AMD Radeon RX 6450M vs Intel Arc Pro B390 Comparison

Where Each One Wins

The benchmark database contains no recorded head-to-head benchmark results for the AMD Radeon RX 6450M versus the Intel Arc Pro B390. Both products hold a percentile rank of 50 against all GPUs in the database, and neither has an average benchmark score recorded. The winsA and winsB fields both show zero, meaning the database currently has no direct performance comparison data for these two mobile graphics solutions.

Without direct benchmark measurements, the use-case split must be derived from the architectural and specification data available. The AMD Radeon RX 6450M delivers a peak FP32 throughput of 3.779 TFLOPS, while the Intel Arc Pro B390 delivers 7.680 TFLOPS, a 2.03x advantage in raw compute throughput for Intel. The Intel part also reaches 15.36 TFLOPS FP16 (2:1), exactly double its FP32 rate, whereas the AMD part reaches 7.557 TFLOPS FP16 (2:1), also exactly double its own FP32 rate. This suggests the Intel architecture is positioned for workloads that scale with shader throughput.

The AMD side counters with a higher pixel fill rate of 78.72 GPixel/s versus 60.00 GPixel/s for Intel, a 31.2% advantage. The AMD Radeon RX 6450M also has 32 ROPs versus 24 ROPs on the Intel part. Texture rate is nearly identical: 118.1 GTexel/s for AMD versus 120.0 GTexel/s for Intel, a 1.6% edge for the Arc Pro B390. Both GPUs have 48 TMUs, which explains the similarity in texture throughput.

Memory configuration differs fundamentally. The AMD Radeon RX 6450M uses 4 GB of dedicated GDDR6 memory on a 64-bit bus, delivering 128.0 GB/s of bandwidth. The Intel Arc Pro B390 uses System Shared memory, with bandwidth listed as System Dependent. For workloads sensitive to dedicated memory bandwidth, the AMD part has a fixed, known figure; for the Intel part, performance depends entirely on the host system's memory configuration.

Architecture Differences

The two GPUs come from different manufacturers, process nodes, and architectural generations. AMD builds the Radeon RX 6450M on the Navi 24 chip using RDNA 2.0 architecture, fabricated by TSMC on a 6 nm process. The chip contains 5,400 million transistors on a 107 mm² die, giving a transistor density of 50.5 million per square millimeter. The device belongs to the Navi Mobile (RX 6000M) generation.

Intel builds the Arc Pro B390 on the Panther Lake chip using Xe3-LPG architecture, fabricated by Intel on a 3 nm process. The database lists transistor count, die size, and transistor density as unknown for this part. It belongs to the Arc Graphics-WM (Panther Lake) generation.

The compute configuration differs in shader count. The AMD part has 768 shading units, while the Intel part has 1536 shading units, exactly double. Both have 48 TMUs and 12 ray tracing cores. The AMD part has 32 ROPs versus 24 ROPs on the Intel part.

Clock behavior also differs substantially. The AMD Radeon RX 6450M has a base clock of 2000 MHz, a game clock of 2220 MHz, and a boost clock of 2460 MHz. The Intel Arc Pro B390 has a base clock of 300 MHz and a boost clock of 2500 MHz, with no game clock listed. The Intel part's very low base clock and high boost clock indicate a different power management strategy, likely ramping aggressively under load. The AMD part runs at a consistently higher floor.

Memory architecture is the other major differentiator. The AMD Radeon RX 6450M has dedicated 4 GB GDDR6 with a 64-bit bus and fixed 128.0 GB/s bandwidth. The Intel Arc Pro B390 shares system memory, with bus width and type both listed as System Shared. This means the Intel GPU's memory performance is not a fixed property of the GPU itself but varies with the host platform.

Power and interface also differ. The AMD part has a 50 W TDP and uses a PCIe 4.0 x4 bus interface. The Intel part has an 80 W TDP and uses an IGP bus interface. Both are listed as IGP slot width with no power connectors, and both are portable device dependent for display outputs.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Neither has tensor cores listed. The AMD part's predecessor is Polaris Mobile, while the Intel part's predecessor is HD Graphics-WM. The AMD Radeon RX 6450M was released on 2023-01-03, and the Intel Arc Pro B390 on 2026-01-26. Both are currently listed as Active production status.

FAQ

Q: Which GPU has higher FP32 compute throughput?

A: The Intel Arc Pro B390 delivers 7.680 TFLOPS FP32, which is 2.03x the 3.779 TFLOPS of the AMD Radeon RX 6450M.

Q: Which GPU has higher pixel fill rate?

A: The AMD Radeon RX 6450M achieves 78.72 GPixel/s, which is 31.2% higher than the 60.00 GPixel/s of the Intel Arc Pro B390.

Q: How do the memory configurations differ?

A: The AMD Radeon RX 6450M uses 4 GB of dedicated GDDR6 memory on a 64-bit bus with 128.0 GB/s bandwidth. The Intel Arc Pro B390 uses System Shared memory with System Dependent bandwidth.

Q: What are the TDP ratings for each GPU?

A: The AMD Radeon RX 6450M has a 50 W TDP, while the Intel Arc Pro B390 has an 80 W TDP.

Q: Do both GPUs support the same graphics APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: How do the boost clocks compare?

A: The Intel Arc Pro B390 boosts to 2500 MHz, slightly higher than the AMD Radeon RX 6450M's boost of 2460 MHz. However, the AMD part has a much higher base clock of 2000 MHz versus 300 MHz for Intel.

