AMD Radeon R9 M390X vs AMD Radeon RX 5600 XT Comparison
AMD Radeon R9 M390X
Radeon RX 5600 XT
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon R9 M390X vs AMD Radeon RX 5600 XT
The AMD Radeon RX 5600 XT and the AMD Radeon R9 M390X represent two distinct eras of AMD graphics technology, with the benchmark data placing them surprisingly close in overall average score. The RX 5600 XT achieves an average benchmark score of 20713, while the R9 M390X sits at 20662, a negligible 0.2% difference. However, this aggregate similarity masks a stark contrast in individual workload performance, particularly in modern API tests where the newer architecture demonstrates a decisive advantage.
Head-to-Head Benchmarks
The direct comparison between these two cards is limited to two benchmark tests, but the results are nothing short of dramatic. In Geekbench Metal, the RX 5600 XT scores 80376, which is a staggering 229.8% higher than the R9 M390X's 24373. This isn't a marginal improvement; it represents a more than threefold increase in raw compute performance under Apple's Metal API. The delta is so large that it effectively places the R9 M390X in a different performance tier, despite their similar aggregate scores.
The gap widens even further in Geekbench Vulkan. Here, the RX 5600 XT delivers a score of 56218, while the R9 M390X manages only 16951. The deltaPct of 231.7% indicates that the newer card is nearly 2.3 times faster in this cross-platform graphics API. This performance disparity is particularly telling because Vulkan is a low-overhead API that scales well with architectural efficiency, and the RDNA 1.0 architecture of the RX 5600 XT clearly exploits this far better than the older GCN 3.0 design.
It is importantly the R9 M390X's performance profile is heavily skewed by its limited benchmark presence. With only Geekbench Metal and Vulkan results available, its average score of 20662 is calculated from just two data points. The RX 5600 XT, by contrast, has a much broader benchmark footprint, including PassMark tests where it scores 13457 in G3D and 6296 in GPU Compute. This means the R9 M390X's aggregate standing is artificially propped up by the absence of more demanding DirectX workloads, where the RX 5600 XT's 7.188 TFLOPS FP32 throughput would likely widen the gap even further.
The nearest rival data confirms the overall parity, with the RX 5600 XT sitting just 0.2% ahead of the R9 M390X. Interestingly, both cards share the same percentile ranking of 66 among all GPUs, indicating they occupy a similar position in the overall performance distribution. However, the Intel Arc A750, Arc B570, and NVIDIA RTX 3070 Mobile all cluster within 0.9% of the RX 5600 XT's score, suggesting that the R9 M390X's inclusion in this group is more a function of its limited test suite than genuine competitive equivalence.
FAQ
Q: Which card is faster in Geekbench Metal?
A: The AMD Radeon RX 5600 XT is vastly faster, scoring 80376 compared to the R9 M390X's 24373, a 229.8% advantage.
Q: How do the two cards compare in Vulkan performance?
A: The RX 5600 XT leads by 231.7%, with a score of 56218 versus 16951 for the R9 M390X. This is the largest win for either card in the head-to-head data.
Q: Are these cards in the same performance percentile?
A: Yes, both the RX 5600 XT and the R9 M390X have a percentileVsAllGpus of 66, meaning they outperform 66% of all GPUs in the database.
Q: What is the average benchmark score difference between them?
A: The RX 5600 XT has an average score of 20713, while the R9 M390X scores 20662. The RX 5600 XT leads by just 0.2%.
Q: Does the R9 M390X have more benchmark results than the RX 5600 XT?
A: No, the opposite is true. The RX 5600 XT has 11 benchmark results, while the R9 M390X has only 2 (Geekbench Metal and Vulkan). This makes the R9 M390X's average score less representative of overall performance.
Q: Which card wins in the head-to-head count?
A: The RX 5600 XT wins both available head-to-head tests, giving it a 2-0 record over the R9 M390X.
Architecture Differences
The architectural gap between these two GPUs is the primary driver of their divergent benchmark results. The RX 5600 XT is built on the RDNA 1.0 architecture, manufactured on a 7 nm process node at TSMC. In contrast, the R9 M390X uses the older GCN 3.0 architecture on a 28 nm process. This process shrink has profound implications: the RX 5600 XT packs 10,300 million transistors into a 251 mm² die, achieving a transistor density of 41.0M / mm². The R9 M390X, meanwhile, has only 5,000 million transistors spread across a much larger 366 mm² die, resulting in a density of just 13.7M / mm².
