AMD Radeon Pro 455 vs NVIDIA GeForce MX350 Comparison

Head-to-Head Benchmarks

The recorded data shows a split decision between these two mobile graphics solutions. In the Geekbench OpenCL test, the AMD Radeon Pro 455 scores 10,336 points against 8,689 points for the NVIDIA GeForce MX350, a 19% advantage for the AMD part. This is the larger margin of the two head-to-head results, and it gives the Radeon Pro 455 a clear edge in compute workloads that leverage OpenCL.

The situation reverses in the Geekbench Vulkan test. Here, the NVIDIA GeForce MX350 scores 13,077 points, surpassing the AMD Radeon Pro 455's 12,240 points by 6.4%. While the margin is smaller than AMD's OpenCL lead, it still represents a decisive win for NVIDIA in Vulkan-based applications.

Looking at the broader database context, the AMD Radeon Pro 455 sits at the 52nd percentile among all GPUs, with an average benchmark score of 12,831 across all recorded tests. The NVIDIA GeForce MX350, by contrast, holds the 49th percentile with an average score of 10,883. The percentile gap is modest, but the average score difference of nearly 2,000 points reflects AMD's stronger overall showing in the recorded test suite.

The Radeon Pro 455's nearest rivals in the database include the NVIDIA GeForce GTX 590 at 12,830 points, the AMD FirePro W5100 at 12,847 points, the AMD Radeon 740M at 12,870 points, and the NVIDIA GeForce GTX 670 at 12,773 points. The delta percentages are all within a fraction of a percent, placing the Radeon Pro 455 in a tightly clustered performance tier. The MX350's nearest rivals include the AMD Radeon Pro 450 at 10,804 points, the NVIDIA Quadro K2200 at 10,761 points, the NVIDIA GeForce GTX 1650 SUPER at 11,047 points, and the AMD Radeon RX 550 at 11,075 points. The MX350 trails the GTX 1650 SUPER by 1.5% and the RX 550 by 1.7%, while leading the Radeon Pro 450 by 0.7% and the Quadro K2200 by 1.1%.

The data indicates that the AMD Radeon Pro 455 competes in a higher performance tier overall, despite being an older product. Its average score of 12,831 places it above the MX350's nearest rivals, while the MX350's average of 10,883 sits below most of the Radeon Pro 455's comparison points. The head-to-head results confirm this: AMD wins one test decisively, NVIDIA wins the other by a smaller margin, and the average score favors AMD by roughly 18%.

Architecture Differences

The two GPUs come from different architectural lineages. The AMD Radeon Pro 455 uses the Baffin chip built on GCN 4.0 architecture, manufactured on a 14 nm process at GlobalFoundries. The NVIDIA GeForce MX350 uses the GP107S chip built on Pascal architecture, also on a 14 nm process but manufactured at Samsung. Both use the same process node, but the foundries differ.

The AMD chip integrates 3,000 million transistors on a 123 mm² die, yielding a transistor density of 24.4 million per square millimeter. The NVIDIA chip contains 3,300 million transistors on a 132 mm² die, for a density of 25.0 million per square millimeter. The NVIDIA chip is slightly larger in both transistor count and die area.

The shader configurations differ substantially. The Radeon Pro 455 has 768 shading units, 48 texture mapping units, and 16 ROPs. The MX350 has 640 shading units, 32 TMUs, and 16 ROPs. AMD leads in shading units and TMUs, while both have identical ROP counts. These differences manifest in the measured rates: the Radeon Pro 455 achieves a pixel rate of 13.68 GPixel/s and a texture rate of 41.04 GTexel/s, while the MX350 achieves 23.49 GPixel/s and 46.98 GTexel/s. Despite having fewer TMUs, the MX350's higher clock speeds produce a faster texture rate, and its pixel rate is substantially higher.

