AMD Radeon 890M vs Intel Arc A380E x2 Comparison

Head-to-Head Benchmarks

The AMD Radeon 890M and the Intel Arc A380E x2 present a unique comparison challenge because the database holds a complete benchmark profile for one part and no direct measurements for the other. The 890M has recorded scores across ten separate tests, while the A380E x2 has no individual test results in the database. This asymmetry means the head-to-head analysis must rely on the 890M's absolute scores and its percentile position to establish a baseline, then compare that baseline against the A380E x2's aggregate ranking.

The 890M's strongest recorded result comes from Geekbench Vulkan, where it scores 40,808 points. Its Geekbench OpenCL result is close behind at 37,254 points, indicating that the Vulkan API path delivers roughly 9.5% higher throughput than OpenCL in that benchmark. In the Passmark suite, the 890M produces a G3D score of 8,076 and a G2D score of 979. The compute-oriented Passmark GPU Compute test yields 4,157 points. The DirectX legacy tests show a wide spread: DirectX 9 scores 97, DirectX 11 scores 73, DirectX 12 scores 37, and DirectX 10 scores 33. The 3DMark Steel Nomad DX12 test records 590 points.

Because the A380E x2 has no benchmark entries, the database assigns it an average benchmark score of zero, which is not a meaningful performance figure. However, the database does place the A380E x2 at the 50th percentile among all GPUs, while the 890M sits at the 45th percentile. That five-point percentile gap indicates the A380E x2 ranks slightly higher in the overall distribution despite lacking measured scores. The 890M's average benchmark score across all tests is 9,210 points.

The nearest rivals for the 890M provide context for its standing. The AMD Radeon Vega 8 averages 9,221 points, which is 0.1% higher than the 890M's average. The NVIDIA GeForce GTX 960 averages 9,273 points, 0.7% higher. The NVIDIA GeForce GTX 465 averages 9,294 points, 0.9% higher. The NVIDIA GeForce GTX 850M averages 9,302 points, 1% higher. The 890M trails all four nearest rivals by margins under one percentage point, which places it in a tightly packed performance cluster.

The A380E x2 has no nearest rival entries in the database, so no direct delta comparisons exist for it. The only available comparative signal is the percentile gap: the A380E x2 at the 50th percentile versus the 890M at the 45th percentile. That difference suggests the Intel part sits slightly higher in the global ranking, but without test scores the magnitude of any performance advantage cannot be quantified from the recorded data.

Where Each One Wins

The AMD Radeon 890M wins in every category where the database contains measurable performance data, simply because it is the only one of the two with recorded benchmark scores. Its compute throughput is substantial for an integrated part: 5.939 TFLOPS FP32 and 5.939 TFLOPS FP16 with a 1:1 ratio. The pixel rate reaches 92.80 GPixel/s and the texture rate reaches 185.6 GTexel/s. These figures give the 890M a clear advantage in any workload that relies on raw shader throughput, texturing, or pixel fill.

The Intel Arc A380E x2 wins in categories that are structural rather than benchmark-derived. It sits at the 50th percentile versus the 890M's 45th, which is the only recorded metric where the Intel part leads. The A380E x2 also has dedicated memory, 6 GB of GDDR6 on a 96-bit bus delivering 186.0 GB/s of bandwidth, whereas the 890M uses system shared memory with bandwidth described as system dependent. For workloads that are sensitive to memory bandwidth and capacity, the A380E x2's dedicated frame buffer is a functional advantage, even though the database contains no direct benchmark to confirm its magnitude.

The 890M has 16 ray tracing cores to the A380E x2's 8, so the AMD part has twice the ray tracing hardware count. The 890M also has a higher boost clock at 2,900 MHz versus the A380E x2's fixed 2,000 MHz. The FP32 throughput advantage for the 890M is about 45% higher (5.939 TFLOPS versus 4.096 TFLOPS). The texture rate advantage is also significant: 185.6 GTexel/s versus 128.0 GTexel/s, a 45% lead. The pixel rate advantage is 92.80 GPixel/s versus 64.00 GPixel/s, a 45% lead as well.

The A380E x2 counters with FP16 throughput that is higher in raw terms: 8.192 TFLOPS with a 2:1 ratio, compared to the 890M's 5.939 TFLOPS at 1:1. For workloads that can use FP16 packed math, the Intel part delivers 38% more FP16 compute. The A380E x2 also has a much higher TDP at 130 W versus the 890M's 15 W, which reflects its discrete card design with a single-slot cooler, a 6-pin power connector, and a suggested power supply of 300 W.

The 890M uses a 4 nm process node with 34,000 million transistors on a 233 mm² die, giving a transistor density of 145.9 million per mm². The A380E x2 uses a 6 nm node with 7,200 million transistors on a 157 mm² die, a density of 45.9 million per mm². The AMD part integrates three times the transistor count in a larger die with a much smaller power envelope.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon 890M has an average benchmark score of 9,210 points. The Intel Arc A380E x2 has no recorded benchmark scores, so its average is listed as zero in the database.

