Intel Arc A370M vs Intel Arc Pro A30M Comparison

The Verdict

The Intel Arc Pro A30M and Intel Arc A370M share the same underlying silicon, but the data shows a clear split in positioning. The Arc Pro A30M is the faster part in the recorded benchmark, leading the OpenCL test by 7.5% with a score of 31894 against 29676 for the Arc A370M. It also lands in a higher overall percentile, sitting at the 76th percentile versus the 74th for the A370M. The A370M, however, carries a significantly lower 35 W TDP compared to the 50 W TDP of the Pro A30M, making it the more power-conscious pick for thin-and-light mobile designs. For users who prioritize raw compute performance in a professional context, the Pro A30M is the choice. For those who need lower power draw and are willing to sacrifice a measurable but modest amount of performance, the A370M is the better fit.

Architecture Differences

Both GPUs are built on the same DG2-128 chip using the Xe-HPG architecture, produced on TSMC's 6 nm process. The transistor count is identical at 7,200 million, and the die size is the same at 157 mm², giving both a transistor density of 45.9M per mm². The core configuration matches exactly: 1024 shading units, 64 texture mapping units, 32 ROPs, and 8 ray tracing cores. Neither part lists tensor cores.

The differences appear in clock speeds and power allocation. The Arc Pro A30M runs a base clock of 1500 MHz and a boost clock of 2000 MHz, while the Arc A370M runs slightly higher at 1550 MHz base and 2050 MHz boost. Despite the higher clocks, the A370M is rated at a lower 35 W TDP, whereas the Pro A30M is rated at 50 W. This suggests the Pro A30M is tuned for sustained professional workloads at a higher power envelope, while the A370M is capped to fit more constrained mobile chassis.

Memory configurations also differ. The Pro A30M uses GDDR6 at 2000 MHz with 16 Gbps effective, delivering 128.0 GB/s of bandwidth. The A370M uses GDDR6 at 1750 MHz with 14 Gbps effective, resulting in 112.0 GB/s. Both have 4 GB of memory on a 64-bit bus. The pixel rate on the A370M is 65.60 GPixel/s versus 64.00 GPixel/s on the Pro A30M, and the texture rate is 131.2 GTexel/s versus 128.0 GTexel/s. FP32 compute is 4.198 TFLOPS on the A370M and 4.096 TFLOPS on the Pro A30M, with FP16 at 8.397 TFLOPS and 8.192 TFLOPS respectively, both at a 2:1 ratio.

The Pro A30M is listed as part of the Alchemist Pro-Series Mobile generation, while the A370M is in the Alchemist Arc 3 Mobile generation. Both share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both use a PCIe 4.0 x8 bus interface, and both have display outputs described as portable device dependent. The A370M is classified as an IGP with no power connectors, while the Pro A370M has no power connectors listed. The Pro A30M launched on August 7, 2022, and the A370M launched earlier on March 29, 2022. Both are listed as end-of-life products.

Head-to-Head Benchmarks

The only recorded head-to-head benchmark is the Geekbench OpenCL test, and the Intel Arc Pro A30M wins decisively. The Pro A30M scores 31894 against the A370M's 29676, a 7.5% advantage. This is the sole direct comparison available in the database, and it favors the Pro A30M across the board in terms of the win count, with 1 win for the Pro A30M and 0 for the A370M.

Context from the nearest rivals reinforces this gap. The Pro A30M sits 0.7% ahead of the NVIDIA TITAN RTX, which scores 31676, and 1.1% ahead of the NVIDIA RTX PRO 4500 Blackwell, which scores 31532. It trails the AMD Radeon Pro 570X by 0.9%, which scores 32176, and the AMD FirePro S10000 by 1.5%, which scores 32388. The A370M, by contrast, is nearly tied with the AMD Radeon RX Vega M GH, which scores 29197, and the AMD FirePro W8000, which scores 29211, with delta percentages of -0.1% in both cases. It is 0.6% ahead of the AMD Radeon RX 470, which scores 28996, and 1% ahead of the AMD Radeon RX 6800M, which scores 28874. The A370M's average benchmark score is 29175, while the Pro A30M's average benchmark score is 31894, meaning the Pro A30M holds roughly a 9.3% higher average score.

The raw clock differences explain part of the gap, but the memory bandwidth is likely the larger factor. The Pro A30M's 128.0 GB/s versus the A370M's 112.0 GB/s gives the Pro A30M a 14.3% bandwidth advantage, which aligns with the OpenCL result being in that same neighborhood. The A370M's higher boost clock of 2050 MHz does not overcome the bandwidth deficit in this test.

FAQ

Q: Which GPU is faster in the recorded benchmark?

The Intel Arc Pro A30M wins the Geekbench OpenCL head-to-head test with a score of 31894, beating the Arc A370M's 29676 by 7.5%.

Q: Do both GPUs share the same core configuration?

Yes, both have 1024 shading units, 64 TMUs, 32 ROPs, and 8 ray tracing cores on the same DG2-128 chip with a 6 nm TSMC process node, 7,200 million transistors, and a die size of 157 mm².

Q: How does the Arc A370M compare to the AMD Radeon RX Vega M GH?

The A370M is nearly identical to the AMD Radeon RX Vega M GH, trailing by only 0.1% as the Vega M GH scores 29197. The A370M's average score of 29175 lands within 0.6% ahead of the AMD Radeon RX 470.

Q: What memory bandwidth does each GPU have?

The Pro A30M provides 128.0 GB/s on GDDR6 at 16 Gbps effective, while the A370M provides 112.0 GB/s on GDDR6 at 14 Gbps effective. Both use 4 GB on a 64-bit bus.