The FP32 throughput figures reflect the same pattern. The Radeon Pro 455 delivers 1,313.3 GFLOPS of FP32 performance. The MX350 delivers 1.879 TFLOPS, which converts to 1,879 GFLOPS, a meaningful advantage. The FP16 results are starkly different: the Radeon Pro 455 offers 1,313.3 GFLOPS of FP16 performance at a 1:1 ratio, while the MX350 manages only 29.36 GFLOPS at a 1:64 ratio. AMD's architecture handles FP16 at full rate, while NVIDIA's Pascal implementation here is heavily limited in that regard.

Memory configurations also diverge. Both use 2 GB of GDDR5, but the bus widths differ: the Radeon Pro 455 uses a 128 bit bus with 81.28 GB/s of bandwidth, while the MX350 uses a 64 bit bus with 56.06 GB/s of bandwidth. The memory clocks differ as well, with AMD at 1270 MHz (5.1 Gbps effective) and NVIDIA at 1752 MHz (7 Gbps effective). The wider bus on the AMD side more than compensates for the lower memory clock.

The MX350 has explicit base and boost clocks recorded at 1354 MHz and 1468 MHz respectively. The Radeon Pro 455 has no base or boost clock listed in the database, only its memory clock. The power envelopes also differ, with the Radeon Pro 455 rated at 35 W and the MX350 at 20 W, making the NVIDIA part the lower-power option.

API support shows small differences. Both support DirectX 12 and OpenGL 4.6. The Radeon Pro 455 supports DirectX 12 at feature level 12_0 and Vulkan 1.3. The MX350 supports DirectX 12 at feature level 12_1 and Vulkan 1.4. The NVIDIA part has a slightly higher DirectX feature level and a newer Vulkan version.

FAQ

Q: Which GPU wins in OpenCL performance?

A: The AMD Radeon Pro 455 scores 10,336 in Geekbench OpenCL, which is 19% higher than the NVIDIA GeForce MX350's score of 8,689.

Q: Which GPU wins in Vulkan performance?

A: The NVIDIA GeForce MX350 scores 13,077 in Geekbench Vulkan, which is 6.4% higher than the AMD Radeon Pro 455's score of 12,240.

Q: How do their memory bandwidth figures compare?

A: The AMD Radeon Pro 455 has a 128 bit memory bus and delivers 81.28 GB/s of bandwidth. The NVIDIA GeForce MX350 has a 64 bit bus and delivers 56.06 GB/s, making the AMD part roughly 45% higher in bandwidth.

Q: What is the FP16 performance difference?

A: The AMD Radeon Pro 455 delivers 1,313.3 GFLOPS of FP16 performance at a 1:1 ratio. The NVIDIA GeForce MX350 delivers 29.36 GFLOPS at a 1:64 ratio, a substantial difference that favors AMD for workloads using FP16.

Q: What is the power consumption of each GPU?

A: The AMD Radeon Pro 455 is rated at 35 W TDP. The NVIDIA GeForce MX350 is rated at 20 W TDP, making it the lower-power option by 15 W.

Q: How do the average benchmark scores compare?

A: The AMD Radeon Pro 455 has an average benchmark score of 12,831 across all recorded tests, placing it at the 52nd percentile. The NVIDIA GeForce MX350 has an average score of 10,883, placing it at the 49th percentile.

Specification Differences

The two GPUs differ across nearly every major specification category. The AMD Radeon Pro 455 uses the Baffin chip with GCN 4.0 architecture, while the NVIDIA GeForce MX350 uses the GP107S chip with Pascal architecture. Both are 14 nm parts, but AMD uses GlobalFoundries as its foundry while NVIDIA uses Samsung.

The AMD chip has 3,000 million transistors on a 123 mm² die. The NVIDIA chip has 3,300 million transistors on a 132 mm² die. Transistor density is 24.4M per mm² for AMD and 25.0M per mm² for NVIDIA.

The Radeon Pro 455 has no recorded base or boost clock in the database. The MX350 has a base clock of 1354 MHz and a boost clock of 1468 MHz. The memory clocks differ: AMD runs at 1270 MHz (5.1 Gbps effective), NVIDIA at 1752 MHz (7 Gbps effective).

