AMD Radeon 820M vs Intel Arc Pro B390 Comparison

AMD Radeon 820M and Intel Arc Pro B390 are both integrated graphics processors, but the database shows they are built on entirely different scales of hardware capability. The Radeon 820M, part of the Krackan Point 2 chip, is a power-efficient IGP designed for mainstream mobility. The Intel Arc Pro B390, using the Panther Lake chip, is a much larger implementation of Intel's Xe3-LPG architecture. The recorded data shows no direct head-to-head benchmark scores for these two parts, and the win tally is zero for both. However, the specification sheets and architectural details reveal a clear separation in their intended performance envelopes.

Head-to-Head Benchmarks

The database contains no recorded head-to-head benchmark results between the AMD Radeon 820M and the Intel Arc Pro B390. Consequently, the win counts for both parts are zero. This absence of direct measurements means the comparison must proceed through the theoretical throughput figures and architectural resource counts present in the database.

The most striking differential in the raw compute metrics is FP32 performance. The Intel Arc Pro B390 delivers 7.680 TFLOPS, while the AMD Radeon 820M delivers 716.8 GFLOPS. This represents a 10.7x advantage for the Intel part in single-precision floating-point throughput. The gap is similarly pronounced in texture rate. The Arc Pro B390 produces 120.0 GTexel/s, while the Radeon 820M produces 22.40 GTexel/s, a 5.4x difference. Pixel rate shows the same trend, with the Intel part hitting 60.00 GPixel/s versus the Radeon's 11.20 GPixel/s, a 5.4x gap.

The FP16 comparison offers a different perspective on the architectures. The Radeon 820M operates FP16 at a 1:1 ratio with FP32, delivering 716.8 GFLOPS. The Arc Pro B390 runs FP16 at a 2:1 ratio, reaching 15.36 TFLOPS. This means the Intel part is 21.4x faster in half-precision throughput, and its architecture scales FP16 performance more efficiently than the AMD part. The shader resource count explains much of this. The Arc Pro B390 has 1536 shading units, 48 TMUs, and 24 ROPs. The Radeon 820M has 128 shading units, 8 TMUs, and 4 ROPs. These are 12x, 6x, and 6x differences, respectively.

Clock speeds present a counterpoint. The Radeon 820M has a base clock of 400 MHz and a boost clock of 2800 MHz. The Arc Pro B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The AMD part runs higher clocks, but the Intel part's massive lead in execution resources overwhelms the clock advantage. The data indicates the Intel Arc Pro B390 is the dominant part in every measurable throughput category.

FAQ

Q: What is the FP32 performance difference between the two GPUs?

A: The Intel Arc Pro B390 delivers 7.680 TFLOPS of FP32 compute, while the AMD Radeon 820M delivers 716.8 GFLOPS. The Intel part is 10.7x faster in single-precision throughput.

Q: How do the ray tracing capabilities compare?

A: The Intel Arc Pro B390 has 12 ray tracing cores, whereas the AMD Radeon 820M has 2. The Intel part has 6x the RT core count.

Q: What is the maximum boost clock for each GPU?

A: The AMD Radeon 820M boosts to 2800 MHz. The Intel Arc Pro B390 boosts to 2500 MHz. The AMD part has a higher boost clock by 300 MHz.

Q: Do both GPUs support the same DirectX version?

A: Yes, both the AMD Radeon 820M and the Intel Arc Pro B390 support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: How does the texture fill rate differ?

A: The Intel Arc Pro B390 achieves 120.0 GTexel/s, while the AMD Radeon 820M achieves 22.40 GTexel/s. The Intel part is 5.4x faster in texture rate.

Q: What are the power consumption figures?

A: The AMD Radeon 820M has a TDP of 15 W. The Intel Arc Pro B390 has a TDP of 80 W. The Intel part consumes 65 W more.

The Verdict

The data positions these two IGPs at opposite ends of the integrated graphics spectrum. The Intel Arc Pro B390 is the clear performance leader across all theoretical throughput metrics. Its 10.7x lead in FP32, 5.4x lead in texture rate, and 6x lead in RT core count indicate it is designed for demanding workloads that the AMD Radeon 820M cannot approach.

The AMD Radeon 820M, with its 15 W TDP, is optimized for efficiency. Its 400 MHz base clock and 2800 MHz boost clock show it can ramp up when needed, but its 128 shading units and 4 ROPs limit its ceiling. The database shows the Radeon 820M is a capable IGP for basic graphics and light compute, but it is not in the same class as the Arc Pro B390.

