AMD Radeon R9 M390X vs NVIDIA RTX A5000 Mobile Comparison

Head-to-Head Benchmarks

The benchmark database includes one directly comparable test between these two mobile graphics processors: Geekbench Vulkan. In this test, the NVIDIA RTX A5000 Mobile scores 88,144, while the AMD Radeon R9 M390X scores 16,951. The result is a decisive victory for the NVIDIA part, with a delta of 420% over the AMD competitor. This is not a marginal difference; the RTX A5000 Mobile delivers more than five times the raw Vulkan compute throughput of the older R9 M390X.

Looking at the broader benchmark averages, the RTX A5000 Mobile records an average score of 24,763 across all its tested workloads. Its nearest rival in the database is the AMD Radeon RX 590 at 24,744, which is a 0.1% difference, essentially a statistical tie. The A5000 Mobile also sits 0.5% ahead of the Intel Arc A350M, 1.3% ahead of the AMD Radeon RX 6600 XT, and 2% ahead of the NVIDIA GeForce GTX 1630. This places the A5000 Mobile in the 70th percentile of all GPUs in the database.

The AMD Radeon R9 M390X, in contrast, has an average benchmark score of 20,662. Its nearest rival is the AMD Radeon RX 5600 XT at 20,713, where the M390X is actually 0.2% behind. It sits 0.4% ahead of the Intel Arc A750, 0.5% ahead of the Intel Arc B570, and 0.6% ahead of the NVIDIA GeForce RTX 3070 Mobile. The M390X falls in the 66th percentile of all GPUs. The gap between the two cards in average score is 4,101 points, which translates to roughly a 20% advantage for the RTX A5000 Mobile across all recorded workloads.

The individual benchmark suite for the RTX A5000 Mobile provides further detail. In Geekbench OpenCL, it scores 110,877. In Passmark tests, it scores 115 in DirectX 10, 133 in DirectX 11, 72 in DirectX 12, and 169 in DirectX 9. Its 2D graphics score is 629, while the 3D graphics score is 15,779. The GPU compute score is 6,945. These figures show a part that is heavily weighted toward modern API performance, with DirectX 12 being a relative weak point compared to older APIs, but compute workloads are clearly strong.

The AMD Radeon R9 M390X has only two recorded benchmarks in the database: Geekbench Metal at 24,373 and Geekbench Vulkan at 16,951. There are no Passmark scores recorded for this part, which limits direct comparison. However, the Vulkan test is the one that matters for head-to-head analysis, and the result is unambiguous.

Architecture Differences

The two GPUs come from different eras and entirely different design philosophies. The NVIDIA RTX A5000 Mobile is built on the GA104 chip using the Ampere architecture, fabricated on an 8 nm process at Samsung. The AMD Radeon R9 M390X uses the Amethyst chip with the GCN 3.0 architecture, fabricated on a 28 nm process at TSMC. The process node difference is substantial: 8 nm versus 28 nm, which has a direct impact on transistor density and power efficiency.

The transistor counts tell the story of scaling. The RTX A5000 Mobile packs 17,400 million transistors on a 392 mm² die, resulting in a transistor density of 44.4 million per mm². The R9 M390X has 5,000 million transistors on a 366 mm² die, with a density of 13.7 million per mm². Despite similar die sizes, the NVIDIA part holds more than three times the transistor count, a direct consequence of the smaller process node.

Compute resources differ dramatically. The RTX A5000 Mobile has 6,144 shading units, 192 texture mapping units, and 96 render output units. It also includes 48 ray tracing cores and 192 tensor cores, features that simply do not exist on the older AMD part. The R9 M390X has 2,048 shading units, 128 TMUs, and 32 ROPs. The shading unit count is exactly three times higher on the NVIDIA part, while the ROP count is three times higher as well.

Clock speeds are not directly comparable because the AMD part has no recorded base or boost clock in the database. The NVIDIA part runs at 900 MHz base and 1575 MHz boost. The memory clock for the NVIDIA part is 1750 MHz, translating to 14 Gbps effective, while the AMD part runs memory at 1250 MHz, or 5 Gbps effective. The memory subsystems are also of different generations: GDDR6 on the A5000 Mobile versus GDDR5 on the R9 M390X.

Memory capacity and bandwidth strongly favor the NVIDIA part. The RTX A5000 Mobile has 16 GB of GDDR6 on a 256-bit bus, delivering 448.0 GB/s of bandwidth. The R9 M390X has 4 GB of GDDR5 on a 256-bit bus, delivering 160.0 GB/s. Both use the same bus width, but the newer memory technology and higher clock speed give the NVIDIA part nearly three times the bandwidth.

The bus interface also differs. The RTX A5000 Mobile uses PCIe 4.0 x16, while the R9 M390X uses PCIe 3.0 x16. The power envelope is another point of separation: the NVIDIA part has a TDP of 150 W, while the AMD part is rated at 75 W. The AMD part is an MXM module, while the NVIDIA part has no slot width specified. Both are marked as end-of-life products.

API support reflects the architectural gap. The RTX A5000 Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The R9 M390X supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. The NVIDIA part also has ray tracing and tensor core hardware, which enables features that the GCN 3.0 architecture cannot provide.

The Verdict

The data points to a clear hierarchy. The RTX A5000 Mobile is the superior part in every measured dimension. Its average benchmark score is 24,763 versus 20,662 for the R9 M390X, a 20% advantage. In the only shared test, Vulkan, the NVIDIA part leads by 420%. The transistor count, shading unit count, memory bandwidth, and API support all favor the Ampere architecture part.

