AMD Radeon RX 6600 LE vs Intel Arc A380E x2 Comparison

Head-to-Head Benchmarks

The database contains benchmark scores for the AMD Radeon RX 6600 LE under two API tests: Geekbench OpenCL and Geekbench Vulkan. The Intel Arc A380E x2 has no recorded benchmark scores in the database, which makes direct numerical comparison impossible for compute workloads. The RX 6600 LE scores 69,229 points in OpenCL and 72,428 points in Vulkan. Its average benchmark score across recorded tests is 70,829.

The RX 6600 LE sits at the 91st percentile among all GPUs in the database, while the Arc A380E x2 sits at the 50th percentile. This percentile gap indicates that the AMD part outperforms the majority of recorded GPUs, whereas the Intel part lands at the median. With no benchmarks for the Arc A380E x2, the database cannot assign it an average score, and it has no nearest rivals listed.

For the RX 6600 LE, the nearest rivals provide context for its average score. The AMD Radeon RX 6650M averages 71,768 points, which is 1.3% higher than the RX 6600 LE. The NVIDIA RTX A3000 Mobile averages 70,140 points, 1% lower. The NVIDIA Quadro P6000 averages 69,986 points, 1.2% lower. The AMD Radeon Pro WX 8200 averages 69,870 points, 1.4% lower. The RX 6600 LE therefore sits within roughly 1.4% of a cluster of professional and mobile GPUs, with the RX 6650M as the closest outperformer.

The Arc A380E x2 has zero recorded wins in the head-to-head table, as does the RX 6600 LE. The absence of benchmark data for the Intel card means the head-to-head comparison relies on architectural and specification differences rather than measured performance.

Where Each One Wins

The AMD Radeon RX 6600 LE wins in every measurable compute category because it has recorded scores and the Intel Arc A380E x2 has none. In OpenCL, the RX 6600 LE delivers 69,229 points. In Vulkan, it delivers 72,428 points. These scores indicate strong compute throughput for a GPU in the 91st percentile.

The Arc A380E x2 cannot claim any benchmark wins from the database. Its percentile rank of 50 places it at the median of all GPUs, but without scores, there is no way to quantify its position relative to the RX 6600 LE. The database shows the RX 6600 LE as the only part with a meaningful performance profile.

For use-case splits, the RX 6600 LE clearly favors Vulkan over OpenCL based on its recorded scores. The 72,428 Vulkan result is 3,199 points higher than the OpenCL result, a 4.6% advantage. This suggests the architecture handles Vulkan workloads slightly better in the measured tests. The Arc A380E x2 has no such split because no data exists.

The RX 6600 LE also wins on memory capacity and bandwidth. It has 8 GB of GDDR6 memory on a 128-bit bus, yielding 224.0 GB/s of bandwidth. The Arc A380E x2 has 6 GB of GDDR6 on a 96-bit bus, yielding 186.0 GB/s. The AMD card provides 20.4% more bandwidth, which benefits memory-intensive workloads like high-resolution textures or compute kernels.

FAQ

Q: Does the Intel Arc A380E x2 have any recorded benchmark scores in the database?

A: No. The database lists no benchmarks for the Arc A380E x2, and its average benchmark score is 0.

Q: How does the AMD Radeon RX 6600 LE compare to its nearest rivals in average score?

A: The RX 6600 LE averages 70,829 points. The AMD Radeon RX 6650M is 1.3% higher at 71,768 points. The NVIDIA RTX A3000 Mobile is 1% lower at 70,140 points. The NVIDIA Quadro P6000 is 1.2% lower at 69,986 points. The AMD Radeon Pro WX 8200 is 1.4% lower at 69,870 points.

Q: What is the percentile ranking for each GPU?

A: The RX 6600 LE is at the 91st percentile among all GPUs. The Arc A380E x2 is at the 50th percentile.

Q: Which GPU has more memory bandwidth?

A: The RX 6600 LE has 224.0 GB/s of bandwidth from 8 GB of GDDR6 on a 128-bit bus. The Arc A380E x2 has 186.0 GB/s from 6 GB of GDDR6 on a 96-bit bus.

Q: What are the FP32 compute figures for both GPUs?

A: The RX 6600 LE delivers 8.942 TFLOPS of FP32 performance with 1,792 shading units. The Arc A380E x2 delivers 4.096 TFLOPS with 1,024 shading units.

Q: Are both GPUs rated for the same power supply?

A: Yes, both list a suggested PSU of 300 W. The RX 6600 LE has a TDP of 132 W, and the Arc A380E x2 has a TDP of 130 W.

Specification Differences

The two GPUs differ across nearly every major specification field. The AMD Radeon RX 6600 LE uses the Navi 23 chip on a 7 nm process from TSMC. The Intel Arc A380E x2 uses the DG2-128 chip on a 6 nm process from TSMC. The AMD chip has 11,060 million transistors on a 237 mm² die, while the Intel chip has 7,200 million transistors on a 157 mm² die. Transistor density is similar: 46.7M per mm² for AMD, 45.9M per mm² for Intel.

Clock speeds differ substantially. The RX 6600 LE has a base clock of 1626 MHz, a boost clock of 2495 MHz, and a game clock of 2045 MHz. The Arc A380E x2 has a fixed base and boost clock of 2000 MHz, with no game clock listed. Memory clocks also differ: the AMD card runs at 1750 MHz (14 Gbps effective), while the Intel card runs at 1937 MHz (15.5 Gbps effective). Despite the higher memory clock, the Intel card's narrower 96-bit bus limits its bandwidth.