The Intel part's 80 W TDP and 3 nm process node from Intel Foundry indicate a part built for performance within a mobile platform, not for minimal power draw. The 1536 shading units and 48 TMUs confirm this design intent. For any application that scales with shader count, texture work, or ray tracing, the Arc Pro B390 is the decisive choice. The Radeon 820M is the choice only when power constraints are paramount, as its 15 W draw is one-fifth of the Intel part's 80 W.

Specification Differences

The two GPUs differ in nearly every measurable specification. The process node differs: the AMD Radeon 820M uses a 4 nm process from TSMC, while the Intel Arc Pro B390 uses a 3 nm process from Intel. The TDP differs significantly, with the Radeon 820M at 15 W and the Arc Pro B390 at 80 W.

Clock speeds are distinct. The Radeon 820M has a base clock of 400 MHz and a boost clock of 2800 MHz. The Arc Pro B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The memory configuration is identical in type, both using System Shared memory with System Dependent bandwidth and bus width.

The core counts show the largest divergence. The Radeon 820M has 128 shading units, 8 TMUs, 4 ROPs, and 2 RT cores. The Arc Pro B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 RT cores. The pixel rate is 11.20 GPixel/s for the AMD part and 60.00 GPixel/s for the Intel part. The texture rate is 22.40 GTexel/s versus 120.0 GTexel/s. FP32 is 716.8 GFLOPS versus 7.680 TFLOPS, and FP16 is 716.8 GFLOPS versus 15.36 TFLOPS.

The bus interface also differs. The Radeon 820M uses PCIe 4.0 x8, while the Arc Pro B390 lists its bus interface simply as IGP. The release dates are distinct, with the Radeon 820M released on 2025-02-28 and the Arc Pro B390 on 2026-01-26. The predecessor names differ as well, with the Radeon 820M succeeding Navi II IGP and the Arc Pro B390 succeeding HD Graphics-WM.

Architecture Differences

The architectural lineage separates these parts clearly. The AMD Radeon 820M is built on RDNA 3.5 and belongs to the Navi III IGP generation for Strix Point Mobile. The chip is Krackan Point 2. The Intel Arc Pro B390 uses the Xe3-LPG architecture and belongs to the Arc Graphics-WM generation for Panther Lake, with the chip being Panther Lake.

The FP16 execution ratio highlights an architectural divergence. The Radeon 820M processes FP16 at a 1:1 ratio with FP32, meaning it uses the same hardware for both. The Arc Pro B390 processes FP16 at a 2:1 ratio, allowing it to double its half-precision throughput. This is reflected in the numbers: the Radeon 820M's FP16 is 716.8 GFLOPS, identical to its FP32, while the Arc Pro B390's FP16 is 15.36 TFLOPS, exactly double its FP32.

The foundry and process node differ. AMD uses TSMC's 4 nm process, while Intel uses its own 3 nm process. The transistor count and die size are unknown for both parts, so no density comparison can be made. Both GPUs share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both are classified as IGP slot width with no power connectors, and both have display outputs that are Portable Device Dependent.

The production status for both is Active. The release date shows the AMD part came first, on 2025-02-28, with the Intel part following on 2026-01-26. The architecture differences point to different design philosophies: RDNA 3.5 focuses on efficiency with a 1:1 FP16 path, while Xe3-LPG prioritizes raw throughput with a 2:1 FP16 path.

Where Each One Wins

The AMD Radeon 820M wins in power efficiency. Its 15 W TDP is 65 W lower than the Intel Arc Pro B390's 80 W. For thin-and-light portable devices, this power draw is a critical advantage. The Radeon 820M also wins on clock speed, with a 2800 MHz boost versus the Intel part's 2500 MHz, though this does not compensate for the resource deficit.

The Intel Arc Pro B390 wins in every compute category. Its FP32 throughput of 7.680 TFLOPS is 10.7x higher than the Radeon's 716.8 GFLOPS. Its FP16 throughput of 15.36 TFLOPS is 21.4x higher. Texture rate is 5.4x higher, and pixel rate is 5.4x higher. The RT core count of 12 versus 2 gives it a 6x advantage in ray tracing workloads.

The use-case split follows these numbers. The Radeon 820M is suited for basic 2D desktop work, light video playback, and power-sensitive mobile applications where the 15 W TDP is a hard constraint. The Arc Pro B390 is suited for GPU-accelerated compute, content creation, and any task that leverages its 1536 shading units. The 3 nm Intel process and 2:1 FP16 ratio suggest the Intel part targets professional and workstation-adjacent mobile uses. The data is unambiguous: the Arc Pro B390 is the performance part, and the Radeon 820M is the efficiency part.