AMD Radeon R9 M295X vs NVIDIA GeForce RTX 2080 SUPER Comparison

Head-to-Head Benchmarks

The benchmark results are decisive. The NVIDIA GeForce RTX 2080 SUPER wins both recorded head-to-head tests, and it wins them by a massive margin. In Geekbench OpenCL, the RTX 2080 SUPER scores 99,226 against the AMD Radeon R9 M295X's 22,858, a delta of 77% in NVIDIA's favor. The gap is nearly as large in Geekbench Vulkan, where the RTX 2080 SUPER posts 111,284 versus 29,091 for the R9 M295X, a 73.9% advantage. There are no benchmark categories in the database where the AMD part comes out ahead.

The overall average benchmark scores tell a slightly different story, one that is worth examining closely. The R9 M295X has an average benchmark score of 28,580 across its three recorded tests, while the RTX 2080 SUPER averages 24,170 across its ten recorded tests. This apparent contradiction stems from the different test suites each card was measured with. The AMD card's average is built from Geekbench Metal, OpenCL, and Vulkan results, all of which are compute-oriented workloads. The NVIDIA card's average includes a much wider range of tests, including legacy DirectX 9 and DirectX 10 tests, 2D graphics tests, and several DirectX 11 and 12 runs, which pull its average down. The head-to-head tests, where both cards ran identical workloads, are the more reliable comparison, and they show a dominant NVIDIA victory.

The percentile rankings also reflect the mixed picture. The R9 M295X sits at the 74th percentile of all GPUs in the database, while the RTX 2080 SUPER sits at the 69th percentile. Again, this is a function of the test mix. The AMD card's three compute-heavy benchmarks all landed in a narrow, high range, from 22,858 to 33,790. The NVIDIA card's ten benchmarks span from 75 to 111,284, with several older API tests scoring very low. Those low scores drag down both its average and its percentile, even though its peak performance is far above anything the AMD card can produce.

Looking at the nearest rivals in the database provides additional context for each card's standing. The R9 M295X's average score of 28,580 places it within 1.4% of the AMD Radeon RX 470, which averages 28,996, and within 0.6% of the NVIDIA Quadro RTX 8000, which averages 28,421. It is also 1% ahead of the AMD Radeon RX 6800M's 28,874 and 0.6% behind the AMD Radeon RX 570's 28,766. These are all close margins, suggesting the R9 M295X performs in line with a cluster of mid-range desktop and mobile parts from multiple generations.

The RTX 2080 SUPER's nearest rivals are a more eclectic group. Its average of 24,170 is 0.3% behind the NVIDIA GeForce GTX 780 Ti's 24,236, 0.4% behind the NVIDIA GeForce GTX 1630's 24,277, 0.4% ahead of the AMD Radeon RX 6800S's 24,063, and 1.1% behind the AMD Radeon RX 6600 XT's 24,442. The presence of the GTX 780 Ti, a card from 2013, and the GTX 1630, an entry-level part, among its nearest rivals is a direct consequence of the RTX 2080 SUPER's diverse benchmark suite. Its compute scores are far above those older parts, but its legacy DirectX and 2D scores are not.

Architecture Differences

The two cards come from different architectural eras and different process technologies. The AMD Radeon R9 M295X uses the Amethyst chip built on GCN 3.0 architecture, manufactured on a 28 nm process at TSMC. The NVIDIA GeForce RTX 2080 SUPER uses the TU104 chip built on Turing architecture, manufactured on a 12 nm process, also at TSMC. The process difference is substantial: 28 nm versus 12 nm, which helps explain the NVIDIA card's ability to pack far more transistors into a larger die. The R9 M295X contains 5,000 million transistors on a 366 mm² die, for a density of 13.7 million transistors per square millimeter. The RTX 2080 SUPER contains 13,600 million transistors on a 545 mm² die, for a density of 25.0 million per square millimeter.

The compute resources differ sharply. The R9 M295X has 2,048 shading units, 128 texture mapping units, and 32 raster output pipelines. The RTX 2080 SUPER has 3,072 shading units, 192 TMUs, and 64 ROPs. That is 50% more shading units, 50% more TMUs, and double the ROPs. The NVIDIA card also brings dedicated hardware that the AMD card lacks entirely: 48 ray tracing cores and 384 tensor cores. These are not present in the GCN 3.0 design at all, as the RTX 2080 SUPER's Turing architecture introduced them for real-time ray tracing and AI acceleration workloads.

