AMD Radeon 840M vs Intel Arc B370 Comparison

FAQ

Q: What are the two integrated GPUs compared here?

A: The AMD Radeon 840M is an integrated graphics processor based on the RDNA 3.5 architecture, part of the Krackan Point chip, and belongs to the Navi III IGP generation. The Intel Arc B370 is an integrated GPU using the Xe3-LPG architecture, part of the Panther Lake chip, and belongs to the Arc Graphics-M generation.

Q: Which GPU has a higher boost clock?

A: The AMD Radeon 840M has a boost clock of 2900 MHz, while the Intel Arc B370 boosts to 2400 MHz. The AMD part also has a higher base clock at 400 MHz versus 300 MHz for the Intel part.

Q: How do the shading unit counts compare?

A: The Intel Arc B370 has 1280 shading units, which is five times the 256 shading units found on the AMD Radeon 840M. This substantial difference in compute unit count is a primary factor in the raw throughput gap between the two.

Q: What is the power draw difference?

A: The AMD Radeon 840M has a TDP of 15 W, while the Intel Arc B370 has a TDP of 25 W. Both are integrated parts with no power connectors and a slot width of IGP.

Q: Which GPU has a higher pixel rate and texture rate?

A: The Intel Arc B370 has a pixel rate of 48.00 GPixel/s and a texture rate of 96.00 GTexel/s. The AMD Radeon 840M has a pixel rate of 23.20 GPixel/s and a texture rate of 46.40 GTexel/s, meaning the Intel part roughly doubles both rates.

Q: What is the FP32 compute throughput for each GPU?

A: The Intel Arc B370 delivers 6.144 TFLOPS of FP32 compute, while the AMD Radeon 840M delivers 1,484.8 GFLOPS. The Intel part is approximately four times higher in FP32 throughput, and it also offers FP16 at 12.29 TFLOPS with a 2:1 ratio, whereas the AMD part provides FP16 at 1,484.8 GFLOPS with a 1:1 ratio.

Architecture Differences

The two integrated GPUs come from different architectural lineages and manufacturing processes. The AMD Radeon 840M uses the RDNA 3.5 architecture, fabricated on a 4 nm process at TSMC. The Intel Arc B370 uses the Xe3-LPG architecture, fabricated on a 3 nm process at Intel's own foundry. Both are integrated parts with system-shared memory, meaning the memory size, type, bus width, and bandwidth are all system-dependent rather than fixed specifications.

The compute configuration differs significantly. The AMD Radeon 840M has 256 shading units, 16 texture mapping units, 8 render output units, and 4 ray tracing cores. The Intel Arc B370 has 1280 shading units, 40 texture mapping units, 20 render output units, and 10 ray tracing cores. In every category, the Intel part has higher counts: five times more shading units, 2.5 times more TMUs, 2.5 times more ROPs, and 2.5 times more ray tracing cores.

The FP32 and FP16 throughput reflects this disparity. The AMD part delivers 1,484.8 GFLOPS in both FP32 and FP16, indicating a 1:1 ratio. The Intel part delivers 6.144 TFLOPS in FP32 and 12.29 TFLOPS in FP16, indicating a 2:1 ratio, effectively doubling its FP16 output relative to FP32. The pixel rate and texture rate also scale accordingly: the AMD part reaches 23.20 GPixel/s and 46.40 GTexel/s, while the Intel part reaches 48.00 GPixel/s and 96.00 GTexel/s.

Clock behavior differs between the two. The AMD Radeon 840M has a base clock of 400 MHz and a boost of 2900 MHz. The Intel Arc B370 has a base clock of 300 MHz and a boost of 2400 MHz. Despite lower clock speeds, the Intel part achieves higher throughput due to its much larger execution resource pool.

Both GPUs share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both are listed as Active production status. The AMD part uses a PCIe 4.0 x8 bus interface, while the Intel part's bus interface is listed as IGP. Both have display outputs that are portable device dependent.

Head-to-Head Benchmarks

The recorded data includes one benchmark result for the Intel Arc B370, while the AMD Radeon 840M has no benchmark entries in the database. The Intel Arc B370 scored 1184 in the 3DMark Steel Nomad DX12 test. This places it in the 5th percentile of all GPUs in the database, with an average benchmark score of 1184.

The nearest rivals for the Intel Arc B370 provide context for this score. The ATI Mobility Radeon HD 5570 has an average score of 1186, which is 0.2% higher than the Intel part. The ATI Radeon HD 5770 has an average score of 1190, which is 0.5% higher. The AMD Radeon HD 7650M has an average score of 1192, which is 0.7% higher. The AMD FirePro M2000 has an average score of 1168, which is 1.4% lower than the Intel part.

The Intel Arc B370 sits within a narrow performance band, with the closest rival only 0.7% ahead and the closest trailing rival 1.4% behind. This indicates that the Intel part's performance is tightly clustered with these older discrete and mobile parts, despite its modern architecture and higher compute specifications.