Specification Differences

The following specification fields differ between the AMD Radeon RX 6450M and the Intel Arc Pro B390:

• Chip: Navi 24 versus Panther Lake
• Architecture: RDNA 2.0 versus Xe3-LPG
• Generation: Navi Mobile (RX 6000M) versus Arc Graphics-WM (Panther Lake)
• Process Node: 6 nm versus 3 nm
• Foundry: TSMC versus Intel
• Transistors: 5,400 million versus unknown
• Die Size: 107 mm² versus unknown
• Transistor Density: 50.5M / mm² versus null
• Base Clock: 2000 MHz versus 300 MHz
• Boost Clock: 2460 MHz versus 2500 MHz
• Game Clock: 2220 MHz versus null
• Memory Speed: 2000 MHz, 16 Gbps effective versus System Shared
• Memory Size: 4 GB versus System Shared
• Memory Type: GDDR6 versus System Shared
• Memory Bus Width: 64 bit versus System Shared
• Memory Bandwidth: 128.0 GB/s versus System Dependent
• Shading Units: 768 versus 1536
• ROPs: 32 versus 24
• Pixel Rate: 78.72 GPixel/s versus 60.00 GPixel/s
• Texture Rate: 118.1 GTexel/s versus 120.0 GTexel/s
• FP32: 3.779 TFLOPS versus 7.680 TFLOPS
• FP16: 7.557 TFLOPS (2:1) versus 15.36 TFLOPS (2:1)
• TDP: 50 W versus 80 W
• Bus Interface: PCIe 4.0 x4 versus IGP
• Release Date: 2023-01-03 versus 2026-01-26
• Predecessor: Polaris Mobile versus HD Graphics-WM

Identical fields include shading units' TMU count (48 each), RT cores (12 each), slot width (IGP), power connectors (None), display outputs (Portable Device Dependent), API support (DirectX 12 Ultimate 12_2, OpenGL 4.6, Vulkan 1.4), and production status (Active). Neither part has a launch MSRP or a successor listed.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries for this pairing. The headToHeadBenchmarks array is empty, and both winsA and winsB are zero. As a result, no direct measurement-based comparison of real-world performance is available. The following analysis relies on the recorded specification data.

The single largest advantage belongs to the Intel Arc Pro B390 in FP32 compute: 7.680 TFLOPS versus 3.779 TFLOPS for AMD. This is a 103.3% lead (2.03x). The FP16 figures follow the same pattern: 15.36 TFLOPS versus 7.557 TFLOPS, also exactly 2.03x. This indicates the Intel part has double the shader count (1536 versus 768) and a higher boost clock (2500 MHz versus 2460 MHz), combining to produce roughly double the arithmetic throughput.

The single largest advantage for the AMD Radeon RX 6450M is pixel fill rate: 78.72 GPixel/s versus 60.00 GPixel/s. This 31.2% lead comes from the combination of 32 ROPs against 24 ROPs and the AMD part's higher sustained clock regime. The AMD base clock of 2000 MHz versus 300 MHz for Intel means the AMD GPU maintains a much higher minimum operating frequency, which directly supports its fill rate advantage.

Texture rate is nearly a tie. The Intel Arc Pro B390 posts 120.0 GTexel/s against 118.1 GTexel/s for AMD, a 1.6% difference. Both GPUs have 48 TMUs, so the small delta comes from the boost clock difference (2500 MHz versus 2460 MHz).

Memory bandwidth is not directly comparable because the Intel part uses System Shared memory with System Dependent bandwidth. The AMD part has a fixed 128.0 GB/s over a 64-bit GDDR6 bus. The absence of a fixed bandwidth figure for Intel means any bandwidth comparison would depend on the host system, which the database does not specify.

The TDP difference is 30 W: 80 W for Intel versus 50 W for AMD. This indicates the Intel part draws more power to support its higher compute throughput. On a percentage basis, the Intel part uses 60% more power while delivering 103.3% more FP32 throughput.

The Verdict

The recorded data paints a clear split. The Intel Arc Pro B390 is the compute-oriented part. It delivers 2.03x the FP32 throughput of the AMD Radeon RX 6450M (7.680 versus 3.779 TFLOPS), doubles the FP16 rate (15.36 versus 7.557 TFLOPS), and has double the shading units (1536 versus 768). The Intel part also has a slightly higher boost clock (2500 MHz versus 2460 MHz) and a slight texture rate edge (120.0 versus 118.1 GTexel/s). Its 80 W TDP reflects the higher power envelope required for that throughput.

The AMD Radeon RX 6450M is the fill-rate-oriented part. It posts 78.72 GPixel/s against 60.00 GPixel/s for Intel, a 31.2% advantage, with 32 ROPs versus 24. It has a 2000 MHz base clock versus 300 MHz for Intel, meaning it sustains a much higher minimum frequency. Its 50 W TDP is 37.5% lower than the Intel part's 80 W TDP. The AMD part also has a fixed 128.0 GB/s of dedicated GDDR6 bandwidth on a 64-bit bus, whereas the Intel part depends on shared system memory.

The database shows no direct benchmark measurements between these two GPUs, so neither wins a head-to-head score. The selection guidance must come from the specification data. For workloads dominated by raw shader compute and FP16 throughput, the Intel Arc Pro B390 holds a decisive theoretical advantage. For workloads dominated by pixel output and where a lower TDP is required, the AMD Radeon RX 6450M has the stronger recorded specifications.

Both parts are IGP-class mobile GPUs with no power connectors, portable-device-dependent display outputs, and identical API support for DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The AMD part belongs to the Radeon RX 6000 series on RDNA 2.0, while the Intel part uses Xe3-LPG on Panther Lake. The Intel part is newer, with a release date of 2026-01-26 against 2023-01-03 for AMD. Neither has a launch MSRP recorded in the database.