AMD Radeon R9 370X vs NVIDIA P106-090 Comparison

FAQ

Q: Which GPU has the higher average benchmark score in the database?

A: The AMD Radeon R9 370X records an average benchmark score of 15,862, placing it at the 58th percentile of all GPUs, while the NVIDIA P106-090 averages 13,470 and sits at the 54th percentile.

Q: How do the two cards compare in OpenCL performance?

A: The AMD Radeon R9 370X scores 25,893 in Geekbench OpenCL, which is 21.5% higher than the NVIDIA P106-090's 21,304, making this a clear win for the AMD card.

Q: Which GPU wins in Vulkan workloads?

A: The NVIDIA P106-090 dominates in Geekbench Vulkan with a score of 18,596, more than double the AMD Radeon R9 370X's 9,018, a 51.5% margin in favor of NVIDIA.

Q: What are the closest rivals to each card according to the database?

A: The R9 370X's nearest neighbors include the AMD Radeon RX 7700 (15,852, 0.1% difference) and the AMD Radeon RX 9060 (16,014, -1% difference). The P106-090's closest rival is the NVIDIA GeForce GTX 570 (13,515, -0.3% difference).

Q: What are the memory configurations of these two GPUs?

A: The AMD Radeon R9 370X has 2 GB of GDDR5 on a 256-bit bus with 179.2 GB/s bandwidth, while the NVIDIA P106-090 has 3 GB of GDDR5 on a 192-bit bus with 192.2 GB/s bandwidth.

Q: Do these cards support the same APIs?

A: Both cards support DirectX 12 and OpenGL 4.6, but the AMD card is listed with DirectX 12 (11_1) and Vulkan 1.2.170, while the NVIDIA card supports DirectX 12 (12_1) and Vulkan 1.4.

Where Each One Wins

The recorded benchmark data splits cleanly between the two cards, with each taking one head-to-head victory. The AMD Radeon R9 370X wins in Geekbench OpenCL with a score of 25,893 against the P106-090's 21,304. That 21.5% margin suggests the AMD architecture handles OpenCL compute workloads with noticeably more efficiency. Users running OpenCL-based applications, whether for rendering, physics simulation, or general GPU compute, would see the data favor the R9 370X.

The NVIDIA P106-090 claims the Vulkan crown with a decisive 18,596 score versus 9,018 for the AMD card. This 51.5% lead is substantial and indicates that Vulkan API workloads, which include many modern games and Vulkan-native applications, run considerably better on the Pascal-based NVIDIA card. The gap is so wide that even the R9 370X's higher average benchmark score overall cannot offset this specific disadvantage.

In terms of overall standing, the AMD card's 15,862 average places it at the 58th percentile, while the NVIDIA card's 13,470 places it at the 54th percentile. The AMD card also edges out its nearest rival, the AMD Radeon RX 7700, by just 0.1%, showing how tightly clustered performance is at this tier. The NVIDIA card, by contrast, sits within 0.5% of the AMD Radeon RX 9070 XT, suggesting that its performance profile is comparable to a much newer GPU in this specific database measurement.

Architecture Differences

The two GPUs come from different architectural generations and design philosophies. The AMD Radeon R9 370X uses the Trinidad chip built on GCN 1.0 architecture, part of the Pirate Islands (R9 300) generation. It is fabricated on a 28 nm process at TSMC with 2,800 million transistors on a 212 mm² die, yielding a transistor density of 13.2 million per square millimeter. The NVIDIA P106-090 uses the GP106 chip with Pascal architecture, belonging to the Mining GPUs generation. It is built on a more advanced 16 nm process, also at TSMC, with 4,400 million transistors packed into a 200 mm² die, giving a transistor density of 22.0 million per square millimeter.

The transistor counts and densities tell an interesting story. NVIDIA packs 57% more transistors into a slightly smaller die, which reflects the denser 16 nm process. This architectural advantage likely contributes to the P106-090's superior Vulkan performance despite having fewer shading units. The AMD card compensates with a wider memory bus and more shading units, which helps in OpenCL workloads.

The P106-090 is a mining-focused card with no display outputs, while the R9 370X offers 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. The NVIDIA card also runs on a PCIe 1.0 x1 bus interface, which is severely limited compared to the R9 370X's PCIe 3.0 x16 connection. This bus limitation could affect data transfer speeds in certain workloads, though the benchmark scores suggest it does not cripple raw compute performance.

Specification Differences

The specification sheets reveal several clear differences between these two cards. The AMD Radeon R9 370X operates at a base clock of 980 MHz with a boost clock of 1030 MHz, while the NVIDIA P106-090 runs significantly faster at 1354 MHz base and 1531 MHz boost. Memory clocks also differ: the AMD card runs at 1400 MHz (5.6 Gbps effective), while the NVIDIA card runs at 2002 MHz (8 Gbps effective).