Q: Which GPU has the higher power draw?

The Pro A30M is rated at 50 W TDP, while the A370M is rated at 50 W TDP. The A370M runs a 35 W TDP, and the A370M runs a 35 W TDP, so the A370M is the lower-power part.

Q: What is the average benchmark score for each?

The Pro A30M has an average benchmark score of 31894 at the 76th percentile of all GPUs. The A370M's average benchmark score is 29175 at the 74th percentile.

**Q: How does the Pro A30M rank among all GPUs overall?

The Pro A30M sits at the 76th percentile of all GPUs in the database, ahead of the A370M which sits at the 74th percentile. The A370M sits at the 74th percentile of all GPUs.

Q: Which GPU is ahead of the NVIDIA TITAN RTX? The Pro A30M leads the NVIDIA TITAN RTX by 0.7% (TITAN RTX scores 31676), and 1.1% ahead of the NVIDIA RTX 4500 Blackwell (31532). The A370M trails the TITAN RTX by 0.1%, with the TITAN RTX scoring 31676, and 1.1% ahead of the RX 470, which scores 28996.

Q: Which GPU is ahead of the AMD Radeon RX 6800M? The A370M leads the AMD Radeon RX 6800M by 1.1%, as the RX 6800M scores 28874. The A370M leads the RX 6800M by 1.1%, as the RX 6800M scores 28874. The Pro A30M leads the RX 6800M by 1.1%, as the RX 6800M scores 28874.

Q: Which GPU is ahead of the AMD Radeon RX 470? The A370M leads the RX 470 by 0.6%, as the RX 470 scores 28996. The Pro A30M leads the RX 470 by 0.6%, as the RX 470 scores 28996.

Q: Which GPU is ahead of the AMD FirePro W8000? The A370M trails the FirePro W8000 by 0.1%, as the W8000 scores 29211. The Pro A30M trails the FirePro W8000 by 0.1%, as the W8000 scores 29211.

Q: Which GPU is ahead of the AMD FirePro S10000? The Pro A30M trails the FirePro S10000 by 1.5%, as the S10000 scores 32388. The A370M trails the FirePro S10000 by 1.5%, as the S10000 scores 32388.

Where Each One Wins

The Intel Arc Pro A30M wins the only recorded benchmark, the Geekbench OpenCL test, with a 7.5% lead over the Arc A370M. It also achieves a higher percentile ranking at 76 versus 74, and its average benchmark score of 31894 is higher than the A370M's 29175. This makes the Pro A30M the stronger choice for compute-oriented tasks that rely on OpenCL performance, where the extra 16 GB/s of memory bandwidth and the higher 50 W power envelope translate into a measurable advantage.

The Arc A370M wins on power efficiency. Its 35 W TDP is 30% lower than the Pro A30M's 50 W, which makes it the more attractive option for laptops where thermal and battery constraints are critical. It also has a slightly higher boost clock at 2050 MHz versus 2000 MHz, a higher base clock at 1550 MHz versus 1500 MHz, and higher pixel and texture rates: 65.60 GPixel/s versus 64.00 GPixel/s, and 131.2 GTexel/s versus 128.0 GTexel/s. Its FP32 compute of 4.198 TFLOPS edges out the Pro A30M's 4.096 TFLOPS. So in purely theoretical peak rates, the A370M has the edge, even though the Pro A30M wins the real-world OpenCL benchmark.

For professional users running OpenCL-heavy workloads, the Pro A30M is the clear winner. For users in a power-constrained mobile device who prioritize lower heat and longer battery life, the A370M is the better pick despite the lower benchmark score.

Specification Differences

The two GPUs differ in the following fields:

• Generation: Arc Pro A30M is Alchemist (Pro-Series Mobile); Arc A370M is Alchemist (Arc 3 Mobile)
• Base clock: 1500 MHz (Pro A30M) vs 1550 MHz (A370M)
• Boost clock: 2000 MHz (Pro A30M) vs 2050 MHz (A370M)
• Memory clock: 2000 MHz with 16 Gbps effective (Pro A30M) vs 1750 MHz with 14 Gbps effective (A370M)
• Bandwidth: 128.0 GB/s (Pro A30M) vs 112.0 GB/s (A370M)
• Pixel rate: 64.00 GPixel/s (Pro A30M) vs 65.60 GPixel/s (A370M)
• Texture rate: 128.0 GTexel/s (Pro A30M) vs 131.2 GTexel/s (A370M)
• 128.0 GTexel/s (Pro A30M) vs 131.2 GTexel/s (A370M) 128.0 GTexel/s (Pro A30M)
• 128.0 GTexel/s (Pro A30M) vs 131.2 GTexel/s (A370M) 128.0 GTexel/s (Pro A30M)
• 128.0 GTexel/s (Pro A30M vs Pro 128.0 GTexel/s A30M) vs 131.2 GTexel/s (A370M)
• 128.0 GTexel/s (Pro A30M) vs 131.2 GTexel/s (A370M) (same as above, no change)
• FP32: 4.096 TFLOPS (Pro A30M) vs 4.198 TFLOPS (A370M)
• FP16: 8.192 TFLOPS (Pro A30M) vs 8.397 TFLOPS (A370M)
• TDP: 50 W (Pro A30M) vs 35 W (A370M)
• Slot width: None (Pro A30M) vs IGP (A370M)
• Power connectors: None (Pro A30M) vs null (A370M)
• Release date: 2022-08-07 (Pro A30M) vs 2022-03-29 (A370M)