AMD Radeon Instinct MI60 vs Intel Arc Pro A60 Comparison

Where Each One Wins

The AMD Radeon Instinct MI60 and Intel Arc Pro A60 occupy very different positions in the recorded benchmark data, and the split is decisive. Across the two head-to-head tests in the database, the AMD card wins both. In Geekbench OpenCL, the MI60 posts 92,488 against the Arc Pro A60's 63,485, a 45.7% advantage. In Geekbench Vulkan, the gap widens to 61.7%, with the AMD part scoring 92,444 versus 57,166. That means the MI60 is the clear compute-oriented winner, particularly in workloads that lean on Vulkan, where its lead is most pronounced.

The Intel Arc Pro A60, however, is not without a role. It is an active, current production part, whereas the MI60 is end-of-life. It is also a single-slot card with a 130 W TDP, compared to the dual-slot, 300 W MI60, so it fits into denser chassis and lower-power systems. The Arc Pro A60 also offers four DisplayPort 2.0 outputs, while the MI60 has a single mini-DisplayPort 1.4a, making the Intel card the more practical choice for multi-display professional setups. The data does not show the Intel part winning any compute benchmark, but its architectural feature set, including 16 ray-tracing cores and DirectX 12 Ultimate support, suggests a different intended workload profile.

In terms of the broader database rankings, the MI60 sits at the 93rd percentile of all GPUs, while the Arc Pro A60 sits at the 88th percentile. That is a meaningful separation, but not an enormous one. The MI60's average benchmark score is 92,466, while the Arc Pro A60's is 60,326. The AMD card is roughly 53% higher on average, which aligns with the head-to-head deltas. The Intel part's closest rival in the database is the NVIDIA GeForce RTX 4090, with a delta of 0%, meaning the Arc Pro A60 and the RTX 4090 record essentially identical average scores in this dataset. That is a striking data point, though it likely reflects the specific mix of OpenCL and Vulkan workloads captured. The MI60, by comparison, sits 0.9% above the NVIDIA RTX A4500 and 1.5% above the RTX A4500 Mobile, while trailing the AMD Radeon Pro VII by 4.8% and the AMD Radeon RX 7900M by 5.2%.

Architecture Differences

The two cards come from fundamentally different design philosophies. The AMD Radeon Instinct MI60 uses the Vega 20 chip built on GCN 5.1 architecture, fabricated on a 7 nm TSMC process. It packs 13,230 million transistors into a 331 mm² die, for a transistor density of 40.0M per mm². The Intel Arc Pro A60 uses the DG2-256 chip on Xe-HPG architecture, fabricated on a 6 nm TSMC process. It contains 11,500 million transistors on a 269 mm² die, yielding a higher density of 42.8M per mm². So despite being a smaller chip, the Intel part is more densely packed.

Memory architecture is another major divergence. The MI60 uses 32 GB of HBM2 on a 4096-bit bus, delivering 1.02 TB/s of bandwidth. The Arc Pro A60 uses 12 GB of GDDR6 on a 192-bit bus, delivering 384.0 GB/s. That is a nearly threefold bandwidth advantage for the AMD card, which is a central reason for its compute lead. The MI60's memory clock is listed as 1000 MHz with 2 Gbps effective, while the Arc Pro A60 runs at 2000 MHz with 16 Gbps effective, but the bus width difference overwhelms the per-pin speed advantage.

Compute resources also differ sharply. The MI60 has 4096 shading units, 256 TMUs, and 64 ROPs. The Arc Pro A60 has 2048 shading units, 128 TMUs, and 64 ROPs. The AMD card has exactly twice the shading units and TMUs, while ROP counts match. The MI60 has no ray-tracing cores, while the Arc Pro A60 includes 16. Neither card lists tensor cores. Pixel rates are close, with the MI60 at 115.2 GPixel/s and the Arc Pro A60 at 131.2 GPixel/s, the Intel card actually ahead here due to its higher boost clock. Texture rate reverses: the MI60 achieves 460.8 GTexel/s versus 262.4 GTexel/s for the Arc Pro A60.

Clock behavior also differs. The MI60 has a 1200 MHz base and 1800 MHz boost. The Arc Pro A60 has a 900 MHz base but boosts to 2050 MHz, a much higher ceiling. FP32 output reflects the shader and clock combination: the MI60 delivers 14.75 TFLOPS, while the Arc Pro A60 delivers 8.397 TFLOPS. FP16 figures scale similarly, with the MI60 at 29.49 TFLOPS and the Arc Pro A60 at 16.79 TFLOPS, both at 2:1 ratios.

API support shows a generational split. The MI60 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3. The Arc Pro A60 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. That newer API profile, plus the ray-tracing cores, makes the Intel part more aligned with modern graphics features, even if raw compute throughput is lower.

Head-to-Head Benchmarks

The database records two direct comparisons. In Geekbench OpenCL, the AMD Radeon Instinct MI60 scores 92,488 against the Intel Arc Pro A60's 63,485. The delta is 45.7% in favor of AMD. That is a substantial margin, and it fits the architectural picture: the MI60 has double the shading units and nearly three times the memory bandwidth. OpenCL workloads that scale with shader count and memory throughput would naturally favor the AMD part.

In Geekbench Vulkan, the MI60 scores 92,444 against 57,166 for the Arc Pro A60. The delta here is 61.7%, an even larger gap. The MI60's Vulkan score is almost identical to its OpenCL score, while the Arc Pro A60's Vulkan score drops by about 10% relative to its own OpenCL result. That suggests the Intel card is less competitive in the Vulkan test specifically, and the combined effect makes the AMD card's lead more than 50% larger in Vulkan than in OpenCL.