Memory and memory bandwidth also show a generational leap. The R9 M295X has 4 GB of GDDR5 memory on a 256-bit bus, delivering 160.0 GB/s of bandwidth. The RTX 2080 SUPER has 8 GB of GDDR6 memory on the same 256-bit bus, delivering 495.9 GB/s. The effective memory clock difference is stark as well: 5 Gbps effective for the AMD card against 15.5 Gbps effective for the NVIDIA card. The pixel rate and texture rate follow the same pattern. The R9 M295X manages 23.14 GPixel/s and 92.54 GTexel/s, while the RTX 2080 SUPER reaches 116.28 GPixel/s and 348.5 GTexel/s.

Floating point throughput is among the most telling differences. The R9 M295X delivers 2.961 TFLOPS for FP32 and the same 2.961 TFLOPS for FP16, a 1:1 ratio, indicating no dedicated half-precision hardware. The RTX 2080 SUPER delivers 11.15 TFLOPS for FP32 and 22.30 TFLOPS for FP16, a 2:1 ratio, showing its Turing architecture processes twice as many FP16 operations per clock. The NVIDIA card also supports DirectX 12 Ultimate with feature level 12_2, while the AMD card supports DirectX 12 with feature level 12_12. Both support OpenGL 4.6. The NVIDIA card supports Vulkan 1.4.

The cards also differ in their physical and system integration details. The R9 M295X is an MXM Module form factor with an MXM-B (3.0) bus interface, designed for portable devices, with display outputs described as portable device dependent and no power connectors listed. The RTX 2080 SUPER is a Dual-slot card with PCIe 3.0 x16, a 6-pin and 8-pin power connectors, and a 600 W suggested power supply. Its dimensions are 267 mm in length, 116 mm in height, and 35 mm in width.

Where Each One Wins

The R9 M295X wins in the narrow category of compute benchmark consistency. Its Geekbench Metal score of 33,790 is its highest recorded score, and it sits above its OpenCL result of 22,858. The spread between its lowest and highest scores is relatively small. Every benchmark it was tested with produced results in the 22,000 to 22,000 to 33,000 range. None of its scores fell below 22,000 in the database, and none of them dragged its average below 28,580. In the database's overall GPU percentile ranking, the R9 M295X sits at the 74th percentile of all GPUs, which is higher than the RTX 2080 SUPER's 69th percentile. For anyone looking at the all-GPU percentile alone, the AMD card ranks higher, even though that ranking is built from a limited test set.

The RTX 2080 SUPER wins in every recorded head-to-head comparison and in every meaningful performance metric. Its Geekbench OpenCL score of 99,226 is more than four times the R9 M295X's 22,858. Its Geekbench Vulkan score of 111,284 is nearly four times the AMD card's 29,091. It has double the memory capacity at 8 GB versus 4 GB, more than triple the memory bandwidth at 495.9 GB/s versus 160.0 GB/s, and roughly 3.8 times the FP32 throughput at 11.15 TFLOPS versus 2.961 TFLOPS. It has more shading units, more TMUs, more ROPs, and the only ray tracing and tensor cores in this comparison. It supports newer DirectX features and a newer Vulkan version. The NVIDIA card's 3DMark Steel Nomad DX12 score of 1,882 provides an additional modern workload data point, and its PassMark G3D score of 19,490 is likewise far above what the AMD card's compute scores suggest it could achieve.

For use cases like modern gaming with high frame rates, ray tracing workloads, and compute-heavy applications that can use Vulkan or OpenCL, the RTX 2080 SUPER is the only viable option between these two. For applications that rely on Metal performance, the R9 M295X has a single strong result in the database, but the head-to-head data does not include a Metal comparison. The AMD card's 74th percentile standing shows it remains competitive with a cluster of mid-range GPUs from later generations, but its absolute performance ceiling is far lower.

The Verdict

The data points to a clear conclusion: the NVIDIA GeForce RTX 2080 SUPER is the superior GPU by every head-to-head measurement in the database. It wins Geekbench OpenCL by 77% and Geekbench Vulkan by 73.9%. Its architectural advantages are overwhelming: more shading units, more TMUs, double the ROPs, dedicated ray tracing and tensor cores, a newer process node, higher transistor density, more memory, and more than triple the memory bandwidth. The only category where the AMD Radeon R9 M295X appears stronger is the overall percentile ranking, where its 74th percentile beats the RTX 2080 SUPER's 69th percentile, and its average benchmark score of 28,580 exceeds the NVIDIA card's 24,170. Those two numbers are artifacts of the different benchmark suites used for each card and should not be mistaken for evidence of competitive performance.

