AMD Radeon 840M vs Intel Arc Pro B370 Comparison

Head-to-Head Benchmarks

The recorded database contains no direct head-to-head benchmark results for the AMD Radeon 840M versus the Intel Arc Pro B370. Both entries have an empty head-to-head benchmark array, zero wins for each side, and a benchmark score of zero. Consequently, the comparison must be built entirely from the listed compute specifications, architectural details, and output capabilities rather than from measured frame rates or synthetic test scores.

The most decisive difference in raw throughput appears in the FP32 shading rate. The Intel Arc Pro B370 is listed at 6.144 TFLOPS, whereas the AMD Radeon 840M is listed at 1,484.8 GFLOPS, which converts to approximately 1.485 TFLOPS. This makes the Intel part about 4.14 times higher in FP32 compute, a substantial margin that will dominate any shader-bound workload. For FP16, the Intel part shows 12.29 TFLOPS due to a 2:1 ratio, while the AMD part shows 1,484.8 GFLOPS with a 1:1 ratio, meaning the Intel part offers roughly 8.28 times the half-precision throughput. These ratios are derived directly from the listed figures and represent the largest performance gaps in the comparison.

Texture and pixel fill rates also favor Intel substantially. The Arc Pro B370 delivers 96.00 GTexel/s and 48.00 GPixel/s, while the Radeon 840M delivers 46.40 GTexel/s and 23.20 GPixel/s. This means the Intel part is approximately 2.07 times higher in texture rate and 2.07 times higher in pixel rate. These figures scale with the shading unit and ROP counts, which are also much larger on the Intel side.

Clock speeds tell a different story. The AMD Radeon 840M has a base clock of 400 MHz and a boost clock of 2900 MHz, while the Intel Arc Pro B370 has a base clock of 300 MHz and a boost clock of 2400 MHz. The AMD part operates at a 500 MHz higher boost clock, which partially compensates for its lower execution width but cannot close the massive gap in shading units, TMUs, and ROPs.

Both parts are classified as integrated graphics processors (IGP) with system-shared memory. Neither has dedicated VRAM, and both list bandwidth as "System Dependent." This means the actual memory performance will be determined by the host platform's RAM configuration, which the database does not specify. As a result, the compute advantages measured in the listed rates may be constrained by shared memory bandwidth in real-world use.

Architecture Differences

The AMD Radeon 840M uses the RDNA 3.5 architecture built on a 4 nm process at TSMC. Its chip is named Krackan Point, and it belongs to the Navi III IGP generation under the Strix Point Mobile family. The Intel Arc Pro B370 uses the Xe3-LPG architecture built on a 3 nm process at Intel. Its chip is named Panther Lake, and it belongs to the Arc Graphics-WM generation under the Panther Lake family. The process node difference, 4 nm versus 3 nm, gives Intel a smaller transistor geometry, though the database lists transistor count and die size as unknown for both.

The execution resource counts differ sharply. The AMD part has 256 shading units, 16 TMUs, 8 ROPs, and 4 ray tracing cores. The Intel part has 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. This means Intel provides 5 times the shading units, 2.5 times the TMUs, 2.5 times the ROPs, and 2.5 times the ray tracing cores. These are direct structural differences that explain the throughput gaps in the fill and compute rates.

Neither part lists tensor cores. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The memory configuration is identical in type: system shared for both, with no dedicated VRAM and no bus width specified beyond "System Shared." The bus interface differs: the AMD part uses PCIe 4.0 x8, while the Intel part lists "IGP" as its bus interface, which typically indicates a direct connection to the processor rather than an external PCIe link.

Power consumption also differs. The AMD Radeon 840M is rated at 15 W TDP, while the Intel Arc Pro B370 is rated at 25 W TDP. Both are IGP slot width with no power connectors and no suggested PSU. The Intel part draws 10 W more, which is consistent with its larger execution array and higher fill rates.

Display outputs are listed as "Portable Device Dependent" for both, meaning the actual connectors depend on the laptop or handheld design. The release dates differ: the AMD part was released on February 28, 2025, and the Intel part on January 26, 2026. The AMD predecessor is Navi II IGP, while the Intel predecessor is HD Graphics-WM. Both are currently active in production.

Where Each One Wins

The AMD Radeon 840M wins in scenarios where lower power draw and higher boost clocks matter. Its 15 W TDP is 10 W lower than the Intel part, making it better suited for thermally constrained thin-and-light designs where sustained load must stay within a modest power envelope. Its boost clock of 2900 MHz is 500 MHz higher than the Intel part's 2400 MHz, which helps in lightly threaded or latency-sensitive tasks that do not fully utilize the execution width. The AMD part also uses PCIe 4.0 x8, which may offer more predictable bandwidth for certain shared-memory configurations compared to an IGP bus interface.

