AMD Radeon R9 M290X vs NVIDIA P106-100 Comparison

The AMD Radeon R9 M290X and NVIDIA P106-100 occupy the same performance tier according to aggregate data, with average benchmark scores of 23276 and 23249 respectively. The R9 M290X is a 2014 mobile graphics solution based on GCN 1.0, while the P106-100 is a 2017 mining-oriented card built on Pascal. Their overall percentile ranking is identical at 68, placing both in the same competitive bracket despite vastly different designs and intended use cases.

Where Each One Wins

The data shows a single head-to-head benchmark between these two cards, and the NVIDIA P106-100 wins decisively. In Geekbench OpenCL, the P106-100 scores 35951 against the R9 M290X’s 22028, a delta of -38.7% from the AMD card’s perspective. This means the NVIDIA part delivers approximately 63% higher raw compute throughput in that specific test. The R9 M290X has zero benchmark wins in the available head-to-head comparison, while the P106-100 claims one.

However, the use-case split is more nuanced than a single test suggests. The R9 M290X is designed for portable systems, using an MXM Module slot width and having no dedicated power connectors, making it suitable for laptops and compact form factors where power delivery is constrained. Its display outputs are listed as “Portable Device Dependent,” confirming its mobile orientation. The P106-100, by contrast, is a desktop-oriented mining card with a Dual-slot design, a 1x 6-pin power connector, a suggested PSU of 300 W, and no display outputs whatsoever. This makes the P106-100 entirely unsuitable for traditional graphics output, while the R9 M290X can drive displays in portable environments.

For compute workloads, the P106-100 is the clear winner based on the OpenCL result and its higher theoretical throughput. The R9 M290X retains relevance in scenarios where mobile integration and display connectivity matter more than raw compute. If a workload requires Vulkan, the P106-100 has a Geekbench Vulkan score of 32897, though the R9 M290X has no Vulkan benchmark entry in the pack.

Architecture Differences

The two GPUs come from different architectural generations. The R9 M290X uses GCN 1.0 with the Neptune chip, fabricated on a 28 nm process at TSMC. The P106-100 uses Pascal with the GP106 chip, fabricated on a 16 nm process, also at TSMC. The process node difference is substantial: 28 nm versus 16 nm, which directly impacts transistor density. The R9 M290X packs 2,800 million transistors into a 212 mm² die, yielding 13.2M transistors per mm². The P106-100 contains 4,400 million transistors in a 200 mm² die, achieving 22.0M per mm². The P106-100 thus fits 57% more transistors into a slightly smaller die.

Clock speeds differ significantly. The R9 M290X runs at 850 MHz base and 900 MHz boost, while the P106-100 operates at 1506 MHz base and 1709 MHz boost. The NVIDIA card’s boost clock is nearly double the AMD card’s base clock. Memory clocks also diverge: the R9 M290X uses 1200 MHz (4.8 Gbps effective) GDDR5, while the P106-100 runs at 2002 MHz (8 Gbps effective) GDDR5. Memory capacity and bus width differ as well, with the R9 M290X featuring 4 GB on a 256-bit bus and the P106-100 featuring 6 GB on a 192-bit bus.

Shading unit counts are identical at 1280, and TMU counts match at 80. The ROP count differs: 32 for the R9 M290X versus 48 for the P106-100. Pixel rate reflects this, with the R9 M290X at 28.80 GPixel/s and the P106-100 at 82.03 GPixel/s. Texture rates also vary widely: 72.00 GTexel/s versus 136.7 GTexel/s. FP32 throughput is 2.304 TFLOPS for the AMD card and 4.375 TFLOPS for the NVIDIA card. The P106-100 also lists FP16 performance at 68.36 GFLOPS with a 1:64 ratio, while the R9 M290X has no FP16 figure.

API support shows generational differences. The R9 M290X supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The P106-100 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The higher DirectX feature level and newer Vulkan version on the Pascal card reflect its later release date. Power consumption differs: 100 W for the R9 M290X versus 120 W for the P106-100. The bus interface also differs, with the R9 M290X using PCIe 3.0 x16 and the P106-100 using PCIe 1.0 x16, a notable limitation for the mining card. The P106-100 measures 250 mm in length (9.8 inches), while the R9 M290X has no listed dimensions due to its MXM form factor.

The Verdict

The data directs distinct choices based on the target environment. For portable computing with display output, the AMD Radeon R9 M290X is the only viable option, as the P106-100 has no display outputs and cannot function as a conventional graphics card. The R9 M290X’s MXM Module form factor and portable-dependent outputs make it suitable for laptops, and its lower 100 W TDP aligns with mobile power budgets.

For compute-heavy workloads where display output is irrelevant, the NVIDIA P106-100 is overwhelmingly superior. The Geekbench OpenCL score of 35951 versus 22028 represents a 63% advantage, and the theoretical FP32 throughput of 4.375 TFLOPS nearly doubles the R9 M290X’s 2.304 TFLOPS. The P106-100 also offers 6 GB of memory versus 4 GB, and its 192.2 GB/s bandwidth exceeds the R9 M290X’s 153.6 GB/s despite the narrower bus. The higher pixel rate (82.03 GPixel/s versus 28.80 GPixel/s) and texture rate (136.7 GTexel/s versus 72.00 GTexel/s) reinforce this compute advantage.