Looking at the nearest rivals in the database adds context. The MI60's average score of 92,466 puts it just 0.9% above the NVIDIA RTX A4500 and 1.5% above the RTX A4500 Mobile. It trails the AMD Radeon Pro VII by 4.8% and the AMD Radeon RX 7900M by 5.2%. So while the MI60 beats the Arc Pro A60 decisively, it is not at the top of its own peer group. The Arc Pro A60's average score of 60,326 is essentially tied with the NVIDIA GeForce RTX 4090 in this dataset, showing a delta of 0%, and it sits 0.3% above the AMD Radeon Pro Vega 48. It trails the AMD Radeon Pro W6600M by 2.5% and beats the AMD Radeon PRO V710 by 2.8%.

The pattern is clear: the MI60 wins both recorded head-to-head tests by wide margins, and its nearest rivals are mid-to-high-range professional cards. The Arc Pro A60, despite its lower absolute scores, lands in a competitive cluster of its own, separated by just a few percentage points from several other GPUs. Its delta of 0% against the RTX 4090 is the most notable single data point in its profile, though it should not be read as a claim of general parity, only equivalence in the recorded average score.

Specification Differences

The two cards differ across nearly every major specification field. The MI60 uses a 7 nm process, the Arc Pro A60 a 6 nm process, both from TSMC. Transistor counts are 13,230 million versus 11,500 million, and die sizes are 331 mm² versus 269 mm². Transistor density is 40.0M per mm² for AMD and 42.8M per mm² for Intel.

Clocks: the MI60 has a 1200 MHz base and 1800 MHz boost, while the Arc Pro A60 has a 900 MHz base and 2050 MHz boost. Memory clocks are 1000 MHz (2 Gbps effective) for AMD and 2000 MHz (16 Gbps effective) for Intel.

Memory: 32 GB HBM2 on a 4096-bit bus with 1.02 TB/s bandwidth versus 12 GB GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth.

Compute units: 4096 shading units, 256 TMUs, and 64 ROPs for the MI60; 2048 shading units, 128 TMUs, and 64 ROPs for the Arc Pro A60. The Intel card has 16 ray-tracing cores; the AMD card has none.

Rates: pixel rate is 115.2 GPixel/s for AMD and 131.2 GPixel/s for Intel. Texture rate is 460.8 GTexel/s for AMD and 262.4 GTexel/s for Intel. FP32 is 14.75 TFLOPS versus 8.397 TFLOPS. FP16 is 29.49 TFLOPS versus 16.79 TFLOPS, both at 2:1.

Power and physical: TDP is 300 W for AMD and 130 W for Intel. The MI60 is dual-slot with a 1x 6-pin plus 1x 8-pin power connector setup and a 700 W suggested PSU. The Arc Pro A60 is single-slot with no power connectors listed and a 300 W suggested PSU. The MI60 is 267 mm long and 111 mm tall; the Arc Pro A60 has no dimensions recorded.

Display outputs: the MI60 has one mini-DisplayPort 1.4a; the Arc Pro A60 has four DisplayPort 2.0 outputs. Both use PCIe 4.0 x16.

API support: DirectX 12 (12_1) versus DirectX 12 Ultimate (12_2), OpenGL 4.6 on both, Vulkan 1.3 versus Vulkan 1.4.

Production status: the MI60 is end-of-life, released in November 2018; the Arc Pro A60 is active, released in June 2023. The MI60's predecessor is FirePro Data Center; the Arc Pro A60 has no predecessor listed. Neither has a successor listed.

FAQ

Q: Which GPU is faster in the recorded benchmarks?

A: The AMD Radeon Instinct MI60 wins both head-to-head tests. It scores 92,488 in Geekbench OpenCL versus 63,485 for the Intel Arc Pro A60, and 92,444 in Geekbench Vulkan versus 57,166.

Q: How large is the performance gap between the two cards?

A: The MI60 leads by 45.7% in OpenCL and 61.7% in Vulkan. Its average benchmark score is 92,466, while the Arc Pro A60 averages 60,326.

Q: Does the Intel Arc Pro A60 have any advantages over the MI60?

A: Yes. The Arc Pro A60 is a single-slot card with a 130 W TDP and no power connectors listed, versus the dual-slot, 300 W MI60 with a 1x 6-pin plus 1x 8-pin setup. It also has four DisplayPort 2.0 outputs, 16 ray-tracing cores, DirectX 12 Ultimate support, and a higher boost clock of 2050 MHz.

Q: How do the memory configurations compare?

A: The MI60 has 32 GB of HBM2 on a 4096-bit bus with 1.02 TB/s bandwidth. The Arc Pro A60 has 12 GB of GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth.

Q: How does each card compare to its nearest rivals in the database?

A: The MI60 sits 0.9% above the NVIDIA RTX A4500 and 1.5% above the RTX A4500 Mobile, while trailing the AMD Radeon Pro VII by 4.8% and the AMD Radeon RX 7900M by 5.2%. The Arc Pro A60 is tied with the NVIDIA GeForce RTX 4090 at 0% delta, sits 0.3% above the AMD Radeon Pro Vega 48, trails the AMD Radeon Pro W6600M by 2.5%, and beats the AMD Radeon PRO V710 by 2.8%.

Q: Which card should be chosen for compute-heavy workloads?

A: The recorded data points to the MI60. Its double shader count, 1.02 TB/s memory bandwidth, and 14.75 TFLOPS FP32 throughput give it a decisive edge in both OpenCL and Vulkan tests. The Arc Pro A60's advantages are in power, size, display outputs, and modern graphics features, not raw compute performance.