The Intel Arc Pro B370 wins in raw throughput across every measured rate category. Its FP32 compute is over 4 times higher, FP16 is over 8 times higher, texture rate is roughly double, and pixel rate is roughly double. This makes it the stronger choice for shader-heavy workloads, including modern game rendering, compute shaders, image processing, and any task that scales with shading unit count. Its 5 times larger shading unit count and 2.5 times more ray tracing cores give it a clear advantage in geometry-heavy and ray-traced scenes, assuming the host platform can feed it enough memory bandwidth.

The 25 W TDP of the Intel part suggests it can sustain higher performance under load, but it also means more heat to dissipate. The AMD part, with its lower TDP, may sustain its clocks better in devices without aggressive cooling. For battery-operated portable devices, the AMD part's lower power draw is a practical advantage. For docked or performance-focused laptops, the Intel part's compute advantage will show more clearly.

Both parts share the same API support, so software compatibility is not a differentiator. The absence of tensor cores on both means AI acceleration, if present, would rely on shader-based paths rather than dedicated matrix hardware.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Intel Arc Pro B370 has 6.144 TFLOPS FP32, while the AMD Radeon 840M has 1,484.8 GFLOPS. The Intel part is about 4.14 times higher.

Q: How do the shading unit counts compare?

A: The Intel Arc Pro B370 has 1280 shading units, while the AMD Radeon 840M has 256. This is a 5:1 ratio in favor of Intel.

Q: What are the boost clocks of each GPU?

A: The AMD Radeon 840M boosts to 2900 MHz, and the Intel Arc Pro B370 boosts to 2400 MHz. The AMD part has a 500 MHz higher boost clock.

Q: Do both GPUs support ray tracing?

A: Yes. The AMD Radeon 840M has 4 ray tracing cores, and the Intel Arc Pro B370 has 10 ray tracing cores.

Q: What is the memory configuration for both?

A: Both use system-shared memory with no dedicated VRAM. Memory size, type, and bus width are listed as "System Shared," and bandwidth is "System Dependent" for both.

Q: Which GPU has a lower TDP?

A: The AMD Radeon 840M has a TDP of 15 W, while the Intel Arc Pro B370 has a TDP of 25 W.

Specification Differences

The following fields differ between the AMD Radeon 840M and the Intel Arc Pro B370:

• Architecture: RDNA 3.5 versus Xe3-LPG
• Process node: 4 nm versus 3 nm
• Foundry: TSMC versus Intel
• Chip: Krackan Point versus Panther Lake
• Generation: Navi III IGP (Strix Point Mobile) versus Arc Graphics-WM (Panther Lake)
• Base clock: 400 MHz versus 300 MHz
• Boost clock: 2900 MHz versus 2400 MHz
• Shading units: 256 versus 1280
• TMUs: 16 versus 40
• ROPs: 8 versus 20
• Ray tracing cores: 4 versus 10
• Pixel rate: 23.20 GPixel/s versus 48.00 GPixel/s
• Texture rate: 46.40 GTexel/s versus 96.00 GTexel/s
• FP32: 1,484.8 GFLOPS versus 6.144 TFLOPS
• FP16: 1,484.8 GFLOPS (1:1) versus 12.29 TFLOPS (2:1)
• TDP: 15 W versus 25 W
• Bus interface: PCIe 4.0 x8 versus IGP
• Release date: 2025-02-28 versus 2026-01-26
• Predecessor: Navi II IGP versus HD Graphics-WM

Fields that are identical include memory size, type, bus width, bandwidth, slot width (IGP), power connectors (None), suggested PSU (null), display outputs (Portable Device Dependent), DirectX (12 Ultimate 12_2), OpenGL (4.6), Vulkan (1.4), production status (Active), and launch MSRP (null for both).

The Verdict

The recorded data indicates a clear split between efficiency and throughput. The AMD Radeon 840M is the lower-power option with a 15 W TDP and a higher boost clock, making it suitable for compact, battery-driven portable devices where thermal and power limits are strict. Its 256 shading units and 4 ray tracing cores are modest, but its 2900 MHz boost clock provides responsive single-threaded performance within its power class.

The Intel Arc Pro B370 is the higher-performance option in every measured throughput category. Its 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores deliver 6.144 TFLOPS FP32 and 12.29 TFLOPS FP16, which are multiples of the AMD part's figures. The 25 W TDP is higher, but it buys a roughly 4 times FP32 advantage and 2 times fill rate advantage. For users who prioritize shader-heavy rendering, ray-traced workloads, or compute tasks, the Intel part is the stronger choice based on the listed specifications.

The absence of benchmark scores means the verdict rests on architectural and specification data. The AMD part suits power-sensitive designs; the Intel part suits performance-oriented designs. Both are integrated with system-shared memory, so the host platform's RAM will ultimately influence real-world results. The database shows no head-to-head measurements, so the decision should be made on the documented compute rates and power envelopes alone.