AMD Radeon Pro 455 vs NVIDIA GeForce GTX 1070 Ti Comparison

Head-to-Head Benchmarks

The recorded benchmark data shows a decisive sweep for the NVIDIA GeForce GTX 1070 Ti across all three shared tests, with the widest margins appearing in compute-heavy workloads. In Geekbench Metal, the GTX 1070 Ti scores 22,180 against 15,916 for the AMD Radeon Pro 455, a 39.4% advantage. That is a substantial lead for an API where both architectures typically show relative strength, and it indicates the NVIDIA card's raw shading and memory throughput translate directly into graphics performance.

The gap widens dramatically in Geekbench OpenCL. The GTX 1070 Ti posts 49,219, while the Radeon Pro 455 manages only 10,336. That delta of 376.2% is not incremental; it represents a completely different performance class. OpenCL workloads often scale with compute unit count, memory bandwidth, and driver efficiency, and the data here suggests the GTX 1070 Ti is operating in a tier that the Radeon Pro 455 cannot approach. Similarly, in Geekbench Vulkan, the GTX 1070 Ti scores 61,006 versus 12,240, a 398.4% advantage. Vulkan's low-overhead nature tends to expose raw hardware capability, and the result reinforces that the NVIDIA card is overwhelmingly faster in this test.

The average benchmark score across all recorded tests tells the same story. The GTX 1070 Ti averages 14,277 across its full benchmark suite, while the Radeon Pro 455 averages 12,831. The GTX 1070 Ti sits at the 56th percentile of all GPUs in the database, with closely matched rivals including the Intel Iris Xe MAX Graphics (average 14,315, 0.3% higher), the AMD Radeon Vega 11 (14,352, 0.5% higher), and the NVIDIA GeForce GTX TITAN (14,373, 0.7% higher). The Radeon Pro 455, by contrast, sits at the 52nd percentile, with its nearest rival being the NVIDIA GeForce GTX 590 at an identical 12,830 average score. In head-to-head terms, the GTX 1070 Ti wins all three shared benchmarks, and the win count stands at 3 for NVIDIA and 0 for AMD.

Architecture Differences

The two cards come from fundamentally different design philosophies and process technologies. The NVIDIA GeForce GTX 1070 Ti uses the GP104 chip built on TSMC's 16 nm process, packing 7,200 million transistors into a 314 mm² die for a transistor density of 22.9 million per square millimeter. The AMD Radeon Pro 455 uses the Baffin chip on GlobalFoundries' 14 nm process, with 3,000 million transistors on a 123 mm² die, yielding a higher density of 24.4 million per square millimeter. The AMD chip is denser per area, but the NVIDIA chip is far larger and carries more than twice the transistor count.

Architecturally, the GTX 1070 Ti is Pascal, while the Radeon Pro 455 is GCN 4.0. The NVIDIA card features 2,432 shading units, 152 texture mapping units, and 64 ROPs. The AMD card has 768 shading units, 48 TMUs, and 16 ROPs. These are not close figures: the GTX 1070 Ti has more than three times the shading units and four times the ROPs. Pixel throughput reflects this, with the GTX 1070 Ti achieving 107.7 GPixel/s against 13.68 GPixel/s for the Radeon Pro 455. Texture rate is similarly lopsided at 255.8 GTexel/s versus 41.04 GTexel/s.

Compute throughput shows a notable architectural difference in floating-point handling. The GTX 1070 Ti delivers 8.186 TFLOPS of FP32 performance, but only 127.9 GFLOPS of FP16, a ratio of 1:64, indicating that half-precision is heavily de-emphasized. The Radeon Pro 455 delivers 1,313.3 GFLOPS in both FP32 and FP16, a 1:1 ratio, meaning its GCN design can process half-precision at the same rate as full precision. For workloads that use FP16, the AMD card is comparatively more efficient relative to its FP32 output, though its absolute FP32 number is far lower.

Memory architecture also differs sharply. The GTX 1070 Ti uses 8 GB of GDDR5 on a 256-bit bus, delivering 256.3 GB/s of bandwidth. The Radeon Pro 455 uses 2 GB of GDDR5 on a 128-bit bus, delivering 81.28 GB/s. The NVIDIA card has four times the memory capacity and more than three times the bandwidth. The Radeon Pro 455's memory clock is 1270 MHz with 5.1 Gbps effective, while the GTX 1070 Ti runs memory at 2002 MHz with 8 Gbps effective.

The power envelope is equally distinct. The GTX 1070 Ti carries a 180 W TDP, uses a dual-slot cooler, requires a single 8-pin power connector, and needs a 450 W suggested PSU. The Radeon Pro 455 has a 35 W TDP, is an MXM module, requires no external power connectors, and lists no PSU recommendation. The GTX 1070 Ti is a desktop expansion card with a 267 mm length, 112 mm height, and 40 mm width. The Radeon Pro 455 is designed for portable or small-form-factor systems, and its dimensions are not recorded in the database.

API support also differs. The GTX 1070 Ti supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The Radeon Pro 455 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The feature level difference in DirectX and the newer Vulkan version give the NVIDIA card a slight software-side edge.

FAQ

Q: Which card has a higher average benchmark score?

A: The NVIDIA GeForce GTX 1070 Ti has an average benchmark score of 14,277, while the AMD Radeon Pro 455 averages 12,831.

