Intel Arc A380E x2 vs NVIDIA GeForce RTX 5090 D Comparison

Intel Arc A380E x2 and NVIDIA GeForce RTX 5090 D occupy vastly different segments of the GPU market, and the recorded data reflects a fundamental mismatch in compute resources, memory architecture, and performance ceilings. The database shows the RTX 5090 D with a 92nd percentile ranking among all GPUs, while the Intel part sits at the 50th percentile. The RTX 5090 D delivers an average benchmark score of 77,712, but the A380E x2 has no recorded benchmark scores in the database, leaving its raw performance unquantified in direct competition.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries pairing the Intel Arc A380E x2 against the NVIDIA GeForce RTX 5090 D. The wins tally stands at zero for each side, meaning no single test result can be directly compared between the two. This absence of overlap stems from the RTX 5090 D being an active flagship product with a full suite of ten benchmark scores, while the A380E x2 is an end-of-life product with no recorded measurements.

For the RTX 5090 D, the recorded data shows a 3DMark Steel Nomad DX12 score of 14,326, which represents a modern DirectX 12 workload. The Geekbench OpenCL result reaches 310,674, while the Vulkan score climbs higher to 376,915, indicating strong raw compute throughput across both API families. Passmark results show a G3D score of 44,065 and a GPU compute score of 28,396, with legacy DirectX tests ranging from 219 in DirectX 12 to 434 in DirectX 9. The 2D graphics score sits at 1,487. These figures place the RTX 5090 D 1.1% ahead of the AMD Radeon RX 6650M XT in average score, but 1.6% behind the AMD Radeon RX 6850M XT, 2.1% behind the NVIDIA Tesla P100 PCIe 12 GB, and 2.4% behind the Tesla P100 PCIe 16 GB.

Without any benchmark data for the A380E x2, the only meaningful comparison comes from architectural specifications. The RTX 5090 D carries 21,760 shading units against 1,024 for the A380E x2, a 21.3x difference in raw shader count. Texture units stand at 680 versus 64, a 10.6x gap, while render output units show 176 versus 32, a 5.5x difference. The RTX 5090 D also holds 170 ray tracing cores compared to 8 for the Intel part, and 680 tensor cores where the Intel part lists none. These ratios suggest the RTX 5090 D should dominate in any compute-heavy workload, but the database cannot confirm this through direct test scores.

Where Each One Wins

The RTX 5090 D wins in every measurable category present in the database. Its FP32 throughput reaches 104.8 TFLOPS against 4.096 TFLOPS for the A380E x2, a 25.6x advantage. FP16 performance shows 104.8 TFLOPS for NVIDIA versus 8.192 TFLOPS for Intel, though the RTX 5090 D achieves this at a 1:1 ratio while the Intel part uses a 2:1 ratio. Pixel fill rate favors the RTX 5090 D at 423.6 GPixel/s versus 64.00 GPixel/s, and texture fill rate shows 1,636.8 GTexel/s versus 128.0 GTexel/s.

Memory capacity gives the RTX 5090 D a 32 GB GDDR7 configuration against 6 GB GDDR6 for the A380E x2, with bandwidth at 1.79 TB/s versus 186.0 GB/s. The bus width difference is stark: 512 bit versus 96 bit. The RTX 5090 D also uses a PCIe 5.0 x16 interface, while the A380E x2 runs on PCIe 4.0 x8, halving the available lanes on an older standard.

The A380E x2 does hold advantages in specific physical characteristics. Its 130 W TDP is substantially lower than the 575 W TDP of the RTX 5090 D, and the suggested power supply of 300 W compares favorably to the 950 W requirement for the NVIDIA card. The Intel card measures 265 mm in length, 127 mm in height, and 20 mm in width, making it a single-slot design, while the RTX 5090 D spans 304 mm by 137 mm by 48 mm as a dual-slot card. The A380E x2 also offers eight mini-DisplayPort 2.0 outputs, while the RTX 5090 D provides one HDMI 2.1b and three DisplayPort 2.1b outputs. These differences point toward the Intel card serving multi-display or embedded scenarios where power and physical footprint matter more than raw performance.

The Verdict

The data indicates the RTX 5090 D is the clear performance leader, with its 92nd percentile ranking and average score of 77,712 confirming its position near the top of the database. The A380E x2 cannot compete on raw compute, memory bandwidth, or feature support, as its 50th percentile ranking and zero recorded benchmarks leave it without a performance case.

Users requiring maximum compute throughput, large memory pools, or modern ray tracing and tensor operations should look to the RTX 5090 D, which the database shows at 1.1% ahead of the AMD Radeon RX 6650M XT and within 2.4% of the Tesla P100 variants. The Intel A380E x2 suits environments where the 130 W TDP, single-slot footprint, and eight DisplayPort outputs take priority, as these physical attributes are unmatched by the larger, higher-power NVIDIA card. The RTX 5090 D carries a launch MSRP of 2,299 USD, while the Intel card has no recorded launch price.