Q: How does the 890M compare to its nearest rivals?

A: The 890M trails the AMD Radeon Vega 8 by 0.1%, the NVIDIA GeForce GTX 960 by 0.7%, the NVIDIA GeForce GTX 465 by 0.9%, and the NVIDIA GeForce GTX 850M by 1% in average benchmark score.

Q: What are the 890M's best and worst recorded benchmark results?

A: Its best result is a Geekbench Vulkan score of 40,808, followed by a Geekbench OpenCL score of 37,254. Its weakest results are Passmark DirectX 10 at 33 and Passmark DirectX 12 at 37.

Q: Does the A380E x2 have any performance advantage over the 890M?

A: The A380E x2 sits at the 50th percentile among all GPUs, while the 890M sits at the 45th percentile. It also has 6 GB of dedicated GDDR6 memory with 186.0 GB/s bandwidth, compared to the 890M's system shared memory.

Q: How do the two GPUs compare in ray tracing hardware?

A: The AMD Radeon 890M has 16 ray tracing cores, while the Intel Arc A380E x2 has 8, giving the AMD part twice the ray tracing core count.

Q: Which GPU has higher FP16 compute throughput?

A: The Intel Arc A380E x2 delivers 8.192 TFLOPS FP16 with a 2:1 ratio, which is higher than the 890M's 5.939 TFLOPS FP16 at a 1:1 ratio.

Specification Differences

The AMD Radeon 890M is an integrated graphics processor with a 15 W TDP, no power connectors, and an IGP slot width. The Intel Arc A380E x2 is a single-slot discrete card with a 130 W TDP, one 6-pin power connector, and a suggested power supply of 300 W. The 890M's base clock is 400 MHz with a boost clock of 2,900 MHz. The A380E x2 runs at a fixed 2,000 MHz for both base and boost. Memory differs fundamentally: the 890M uses system shared memory with system dependent bandwidth, while the A380E x2 has 6 GB of GDDR6 on a 96-bit bus with 186.0 GB/s bandwidth and a 1,937 MHz memory clock at 15.5 Gbps effective.

The physical dimensions differ as well. The A380E x2 measures 265 mm in length, 127 mm in height, and 20 mm in width. The 890M has no recorded dimensions because it is an IGP. Display outputs differ: the 890M is portable device dependent, while the A380E x2 provides 8x mini-DisplayPort 2.0 outputs. The production status also differs: the 890M is active, while the A380E x2 is end-of-life with a successor named Battlemage. The 890M's predecessor is Navi II IGP, and the A380E x2's predecessor is Xe Graphics.

The 890M has a pixel rate of 92.80 GPixel/s, a texture rate of 185.6 GTexel/s, and FP32 of 5.939 TFLOPS. The A380E x2 has a pixel rate of 64.00 GPixel/s, a texture rate of 128.0 GTexel/s, and FP32 of 4.096 TFLOPS. Both parts share the same shading unit count of 1,024, the same TMU count of 64, and the same ROP count of 32. Both use a PCIe 4.0 x8 bus interface. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The release dates differ by roughly three and a half months. The A380E x2 launched on 2024-03-31, and the 890M launched on 2024-07-14. Neither part has a recorded launch MSRP in the database.

Architecture Differences

The AMD Radeon 890M uses the RDNA 3.5 architecture and is built on a 4 nm process at TSMC. Its transistor count is 34,000 million on a 233 mm² die, with a transistor density of 145.9 million per mm². The chip is Strix Point, and the generation is listed as Navi III IGP for Strix Point Mobile. The Intel Arc A380E x2 uses the Xe-HPG architecture, built on a 6 nm process at TSMC. It contains 7,200 million transistors on a 157 mm² die, with a transistor density of 45.9 million per mm². The chip is DG2-128, and the generation is Alchemist Arc 3.

The process node difference is significant: 4 nm versus 6 nm. The 890M packs nearly five times the transistor count into a die that is only about 48% larger by area, resulting in a transistor density roughly 3.2 times higher. The 890M's FP16 execution runs at a 1:1 ratio with FP32, meaning it does not double-rate FP16 operations. The A380E x2 runs FP16 at a 2:1 ratio, doubling its FP16 throughput to 8.192 TFLOPS while its FP32 stays at 4.096 TFLOPS.

Ray tracing hardware differs by a factor of two: the 890M has 16 RT cores, the A380E x2 has 8. Both parts share identical shading unit, TMU, and ROP counts. The 890M's boost clock reaches 2,900 MHz, which is 45% higher than the A380E x2's fixed 2,000 MHz clock. The 890M's memory architecture is fully shared with the system, with no dedicated VRAM, while the A380E x2 uses dedicated GDDR6. The 890M's power envelope is 15 W, versus 130 W for the A380E x2, a difference that reflects the integrated versus discrete design philosophy. The 890M has no power connectors and no slot width beyond IGP, while the A380E x2 requires a single slot, a 6-pin connector, and a 300 W power supply.