The RTX A5000 Mobile should be the choice for workloads that demand modern API support, high compute throughput, and large memory capacity. The 16 GB frame buffer and 448.0 GB/s bandwidth make it suitable for large datasets and high-resolution textures. The presence of ray tracing and tensor cores, along with DirectX 12 Ultimate support, positions it for current-generation gaming and compute workloads.

The R9 M390X, while far behind in absolute performance, has its own profile. It is a 75 W part, which is half the TDP of the RTX A5000 Mobile. For systems with strict power or thermal limits, the lower power draw could be relevant. However, the performance gap is so large that this advantage is hard to justify in most scenarios. The R9 M390X belongs to the GCN 3.0 era and shows its age in the benchmark data.

The percentile rankings reinforce this. The RTX A5000 Mobile sits in the 70th percentile of all GPUs, while the R9 M390X sits in the 66th percentile. The gap in percentile is modest, but the gap in raw scores is substantial. The nearest rivals for each card illustrate the competitive landscape: the A5000 Mobile trades blows with desktop parts like the RX 590 and RX 6600 XT, while the M390X aligns with mid-range parts like the RX 5600 XT and RTX 3070 Mobile.

For users choosing between these two, the decision is straightforward based on the recorded data. The RTX A5000 Mobile is the higher-performing part across the board. The only scenario where the R9 M390X might be preferable is when power consumption is the primary constraint, as its 75 W TDP is half that of the NVIDIA part.

Specification Differences

The two GPUs differ in nearly every specification category recorded in the database.

Chip and Architecture: The RTX A5000 Mobile uses the GA104 chip with Ampere architecture. The R9 M390X uses the Amethyst chip with GCN 3.0 architecture.

Process and Foundry: The RTX A5000 Mobile is built on an 8 nm process at Samsung. The R9 M390X uses a 28 nm process at TSMC.

Transistors and Die: The RTX A5000 Mobile has 17,400 million transistors on a 392 mm² die with a density of 44.4M per mm². The R9 M390X has 5,000 million transistors on a 366 mm² die with a density of 13.7M per mm².

Clocks: The RTX A5000 Mobile has a base clock of 900 MHz and a boost clock of 1575 MHz. The R9 M390X has no recorded base or boost clock. Memory clock is 1750 MHz (14 Gbps effective) on the NVIDIA part versus 1250 MHz (5 Gbps effective) on the AMD part.

Memory: The RTX A5000 Mobile has 16 GB of GDDR6 on a 256-bit bus with 448.0 GB/s bandwidth. The R9 M390X has 4 GB of GDDR5 on a 256-bit bus with 160.0 GB/s bandwidth.

Compute Units: The RTX A5000 Mobile has 6,144 shading units, 192 TMUs, and 96 ROPs. The R9 M390X has 2,048 shading units, 128 TMUs, and 32 ROPs. The NVIDIA part also has 48 RT cores and 192 tensor cores; the AMD part has none.

Performance Rates: The RTX A5000 Mobile delivers 151.2 GPixel/s pixel rate, 302.4 GTexel/s texture rate, and 19.35 TFLOPS FP32. The R9 M390X delivers 23.14 GPixel/s, 92.54 GTexel/s, and 2.961 TFLOPS FP32. Both have 1:1 FP16 rates.

Power: The RTX A5000 Mobile has a TDP of 150 W. The R9 M390X has a TDP of 75 W and is specified as an MXM Module.

Bus Interface: The RTX A5000 Mobile uses PCIe 4.0 x16. The R9 M390X uses PCIe 3.0 x16.

API Support: The RTX A5000 Mobile supports DirectX 12 Ultimate (12_2) and Vulkan 1.4. The R9 M390X supports DirectX 12 (12_0) and Vulkan 1.2.170. Both support OpenGL 4.6.

Release Date: The RTX A5000 Mobile was released in April 2021. The R9 M390X was released in May 2015.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA RTX A5000 Mobile has an average benchmark score of 24,763, while the AMD Radeon R9 M390X has an average score of 20,662.

Q: How large is the performance gap in the shared Vulkan test?

A: The RTX A5000 Mobile scores 88,144 in Geekbench Vulkan, which is 420% higher than the R9 M390X score of 16,951.

Q: What are the memory specifications for each card?

A: The RTX A5000 Mobile has 16 GB of GDDR6 on a 256-bit bus with 448.0 GB/s bandwidth. The R9 M390X has 4 GB of GDDR5 on a 256-bit bus with 160.0 GB/s bandwidth.

Q: Does the R9 M390X support ray tracing or tensor cores?

A: No. The R9 M390X has no recorded RT cores or tensor cores. The RTX A5000 Mobile has 48 RT cores and 192 tensor cores.

Q: How do the transistor counts compare?

A: The RTX A5000 Mobile has 17,400 million transistors, while the R9 M390X has 5,000 million transistors. The die sizes are 392 mm² and 366 mm², respectively.

Q: What is the TDP difference between the two GPUs?

A: The RTX A5000 Mobile has a TDP of 150 W, while the R9 M390X has a TDP of 75 W. The AMD part is also specified as an MXM module.

Q: Which GPU has better API support?

A: The RTX A5000 Mobile supports DirectX 12 Ultimate (12_2) and Vulkan 1.4. The R9 M390X supports DirectX 12 (12_0) and Vulkan 1.2.170. Both support OpenGL 4.6.