A user who needs maximum compute throughput, modern API support, ray tracing, tensor operations, or high-bandwidth memory should pick the RTX 2080 SUPER. A user who is looking at the database's percentile ranking alone might be tempted by the R9 M295X's higher placement, but the head-to-head results show that placement is misleading. The RTX 2080 SUPER belongs to a different performance class.

FAQ

Q: Which GPU has the higher Geekbench Vulkan score?

A: The NVIDIA GeForce RTX 2080 SUPER scores 111,284 in Geekbench Vulkan, compared to 29,091 for the AMD Radeon R9 M295X, a 73.9% difference.

Q: What is the transistor count difference between the two cards?

A: The R9 M295X has 5,000 million transistors on a 28 nm process, while the RTX 2080 SUPER has 13,600 million transistors on a 12 nm process.

Q: Does the AMD Radeon R9 M295X support ray tracing?

A: No. The R9 M295X has no ray tracing cores, while the RTX 2080 SUPER has 48 ray tracing cores and 384 tensor cores.

Q: Which card has more memory bandwidth?

A: The RTX 2080 SUPER has 495.9 GB/s of bandwidth with 8 GB of GDDR6, while the R9 M295X has 160.0 GB/s with 4 GB of GDDR5.

Q: Why does the R9 M295X have a higher average benchmark score if the RTX 2080 SUPER wins every head-to-head test?

A: The R9 M295X was tested with three compute benchmarks, Geekbench Metal, OpenCL, and Vulkan, all of which scored between 22,858 and 33,790. The RTX 2080 SUPER was tested with ten benchmarks, including legacy DirectX 9, DirectX 10, and 2D tests that scored as low as 75, pulling its average down to 24,170.

Q: What is the process node for each card?

A: The R9 M295X uses a 28 nm process at TSMC, and the RTX 2080 SUPER uses a 12 nm process, also at TSMC.

Specification Differences

The two cards differ in every major specification category in the database. The R9 M295X uses GCN 3.0 architecture with the Amethyst chip, while the RTX 2080 SUPER uses Turing architecture with TU104. The process node, foundry, process node, foundry, and transistor density all differ. The R9 M295X is 28 nm, TSMC, 5,000 million, on a 366 mm² die, with 13.7M / mm². The RTX 2080 SUPER is 12 nm, TSMC, 13,600 million, on a 545 mm² die, with 25.0M / mm². The R9 M295X has a memory clock of 1250 MHz with 5 Gbps effective, while the RTX 2080 SUPER has a base clock of 1650 MHz, a boost clock of 1815 MHz, a memory clock of 1937 MHz, and 15.5 Gbps effective.

Memory configurations differ completely: 4 GB GDDR5 on a 256-bit bus versus 8 GB GDDR6 on a 256-bit bus. Bandwidth is 160.0 GB/s versus 495.9 GB/s. Compute resources are 2048 shading units, 128 TMUs, and 32 ROPs versus 3072 shading units, 192 TMUs, and 64 ROPs. The RTX 2080 SUPER has 48 RT cores and 384 tensor cores; the R9 M295X has neither. Pixel rate is 23.14 GPixel/s versus 116.2 GPixel/s, texture rate is 92.54 GTexel/s versus 348.5 GTexel/s, FP32 is 2.961 TFLOPS versus 11.15 TFLOPS, and FP16 is 2.961 TFLOPS at 1:1 versus 22.30 TFLOPS at 2:1.

The form factors reflect their intended systems: the R9 M295X is an MXM Module with MXM-B (3.0) and no power connectors, while the RTX 2080 SUPER is a Dual-slot card with PCIe 3.0 x16, a 6-pin and 8-pin power connector, and a 600 W suggested power supply. Display outputs are portable device dependent for the AMD card, versus 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C for the NVIDIA card. The RTX 2080 SUPER measures 267 mm by 116 mm by 35 mm; the R9 M295X has no recorded dimensions. DirectX support differs: 12 (12_0) versus 12 Ultimate (12_2). Vulkan support differs: 1.2.170 versus 1.4. Both support OpenGL 4.6. The RTX 2080 SUPER has a launch MSRP of 699 USD; the R9 M295X has no recorded launch MSRP.