Memory configuration diverges: the RX 6600 LE uses 8 GB of GDDR6 on a 128-bit bus for 224.0 GB/s, while the Arc A380E x2 uses 6 GB of GDDR6 on a 96-bit bus for 186.0 GB/s. The AMD card has 1,792 shading units, 112 texture mapping units, and 64 ROPs. The Intel card has 1,024 shading units, 64 TMUs, and 32 ROPs. The RX 6600 LE has 28 ray tracing cores; the Arc A380E x2 has 8.

Pixel and texture rates differ accordingly. The RX 6600 LE achieves 159.7 GPixel/s and 279.4 GTexel/s. The Arc A380E x2 achieves 64.00 GPixel/s and 128.0 GTexel/s. The FP32 throughput is 8.942 TFLOPS for AMD versus 4.096 TFLOPS for Intel. FP16 figures are 17.88 TFLOPS (2:1) for AMD and 8.192 TFLOPS (2:1) for Intel.

Physical dimensions and power connectors differ. The RX 6600 LE is a dual-slot card measuring 190 mm by 110 mm by 40 mm, with a single 8-pin power connector. The Arc A380E x2 is a single-slot card measuring 265 mm by 127 mm by 20 mm, with a single 6-pin connector. TDP values are close: 132 W for AMD, 130 W for Intel. Both use PCIe 4.0 x8. Display outputs differ: AMD provides 1x HDMI 2.1 and 3x DisplayPort 1.4a, while Intel provides 8x mini-DisplayPort 2.0.

Production status differs. The RX 6600 LE is listed as Active, while the Arc A380E x2 is End-of-life. Release dates also differ: the AMD card released on 2023-12-07, the Intel card on 2024-03-31.

Architecture Differences

The AMD Radeon RX 6600 LE is built on RDNA 2.0 architecture from the Navi II generation (RX 6000 series). The Intel Arc A380E x2 uses Xe-HPG architecture from the Alchemist generation (Arc 3). Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API feature levels match.

The process node differs: AMD uses 7 nm TSMC, Intel uses 6 nm TSMC. The AMD chip has 11,060 million transistors compared to 7,200 million for Intel. The AMD die is larger at 237 mm² versus 157 mm², but transistor density is nearly identical at 46.7M/mm² versus 45.9M/mm².

Core counts differ by design. The RX 6600 LE has 1,792 shading units, 112 TMUs, and 64 ROPs. The Arc A380E x2 has 1,024 shading units, 64 TMUs, and 32 ROPs. Ray tracing cores number 28 on the AMD card and 8 on the Intel card. Neither card has tensor cores listed. The AMD card supports FP16 at a 2:1 ratio relative to FP32, as does the Intel card.

The memory architecture diverges in bus width and capacity. The AMD card uses a 128-bit bus with 8 GB, the Intel card uses a 96-bit bus with 6 GB. This affects bandwidth (224.0 GB/s versus 186.0 GB/s) despite the Intel card's higher memory clock. The RX 6600 LE has a boost clock 495 MHz higher than the Arc A380E x2's fixed 2000 MHz, which contributes to its higher pixel and texture rates.

The Intel card's display output configuration (8x mini-DisplayPort 2.0) suggests a different target use case compared to the AMD card's mixed HDMI and DisplayPort outputs. The single-slot form factor of the Intel card versus the dual-slot AMD card also indicates different physical design priorities. The Arc A380E x2 lists its predecessor as Xe Graphics and successor as Battlemage, while the RX 6600 LE lists Navi as predecessor and Navi III as successor.

The Verdict

The database shows a clear performance hierarchy between these two GPUs, but only for the AMD part. The AMD Radeon RX 6600 LE records an average benchmark score of 70,829, placing it at the 91st percentile. Its nearest rivals cluster within 1.4% of its score, confirming consistent positioning among mid-range and professional GPUs. The Intel Arc A380E x2 has no recorded benchmarks, an average score of 0, and sits at the 50th percentile. Without measurement data, the Intel card cannot be compared on performance grounds.

For compute workloads, the RX 6600 LE delivers 8.942 TFLOPS of FP32 performance, more than double the Arc A380E x2's 4.096 TFLOPS. The AMD card also provides 8 GB of memory versus 6 GB, and 224.0 GB/s of bandwidth versus 186.0 GB/s. Pixel rate is 159.7 GPixel/s versus 64.00 GPixel/s, and texture rate is 279.4 GTexel/s versus 128.0 GTexel/s. These figures indicate the AMD card handles rasterization and texture-heavy workloads with significantly more throughput.

The Arc A380E x2 offers advantages in physical design. It is a single-slot card at 20 mm width, compared to the dual-slot 40 mm AMD card. It also provides 8x mini-DisplayPort 2.0 outputs, which could suit multi-display installations. The Intel card has a higher memory clock (1937 MHz versus 1750 MHz) and a slightly lower TDP (130 W versus 132 W), but these do not offset the bandwidth disadvantage from the narrower 96-bit bus.

The RX 6600 LE is the only part with measurable performance in this comparison. Its 91st percentile ranking and active production status indicate current relevance. The Arc A380E x2 is end-of-life with no benchmark data, making it unquantifiable in the database. For any workload requiring compute performance, memory bandwidth, or ray tracing throughput, the recorded data favors the AMD card. The Intel card's only clear advantages are form factor and display output count, both qualitative features without performance scores to back them.