Q: How large is the performance gap in Geekbench Metal?

A: The GTX 1070 Ti scores 22,180 versus 15,916 for the Radeon Pro 455, a 39.4% advantage for NVIDIA.

Q: Does the AMD card win any shared benchmark?

A: No. Across the three head-to-head tests (Geekbench Metal, OpenCL, and Vulkan), the GTX 1070 Ti wins all of them. The win count is 3 for NVIDIA and 0 for AMD.

Q: What is the memory capacity difference?

A: The GTX 1070 Ti has 8 GB of GDDR5 on a 256-bit bus, while the Radeon Pro 455 has 2 GB of GDDR5 on a 128-bit bus.

Q: How do the power requirements compare?

A: The GTX 1070 Ti has a 180 W TDP, requires a dual-slot cooler, a single 8-pin power connector, and a 450 W suggested PSU. The Radeon Pro 455 has a 35 W TDP, is an MXM module, and needs no external power connectors.

Q: What are the FP16 capabilities of each card?

A: The GTX 1070 Ti delivers 127.9 GFLOPS of FP16, a 1:64 ratio relative to its FP32 output. The Radeon Pro 455 delivers 1,313.3 GFLOPS of FP16, a 1:1 ratio with its FP32 output.

Specification Differences

The two cards differ across nearly every major specification. The GTX 1070 Ti uses the GP104 chip with 7,200 million transistors on a 314 mm² die, while the Radeon Pro 455 uses Baffin with 3,000 million transistors on a 123 mm² die. The GTX 1070 Ti is built on TSMC's 16 nm process; the Radeon Pro 455 uses GlobalFoundries' 14 nm process. Transistor density favors AMD at 24.4M per mm² versus 22.9M per mm² for NVIDIA.

Shading units stand at 2,432 for the GTX 1070 Ti versus 768 for the Radeon Pro 455. TMUs are 152 versus 48, and ROPs are 64 versus 16. Pixel rate is 107.7 GPixel/s versus 13.68 GPixel/s, and texture rate is 255.8 GTexel/s versus 41.04 GTexel/s. FP32 compute is 8.186 TFLOPS versus 1,313.3 GFLOPS.

Memory differs in size, bus width, and bandwidth: 8 GB versus 2 GB, 256-bit versus 128-bit, and 256.3 GB/s versus 81.28 GB/s. Memory clock is 2002 MHz (8 Gbps effective) versus 1270 MHz (5.1 Gbps effective). The GTX 1070 Ti has a 180 W TDP, dual-slot width, 1x 8-pin power connector, and a 450 W suggested PSU. The Radeon Pro 455 has a 35 W TDP, uses an MXM module, has no power connectors, and no PSU suggestion.

Bus interface also differs: PCIe 3.0 x16 for NVIDIA versus PCIe 3.0 x8 for AMD. Display outputs are 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a on the GTX 1070 Ti, while the Radeon Pro 455 lists display outputs as portable device dependent. API versions differ in DirectX (12_1 versus 12_0) and Vulkan (1.4 versus 1.3), though both support OpenGL 4.6. The GTX 1070 Ti measures 267 mm in length, 112 mm in height, and 40 mm in width; the Radeon Pro 455 has no recorded dimensions. The GTX 1070 Ti launched in November 2017 with a launch MSRP of 399 USD. The Radeon Pro 455 launched in October 2016 with no recorded MSRP.

Where Each One Wins

The NVIDIA GeForce GTX 1070 Ti wins in every measured category. Its 39.4% Metal lead, 376.2% OpenCL lead, and 398.4% Vulkan lead make it the clear choice for any application that relies on those APIs. The card's 8 GB memory capacity and 256.3 GB/s bandwidth position it for higher-resolution textures and larger datasets, while its 8.186 TFLOPS of FP32 compute allow it to handle demanding graphics and compute workloads without bottlenecking. The 56th percentile ranking among all GPUs, with rivals like the GeForce GTX TITAN and Radeon RX Vega 11 within 1%, places it in a competitive desktop performance tier.

The AMD Radeon Pro 455 does not win any benchmark, but its profile suggests a different purpose. At 35 W TDP with no external power connector and an MXM form factor, it is built for portability and constrained thermal environments. Its 1:1 FP16 ratio means it can process half-precision workloads at the same rate as full precision, which is a useful trait for certain compute tasks that favor FP16. Its 52nd percentile ranking, with rivals like the GeForce GTX 590 and Radeon 740M within 0.5%, shows it is not a low-end part, but it is clearly not in the same class as the GTX 1070 Ti.

For users choosing between these two, the decision comes down to context. The GTX 1070 Ti is the superior performer in every recorded benchmark, with more memory, more bandwidth, more shading units, and a much higher power ceiling. The Radeon Pro 455 is a low-power mobile module that trades performance for efficiency and compactness. In a desktop system with room for a dual-slot, 267 mm card and a 450 W PSU, the GTX 1070 Ti is the obvious choice. In a thin laptop or a chassis that can only accommodate an MXM module without auxiliary power, the Radeon Pro 455 is the only one of the two that fits, and its 35 W TDP makes it far easier to cool. The data does not show any scenario where the Radeon Pro 455 outperforms the GTX 1070 Ti; it simply exists in a different power and form-factor class.