NVIDIA GeForce RTX 2080 vs NVIDIA P106-100 Comparison

The NVIDIA P106-100 and the NVIDIA GeForce RTX 2080 represent two radically different purposes from the same manufacturer. The P106-100 is a dedicated mining GPU from the Pascal era, stripped of display outputs, while the RTX 2080 is a flagship Turing consumer card packed with real-time ray tracing and tensor core hardware. Benchmark data shows a complete rout in favor of the RTX 2080, but the story is more nuanced when considering the P106-100’s specialized origins. The data reveals that while the RTX 2080 dominates in raw compute, the P106-100’s existence highlights how NVIDIA segmented its product stack for the cryptocurrency boom.

Where Each One Wins

The head-to-head benchmark results show a clean sweep for the NVIDIA GeForce RTX 2080, winning all three recorded tests. There is no benchmark category where the P106-100 outperforms the RTX 2080 in the available data. The RTX 2080’s wins are decisive, with deltas ranging from -48.7% to -69.5% relative to the P106-100. In the 3DMark Steel Nomad DX12 test, the RTX 2080 scores 1752 against the P106-100’s 899, a massive gap that indicates the Turing card is nearly twice as fast in this modern DirectX 12 workload.

The compute-oriented benchmarks tell an even more lopsided story. In Geekbench OpenCL, the RTX 2080’s 91313 score dwarfs the P106-100’s 35951, representing a 60.6% advantage. The Geekbench Vulkan result is even more extreme, with the RTX 2080 posting 107797 versus 32897, a 69.5% lead. This suggests the RTX 2080’s architecture is dramatically more efficient at handling general-purpose compute and modern graphics APIs. The P106-100, despite its mining-focused design, does not have a single category where it can claim victory, making its use case strictly limited to its original purpose rather than any competitive gaming or compute scenario.

Architecture Differences

The two GPUs are built on fundamentally different architectures and process nodes. The P106-100 uses the Pascal architecture on TSMC’s 16 nm process, featuring the GP106 chip with 4,400 million transistors on a 200 mm² die. The RTX 2080 employs the Turing architecture on a 12 nm TSMC process, using the TU104 chip with 13,600 million transistors on a much larger 545 mm² die. This represents a transistor density increase from 22.0M / mm² on the P106-100 to 25.0M / mm² on the RTX 2080, showing that Turing packed more logic into each square millimeter despite the larger overall die.

The computing resources differ enormously. The P106-100 has 1280 shading units, 80 texture mapping units, and 48 ROPs. The RTX 2080 nearly doubles the shading units to 2944, more than doubles the TMUs to 184, and increases ROPs to 64. Critically, the RTX 2080 adds 46 RT cores and 368 tensor cores, hardware that the P106-100 lacks entirely. These dedicated units enable real-time ray tracing and AI-accelerated features, which explains why the RTX 2080 excels in modern workloads. The P106-100’s FP32 throughput is 4.375 TFLOPS, while the RTX 2080 reaches 10.07 TFLOPS, a 2.3x advantage. The FP16 figures are even more divergent: the P106-100 manages just 68.36 GFLOPS at a 1:64 ratio, while the RTX 2080 hits 20.14 TFLOPS at a 2:1 ratio, indicating a complete redesign of compute capabilities.

FAQ

Q: Does the P106-100 have any display outputs?

A: No, the P106-100 has no display outputs. This is a mining-specific GPU designed for compute workloads, not for connecting monitors or gaming.

Q: What is the memory configuration difference between the two cards?

A: The P106-100 has 6 GB of GDDR5 memory on a 192-bit bus with 192.2 GB/s bandwidth. The RTX 2080 has 8 GB of GDDR6 memory on a 256-bit bus with 448.0 GB/s bandwidth, more than double the bandwidth.

Q: Which card has better DirectX support in the data?

A: The RTX 2080 supports DirectX 12 Ultimate (12_2), while the P106-100 supports DirectX 12 (12_1). The RTX 2080’s higher feature level enables more advanced rendering techniques.

Q: How do the power requirements compare?

A: The P106-100 has a 120 W TDP with a single 6-pin power connector and a suggested 300 W PSU. The RTX 2080 requires 215 W TDP with 1x 6-pin plus 1x 8-pin connectors and a suggested 550 W PSU.

Q: What is the performance percentile for each card?

A: Both cards sit at the 68th percentile among all GPUs, despite the RTX 2080 having vastly higher benchmark scores. This indicates the percentile is relative to the dataset, not absolute performance.