Memory configurations diverge substantially. The R9 370X has 2 GB of GDDR5 on a 256-bit bus, delivering 179.2 GB/s of bandwidth. The P106-090 has 3 GB of GDDR5 on a 192-bit bus, delivering 192.2 GB/s. Despite the narrower bus, the NVIDIA card achieves higher bandwidth due to its faster memory clock.

Compute resources differ in an interesting way. The AMD card has 1,280 shading units, 80 texture mapping units, and 32 ROPs. The NVIDIA card has fewer shading units at 768, fewer TMUs at 48, but more ROPs at 48. This configuration explains the pixel rate difference: the NVIDIA card achieves 73.49 GPixel/s versus the AMD card's 32.96 GPixel/s. Texture rates are closer, with the AMD card at 82.40 GTexel/s and the NVIDIA card at 73.49 GTexel/s. In FP32 compute, the AMD card leads with 2.637 TFLOPS against the NVIDIA card's 2.352 TFLOPS. The NVIDIA card has a negligible FP16 rate of 36.74 GFLOPS (1:64), while the AMD card lists no FP16 capability.

Power requirements differ dramatically. The R9 370X has a TDP of 180 W with dual 6-pin power connectors and a suggested PSU of 450 W. The P106-090 sips power at 75 W TDP with a single 6-pin connector and a suggested PSU of 250 W. Physical dimensions also vary: the AMD card is 221 mm long and 111 mm tall, while the NVIDIA card is longer at 250 mm with no listed height. Both are dual-slot cards.

Head-to-Head Benchmarks

The database records two direct head-to-head comparisons between these GPUs, and the results could not be more different. In Geekbench OpenCL, the AMD Radeon R9 370X scores 25,893 against the NVIDIA P106-090's 21,304. That is a 21.5% advantage for AMD. The R9 370X's higher FP32 throughput of 2.637 TFLOPS compared to 2.352 TFLOPS likely contributes to this OpenCL win, as does its larger count of shading units (1,280 versus 768). OpenCL workloads that scale with shader count and raw FP32 performance would naturally favor the AMD card.

The Vulkan result flips the script completely. The P106-090 scores 18,596 in Geekbench Vulkan, while the R9 370X manages only 9,018. The NVIDIA card leads by 51.5%, a massive margin. This is particularly striking given that the AMD card has more shading units and higher FP32 throughput. The Pascal architecture's Vulkan driver implementation and architectural efficiency appear to overcome the AMD card's raw compute advantages. The P106-090's higher clock speeds (1531 MHz boost versus 1030 MHz) and its newer 16 nm process likely play a role in this efficiency.

Wider database context adds perspective. The R9 370X's average score of 15,862 places it just 0.1% ahead of the AMD Radeon RX 7700 and 1.2% ahead of the AMD Radeon Pro W5500. The P106-090's 13,470 average sits 0.3% behind the NVIDIA GeForce GTX 570 and 0.5% behind the AMD Radeon RX 9070 XT. These rival comparisons show that the R9 370X holds its own against much newer GPUs in average terms, while the P106-090 lags slightly behind its closest competitors. The overall average score gap between the two cards is 2,392 points, favoring the AMD card by roughly 17.8%.

The Verdict

The data paints a clear picture of two GPUs with distinctly different strengths. The AMD Radeon R9 370X is the better overall card in the database's aggregate measurements, with a 15,862 average score against the P106-090's 13,470. It holds the 58th percentile position versus the NVIDIA card's 54th, and it wins the OpenCL head-to-head by 21.5%. Users whose workloads rely on OpenCL compute should choose the R9 370X without hesitation.

The NVIDIA P106-090, however, is the definitive choice for Vulkan-based applications. Its 51.5% lead in Geekbench Vulkan is overwhelming, and its higher pixel rate (73.49 GPixel/s versus 32.96 GPixel/s) suggests advantages in rasterization-heavy tasks. The card also offers more memory (3 GB versus 2 GB) and higher memory bandwidth (192.2 GB/s versus 179.2 GB/s), which could benefit texture-heavy workloads. Its dramatically lower power draw (75 W versus 180 W) and simpler power requirements (single 6-pin versus dual 6-pin, 250 W PSU versus 450 W PSU) make it the more practical choice for systems with limited power delivery.

The R9 370X counters with higher FP32 compute (2.637 TFLOPS versus 2.352 TFLOPS), more shading units, and a wider 256-bit memory bus. It also has the benefit of display outputs, making it usable in standard desktop configurations, whereas the P106-090 has no outputs and is clearly designed for mining or compute-only roles. The AMD card's PCIe 3.0 x16 interface is also far superior to the P106-090's PCIe 1.0 x1, which could bottleneck data-heavy workloads. For a general-purpose GPU that can drive displays and handle OpenCL compute, the R9 370X is the data-backed choice. For Vulkan performance and power efficiency in a compute-only environment, the P106-090 wins decisively. The choice ultimately depends on which API and workload profile matters more to the user.