The memory subsystems also differ fundamentally. The RX 5600 XT uses 6 GB of GDDR6 memory on a 192-bit bus, delivering 288.0 GB/s of bandwidth. The R9 M390X uses 4 GB of GDDR5 on a wider 256-bit bus, but achieves only 160.0 GB/s due to its lower 1250 MHz memory clock (5 Gbps effective). The RX 5600 XT's memory runs at 1500 MHz (12 Gbps effective), giving it nearly double the bandwidth despite a narrower bus.
Compute resources are similarly lopsided. The RX 5600 XT features 2304 shading units, 144 texture mapping units, and 64 render output units. The R9 M390X has 2048 shaders, 128 TMUs, but only 32 ROPs. This halving of ROPs is a major bottleneck for the older card, explaining its much lower pixel rate of 23.14 GPixel/s versus the RX 5600 XT's 99.84 GPixel/s. The texture rate gap is equally stark at 92.54 GTexel/s versus 224.6 GTexel/s.
FP32 compute performance tells the story of generational improvement. The RX 5600 XT delivers 7.188 TFLOPS, while the R9 M390X manages only 2.961 TFLOPS. Notably, the R9 M390X's FP16 performance is identical at 2.961 TFLOPS (1:1 ratio), whereas the RX 5600 XT doubles its FP32 throughput to 14.38 TFLOPS for FP16 operations (2:1 ratio). This makes the newer card far more efficient in mixed-precision workloads.
Power and interface differences are also significant. The RX 5600 XT has a 150 W TDP with a dual-slot design and a single 8-pin power connector, requiring a 450 W suggested PSU. The R9 M390X is an MXM Module with a much lower 75 W TDP and no external power connectors, reflecting its mobile laptop origins. The RX 5600 XT also uses PCIe 4.0 x16, while the R9 M390X is limited to PCIe 3.0 x16.
The Verdict
The data presents a clear picture for most use cases. The AMD Radeon RX 5600 XT is the superior performer in every head-to-head test, with advantages of 229.8% in Metal and 231.7% in Vulkan. Its architectural advantages—7 nm process, nearly double the FP32 throughput, and almost double the memory bandwidth—make it the obvious choice for any modern workload that utilizes DirectX 12, Vulkan, or Metal.
However, the R9 M390X is not without its niche. Its 75 W power envelope, absence of external power connectors, and MXM form factor make it suited for portable devices where the RX 5600 XT's 150 W TDP and dual-slot cooler would be impractical. For users constrained by a laptop chassis or a low-power SFF build, the R9 M390X offers a functional, if dated, solution.
The verdict from the benchmark data is unambiguous: the RX 5600 XT is the right choice for desktop users seeking performance. The R9 M390X should only be considered for its unique form factor and power characteristics, not its compute capabilities. The 0.2% difference in average score is a statistical artifact of the R9 M390X's limited benchmark coverage; in any real-world comparison involving modern APIs, the RX 5600 XT wins decisively.
Specification Differences
| Specification | AMD Radeon RX 5600 XT | AMD Radeon R9 M390X |
|---|---|---|
| Architecture | RDNA 1.0 | GCN 3.0 |
| Process Node | 7 nm | 28 nm |
| Transistors | 10,300 million | 5,000 million |
| Die Size | 251 mm² | 366 mm² |
| Transistor Density | 41.0M / mm² | 13.7M / mm² |
| Memory Size | 6 GB | 4 GB |
| Memory Type | GDDR6 | GDDR5 |
| Memory Bus Width | 192 bit | 256 bit |
| Memory Bandwidth | 288.0 GB/s | 160.0 GB/s |
| Shading Units | 2304 | 2048 |
| TMUs | 144 | 128 |
| ROPs | 64 | 32 |
| Pixel Rate | 99.84 GPixel/s | 23.14 GPixel/s |
| Texture Rate | 224.6 GTexel/s | 92.54 GTexel/s |
| FP32 Performance | 7.188 TFLOPS | 2.961 TFLOPS |
| FP16 Performance | 14.38 TFLOPS (2:1) | 2.961 TFLOPS (1:1) |
| TDP | 150 W | 75 W |
| Slot Width | Dual-slot | MXM Module |
| Power Connectors | 1x 8-pin | None |
| Suggested PSU | 450 W | Not specified |
| Bus Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| DirectX Support | 12 (12_1) | 12 (12_0) |
| Vulkan Support | 1.4 | 1.2.170 |
| Release Date | 2020-01-20 | 2015-05-04 |