Q: Are these cards still in production?

A: Both are end-of-life products. The P106-100 was released on June 18, 2017, while the RTX 2080 came later on September 19, 2018.

Specification Differences

The bus interface differs notably: the P106-100 uses PCIe 1.0 x16, while the RTX 2080 uses PCIe 3.0 x16. This is a major bandwidth limitation for the P106-100, though it matters less for mining workloads. The memory clocks are 2002 MHz (8 Gbps effective) for the P106-100 versus 1750 MHz (14 Gbps effective) for the RTX 2080, with the latter’s GDDR6 providing higher effective throughput. The physical dimensions show the RTX 2080 is longer at 267 mm versus 250 mm, and has specified height and width of 116 mm and 35 mm, while the P106-100 has no listed height or width.

The RTX 2080 includes display outputs (1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C), a feature completely absent on the P106-100. The base and boost clocks are nearly identical: 1506 MHz / 1709 MHz for the P106-100 versus 1515 MHz / 1710 MHz for the RTX 2080. However, the internal architecture differences make the raw clock comparison misleading. The RTX 2080 has a launch MSRP of 699 USD, while the P106-100 has no listed MSRP. The P106-100’s pixel rate is 82.03 GPixel/s and texture rate is 136.7 GTexel/s, while the RTX 2080 achieves 109.4 GPixel/s and 314.6 GTexel/s respectively.

Head-to-Head Benchmarks

The 3DMark Steel Nomad DX12 benchmark shows the RTX 2080 scoring 1752 against the P106-100’s 899. This 48.7% deficit for the P106-100 is the smallest gap of the three tests, yet still represents a near-doubling of performance. This test likely stresses the modern feature set where the RTX 2080’s Turing architecture excels, including its higher pixel rate and much larger texture throughput. The P106-100’s older Pascal architecture, despite similar clock speeds, cannot keep pace with the newer design.

Geekbench OpenCL reveals a 60.6% advantage for the RTX 2080, with scores of 91313 versus 35951. This test measures general compute performance, where the RTX 2080’s 2944 shading units and 20.14 TFLOPS FP16 capability provide a massive edge. The P106-100’s FP16 performance is negligible at 68.36 GFLOPS, meaning it cannot leverage half-precision compute efficiently. The RTX 2080’s tensor cores also contribute to OpenCL workloads that can utilize them, though the benchmark does not specifically isolate that functionality.

The Geekbench Vulkan result is the most lopsided, with the RTX 2080 scoring 107797 versus 32897, a 69.5% gap. Vulkan’s low-level API allows the RTX 2080’s superior hardware to shine, particularly its 448.0 GB/s memory bandwidth versus the P106-100’s 192.2 GB/s. This bandwidth advantage is critical for graphics workloads that constantly stream texture and geometry data. The RTX 2080’s 64 ROPs versus 48 also helps in pixel-heavy operations, contributing to its 109.4 GPixel/s fill rate compared to the P106-100’s 82.03 GPixel/s.

The Verdict

The data unequivocally points to the NVIDIA GeForce RTX 2080 as the superior performer in every measured category. Its 3DMark, OpenCL, and Vulkan scores are all dramatically higher, with advantages ranging from 48.7% to 69.5%. Any user seeking modern gaming performance, compute capability, or feature support should choose the RTX 2080, which also offers display outputs, ray tracing cores, and tensor cores. The RTX 2080’s 8 GB GDDR6 memory with 448.0 GB/s bandwidth provides 2.3x the bandwidth of the P106-100, making it far better suited for high-resolution textures and complex scenes.

The P106-100, however, is not without its niche. Its 120 W TDP and single 6-pin power connector make it a low-power compute option, and its lack of display outputs indicates it was built solely for mining. For that specific task, the lower power draw could be advantageous in large-scale installations where efficiency per watt matters more than absolute performance. The P106-100’s 68th percentile ranking matches the RTX 2080’s, suggesting that in the broader GPU landscape, both cards occupy a similar relative position despite the RTX 2080’s overwhelming benchmark superiority. The RTX 2080’s nearest rivals include the Intel Arc B580 with a -0.5% delta and the NVIDIA GeForce RTX 3080 at -1.2%, while the P106-100 sits near the AMD Radeon Pro Vega 16 with a 0% delta and the AMD Radeon RX 6600M at -0.1%. This contextualizes the P106-100 as a mid-range compute card from 2017, while the RTX 2080, despite being a 2018 flagship, now trades blows with modern mid-range offerings.