The AMD Radeon 840M has no benchmark data, no nearest rivals, and no wins recorded. The head-to-head benchmark array is empty, and both wins counters show zero. The database contains no comparable score for the AMD part, so no direct numerical comparison can be made between the two GPUs in this dataset.

The percentile ranking for the Intel Arc B370 at 5th percentile underscores that this is a low-performance tier part relative to the broader GPU landscape. Its 1184 score in Steel Nomad DX12 is a modest result, and the AMD part has no equivalent measurement to place alongside it.

Specification Differences

The two GPUs differ across multiple specification fields. The process node differs: the AMD Radeon 840M uses 4 nm from TSMC, while the Intel Arc B370 uses 3 nm from Intel. The architectures are distinct as well, with RDNA 3.5 on the AMD side and Xe3-LPG on the Intel side.

Clock speeds differ in both base and boost. The AMD part runs at 400 MHz base and 2900 MHz boost. The Intel part runs at 300 MHz base and 2400 MHz boost.

Compute unit counts differ substantially. The AMD Radeon 840M has 256 shading units, 16 TMUs, 8 ROPs, and 4 ray tracing cores. The Intel Arc B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores.

Pixel and texture rates differ, with the Intel part at 48.00 GPixel/s and 96.00 GTexel/s versus the AMD part at 23.20 GPixel/s and 46.40 GTexel/s. FP32 throughput differs, with the Intel part at 6.144 TFLOPS versus the AMD part at 1,484.8 GFLOPS. FP16 throughput also differs, with the Intel part at 12.29 TFLOPS (2:1 ratio) versus the AMD part at 1,484.8 GFLOPS (1:1 ratio).

TDP differs: 15 W for the AMD part versus 25 W for the Intel part. The bus interface differs: PCIe 4.0 x8 for the AMD part versus IGP for the Intel part. Release dates differ as well, with the AMD part released on February 28, 2025, and the Intel part released on January 26, 2026.

The generation naming differs: the AMD part is listed under Navi III IGP (Strix Point Mobile), while the Intel part is under Arc Graphics-M (Panther Lake). The predecessor field shows Navi II IGP for the AMD part, while the Intel part has no predecessor listed. Both have no successor listed.

Where Each One Wins

Based on the recorded data, the Intel Arc B370 wins in all measured compute categories. Its FP32 throughput of 6.144 TFLOPS is approximately four times the 1,484.8 GFLOPS of the AMD Radeon 840M. Its FP16 throughput of 12.29 TFLOPS is more than eight times the AMD part's FP16 figure. The pixel rate of 48.00 GPixel/s and texture rate of 96.00 GTexel/s both double the corresponding AMD rates of 23.20 GPixel/s and 46.40 GTexel/s.

The Intel Arc B370 also has more execution resources across the board. With 1280 shading units versus 256, 40 TMUs versus 16, 20 ROPs versus 8, and 10 ray tracing cores versus 4, the Intel part is designed for higher throughput workloads. The benchmark score of 1184 in 3DMark Steel Nomad DX12 confirms that the Intel part delivers measurable performance in a modern DirectX 12 workload, even if that score places it in the 5th percentile overall.

The AMD Radeon 840M wins in power efficiency as measured by TDP. At 15 W, it draws 10 W less than the Intel Arc B370's 25 W. It also has a higher base clock of 400 MHz versus 300 MHz and a higher boost clock of 2900 MHz versus 2400 MHz. For systems with stricter thermal or power budgets, the AMD part may be preferable despite its lower raw throughput.

The AMD part also has no recorded benchmark score, so it cannot be positioned against the Intel part's 1184 Steel Nomad result. The absence of data means the AMD part's real-world performance in the same workload is unknown in this dataset.

The Verdict

The data shows a clear split between raw performance and power draw. The Intel Arc B370 delivers substantially higher compute throughput, with four times the FP32 performance, more than eight times the FP16 performance, double the pixel and texture rates, and a recorded benchmark score of 1184 in 3DMark Steel Nomad DX12. Its nearest rivals, all with scores between 1168 and 1192, confirm that the Intel part operates in a specific performance band, trailing the ATI Mobility Radeon HD 5570 by 0.2%, the ATI Radeon HD 5770 by 0.5%, and the AMD Radeon HD 7650M by 0.7%, while leading the AMD FirePro M2000 by 1.4%.

The AMD Radeon 840M has no benchmark entries, no nearest rivals, and no wins recorded in the database. Its specifications show lower compute resources and lower throughput, but also lower power consumption at 15 W versus 25 W and higher clock speeds at 2900 MHz boost versus 2400 MHz boost. For workloads that depend on clock frequency and power efficiency, the AMD part may hold an advantage, but the database contains no measured score to substantiate this.

The Intel Arc B370 should be chosen when the priority is raw compute throughput, higher shading unit count, faster pixel and texture fill, and a validated benchmark result. The AMD Radeon 840M should be chosen when power draw is the limiting factor, given its 15 W TDP and higher boost clock, though its actual performance remains unmeasured in this dataset. The recorded data does not support a direct performance comparison, as only one side has a benchmark score.