The production status also differs, with the RTX 5090 D listed as active and the A380E x2 marked end-of-life. The RTX 5090 D launched on 2025-01-29, succeeding the GeForce 40 series, while the A380E x2 released on 2024-03-31, succeeding Xe Graphics and preceding Battlemage. These lifecycle positions further reinforce the RTX 5090 D as the forward-looking choice for performance-focused buyers.

FAQ

Q: Which GPU has more shading units?

A: The NVIDIA GeForce RTX 5090 D has 21,760 shading units, while the Intel Arc A380E x2 has 1,024.

Q: What is the memory bandwidth difference?

A: The RTX 5090 D provides 1.79 TB/s bandwidth from 32 GB of GDDR7 on a 512-bit bus, while the A380E x2 offers 186.0 GB/s from 6 GB of GDDR6 on a 96-bit bus.

Q: How do the power requirements compare?

A: The RTX 5090 D has a 575 W TDP and requires a 950 W suggested power supply, while the A380E x2 has a 130 W TDP and needs a 300 W suggested power supply.

Q: Does the RTX 5090 D outperform its nearest rivals?

A: The database shows the RTX 5090 D is 1.1% ahead of the AMD Radeon RX 6650M XT but 1.6% behind the AMD Radeon RX 6850M XT, 2.1% behind the NVIDIA Tesla P100 PCIe 12 GB, and 2.4% behind the Tesla P100 PCIe 16 GB.

Q: What display outputs does each card offer?

A: The A380E x2 provides eight mini-DisplayPort 2.0 outputs, while the RTX 5090 D offers one HDMI 2.1b and three DisplayPort 2.1b outputs.

Q: Which card has tensor cores?

A: The RTX 5090 D includes 680 tensor cores, while the Intel Arc A380E x2 lists no tensor core count.

Architecture Differences

The Intel Arc A380E x2 uses the DG2-128 chip built on the Xe-HPG architecture, specifically the Alchemist generation for Arc 3 products. This chip is fabricated on a 6 nm process at TSMC, containing 7,200 million transistors on a 157 mm² die, giving a transistor density of 45.9M per mm². The NVIDIA GeForce RTX 5090 D uses the GB202 chip with Blackwell 2.0 architecture from the GeForce 50 series, built on a 5 nm TSMC process. This larger chip holds 92,200 million transistors across a 750 mm² die, achieving a density of 122.9M per mm². The transistor count difference stands at 12.8x in favor of NVIDIA, while the die area is 4.8x larger.

The ray tracing cores differ substantially, with the RTX 5090 D carrying 170 RT cores against 8 for the A380E x2. Tensor cores appear only on the NVIDIA side at 680 units. Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API compatibility does not separate them. The memory types also differ: GDDR7 for NVIDIA and GDDR6 for Intel, with respective effective speeds of 28 Gbps and 15.5 Gbps. The memory clock for the RTX 5090 D is listed at 1750 MHz, while the A380E x2 runs at 1937 MHz, though the wider bus and newer memory type give NVIDIA the bandwidth advantage.

The FP16 ratio differs as well, with the RTX 5090 D achieving 104.8 TFLOPS at a 1:1 ratio, while the A380E x2 reaches 8.192 TFLOPS at a 2:1 ratio. This means the NVIDIA card does not halve its FP16 throughput, while the Intel card does. The pixel and texture rates follow the same pattern, with the RTX 5090 D delivering 423.6 GPixel/s and 1,636.8 GTexel/s against 64.00 GPixel/s and 128.0 GTexel/s for the Intel part.

Specification Differences

The core clock speeds show a narrow gap: the A380E x2 runs at 2000 MHz for both base and boost, while the RTX 5090 D has a 2017 MHz base and 2407 MHz boost. The boost clock difference of 407 MHz favors NVIDIA, though the base clocks sit nearly identical. Memory size differs at 32 GB versus 6 GB, and the bus width shows 512 bit versus 96 bit. The bandwidth gap reaches 1.79 TB/s versus 186.0 GB/s, a 9.6x difference.

Power delivery uses a single 6-pin connector on the Intel card and a single 16-pin connector on the NVIDIA card. The slot width differs at single-slot versus dual-slot, and the dimensions show the Intel card is shorter, narrower, and thinner. The bus interface moves from PCIe 4.0 x8 to PCIe 5.0 x16. The RTX 5090 D lists a launch MSRP of 2,299 USD, while the A380E x2 has no recorded MSRP. The production status shows end-of-life for Intel and active for NVIDIA, with release dates of 2024-03-31 and 2025-01-29 respectively. The predecessor and successor fields also differ: Xe Graphics to Battlemage for Intel, and GeForce 40 to GeForce 60 for NVIDIA.