Memory size is identical at 2 GB of GDDR5, but the bus widths differ: 128 bit for AMD versus 64 bit for NVIDIA. Bandwidth is 81.28 GB/s for AMD versus 56.06 GB/s for NVIDIA.

The shader configuration differs: AMD has 768 shading units and 48 TMUs, NVIDIA has 640 shading units and 32 TMUs. Both have 16 ROPs. Pixel rates are 13.68 GPixel/s for AMD and 23.49 GPixel/s for NVIDIA. Texture rates are 41.04 GTexel/s for AMD and 46.98 GTexel/s for NVIDIA.

FP32 performance is 1,313.3 GFLOPS for AMD and 1.879 TFLOPS for NVIDIA. FP16 performance is 1,313.3 GFLOPS at 1:1 for AMD and 29.36 GFLOPS at 1:64 for NVIDIA.

TDP differs: 35 W for AMD, 20 W for NVIDIA. The bus interface differs: PCIe 3.0 x8 for AMD, PCIe 3.0 x4 for NVIDIA. DirectX support is 12_0 for AMD and 12_1 for NVIDIA. Vulkan support is 1.3 for AMD and 1.4 for NVIDIA. The AMD part uses an MXM module slot width, while no slot width is recorded for the NVIDIA part.

Where Each One Wins

The AMD Radeon Pro 455 wins in OpenCL compute performance, delivering 19% higher scores than the MX350. Its FP32 throughput of 1,313.3 GFLOPS, while lower than the MX350's 1,879 GFLOPS, is paired with full-rate FP16 at 1,313.3 GFLOPS, giving it a distinct advantage in workloads that can use half-precision arithmetic. The wider 128 bit memory bus and 81.28 GB/s bandwidth provide a substantial bandwidth advantage over the 64 bit bus and 56.06 GB/s of the MX350, which matters in memory-bound tasks. The Radeon Pro 455 also has more shading units and TMUs, which supports its higher average benchmark score of 12,831 and its 52nd percentile ranking.

The NVIDIA GeForce MX350 wins in Vulkan performance, with a 6.4% higher score in the Geekbench Vulkan test. Its higher clock speeds, with a base of 1354 MHz and boost of 1468 MHz, drive pixel rates of 23.49 GPixel/s and texture rates of 46.98 GTexel/s, both of which exceed the AMD part's rates. Its FP32 throughput of 1.879 TFLOPS is roughly 43% higher than the Radeon Pro 455's FP32 figure. The MX350 also consumes less power at 20 W versus 35 W, making it the more efficient option for thermally constrained notebooks.

The overall benchmark picture favors the AMD Radeon Pro 455 due to its higher average score and percentile ranking, but the MX350's wins in Vulkan and its lower power draw make it competitive for specific use cases.

The Verdict

The data points to a clear choice for users prioritizing OpenCL compute, memory bandwidth, or FP16 workloads: the AMD Radeon Pro 455. Its 19% OpenCL lead, 81.28 GB/s of bandwidth, full-rate FP16 support, and higher average benchmark score of 12,831 make it the stronger all-around performer in the recorded tests. The 52nd percentile ranking confirms it sits above the MX350's 49th percentile in the broader database.

The NVIDIA GeForce MX350 is the better pick for Vulkan-based applications, where its 6.4% score advantage is recorded. Its lower 20 W TDP makes it the more power-efficient option, and its higher clock speeds deliver superior pixel and texture rates. The MX350's FP32 throughput of 1.879 TFLOPS also exceeds the Radeon Pro 455's 1,313.3 GFLOPS, making it the better choice for FP32-heavy workloads.

Users who need maximum compute flexibility across OpenCL and FP16 should select the AMD Radeon Pro 455. Users who prioritize Vulkan performance, FP32 throughput, or lower power consumption should select the NVIDIA GeForce MX350. The two GPUs serve different priorities, and the recorded data supports either choice depending on the workload.