVIDIA GeForce RTX 5090 SE has a release date of 2025-12-31.

Q: What are the transistor counts?

A: The Intel chip contains 7,200 million transistors on a 157 mm² die. The NVIDIA chip contains 92,200 million transistors on a 750 mm² die.

Q: Do both support the same graphics APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.