Neither card is current, as both are marked end-of-life. The R9 M290X released in January 2014 and has a successor in Polaris Mobile, while the P106-100 released in June 2017 with no listed predecessor or successor. The R9 M290X’s aggregate score of 23276 sits 0.1% above the P106-100’s 23249, but this difference is negligible and driven by the AMD card’s Geekbench Metal score of 24524, a test the P106-100 does not appear in. The P106-100’s OpenCL advantage in the direct head-to-head is the more meaningful metric for compute applications.

FAQ

Q: Which card has a higher average benchmark score?

A: The AMD Radeon R9 M290X has an average benchmark score of 23276, which is 0.1% higher than the NVIDIA P106-100’s 23249. The AMD Radeon RX 6600M sits between them at 23273.

Q: Does the NVIDIA P106-100 support display output?

A: No. The P106-100’s display outputs are listed as “No outputs,” making it unusable for conventional graphics display. The R9 M290X, by contrast, has “Portable Device Dependent” outputs.

Q: What is the memory capacity of each card?

A: The R9 M290X has 4 GB of GDDR5 on a 256-bit bus with 153.6 GB/s bandwidth. The P106-100 has 6 GB of GDDR5 on a 192-bit bus with 192.2 GB/s bandwidth.

Q: Which card has higher clock speeds?

A: The P106-100 runs at 1506 MHz base and 1709 MHz boost, compared to the R9 M290X’s 850 MHz base and 900 MHz boost. The memory clock is also higher: 2002 MHz (8 Gbps effective) versus 1200 MHz (4.8 Gbps effective).

Q: What is the power consumption difference?

A: The R9 M290X has a TDP of 100 W, while the P106-100 has a TDP of 120 W. The P106-100 also requires a 1x 6-pin power connector and a suggested PSU of 300 W, while the R9 M290X has no power connectors listed.

Q: How do the two cards compare in Vulkan support?

A: The P106-100 supports Vulkan 1.4 and has a Geekbench Vulkan score of 32897. The R9 M290X supports Vulkan 1.2.170 but has no Vulkan benchmark score in the data pack.

Head-to-Head Benchmarks

The only direct benchmark comparison available is Geekbench OpenCL. The NVIDIA P106-100 scores 35951, while the AMD Radeon R9 M290X scores 22028. The delta is -38.7% from the AMD card’s perspective, meaning the NVIDIA card is approximately 63% faster. This is a substantial margin that aligns with the theoretical specifications: the P106-100’s FP32 throughput of 4.375 TFLOPS versus 2.304 TFLOPS for the R9 M290X, and its texture rate of 136.7 GTexel/s versus 72.00 GTexel/s.

The R9 M290X does have additional benchmark data not shared with the P106-100. In Geekbench Metal, it scores 24524, and in OpenCL it scores 22028, giving it an average of 23276 across those two tests. The P106-100’s average of 23249 comes from three tests: 3DMark Steel Nomad DX12 at 899, Geekbench OpenCL at 35951, and Geekbench Vulkan at 32897. The OpenCL result is the only overlapping test, and the NVIDIA card’s dominance there is unambiguous.

The R9 M290X’s nearest rivals include the AMD Radeon RX 6600M (23273, delta 0%) and the AMD Radeon Pro Vega 16 (23250, delta 0.1%). The P106-100’s nearest rivals include the same cards with inverted deltas: the Radeon Pro Vega 16 (23250, delta 0%) and the RX 6600M (23273, delta -0.1%). Both cards also sit near the AMD Radeon AI PRO R9700 (23315), which is 0.2-0.3% ahead. This clustering indicates that both cards perform within a narrow band of each other in aggregate, despite the single-test disparity.

Specification Differences

The following specification fields differ between the two cards. The R9 M290X uses the Neptune chip with GCN 1.0 architecture, while the P106-100 uses the GP106 chip with Pascal architecture. The process node is 28 nm for AMD and 16 nm for NVIDIA. Transistor count is 2,800 million versus 4,400 million, and die size is 212 mm² versus 200 mm². Transistor density is 13.2M per mm² versus 22.0M per mm².

Base clock is 850 MHz versus 1506 MHz, and boost clock is 900 MHz versus 1709 MHz. Memory clock is 1200 MHz (4.8 Gbps effective) versus 2002 MHz (8 Gbps effective). Memory size is 4 GB versus 6 GB, bus width is 256 bit versus 192 bit, and bandwidth is 153.6 GB/s versus 192.2 GB/s. ROPs are 32 versus 48. Pixel rate is 28.80 GPixel/s versus 82.03 GPixel/s, and texture rate is 72.00 GTexel/s versus 136.7 GTexel/s. FP32 is 2.304 TFLOPS versus 4.375 TFLOPS. FP16 is null versus 68.36 GFLOPS (1:64).

TDP is 100 W versus 120 W. Slot width is MXM Module versus Dual-slot. Power connectors are None versus 1x 6-pin. Suggested PSU is null versus 300 W. Bus interface is PCIe 3.0 x16 versus PCIe 1.0 x16. Display outputs are Portable Device Dependent versus No outputs. DirectX support is 12 (11_1) versus 12 (12_1). Vulkan support is 1.2.170 versus 1.4. The P106-100 has a length of 250 mm (9.8 inches), while the R9 M290X has no dimensions listed. Release dates are January 2014 versus June 2017. The R9 M290X has a successor (Polaris Mobile), while the P106-100 has none. Shading units (1280) and TMUs (80) are identical, as are OpenGL support (4.6) and production status (end-of-life).