AMD Radeon R9 M390X vs AMD Radeon RX 5700 Comparison

AMD
RADEON

AMD Radeon R9 M390X

CORE STATE Amethyst
VRAM 4 GB
CLOCK SPEED —
TDP 75 W
BUS WIDTH 256 bit
ARCHITECTURE GCN 3.0
nm
PROCESS 28 nm
LAUNCH DATE 2015
VS
AMD
RADEON

Radeon RX 5700

CORE STATE Navi 10
VRAM 8 GB
CLOCK SPEED 1725 MHz
TDP 180 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 1.0
nm
PROCESS 7 nm
LAUNCH DATE 2019

PERFORMANCE BENCHMARKS

geekbench_metal
24,373
86,079
geekbench_vulkan
16,951
64,166
3dmark_3dmark_steel_nomad_dx12
N/A
1,862
geekbench_opencl
N/A
69,603
passmark_directx_10
N/A
87
passmark_directx_11
N/A
101
passmark_directx_12
N/A
54
passmark_directx_9
N/A
209
passmark_g2d
N/A
877
passmark_g3d
N/A
14,314
passmark_gpu_compute
N/A
6,517

Analysis: AMD Radeon R9 M390X vs AMD Radeon RX 5700

The AMD Radeon RX 5700 and the AMD Radeon R9 M390X represent two distinct eras of graphics technology, with the data showing a decisive generational gap. The RX 5700, built on the RDNA 1.0 architecture, is a desktop-focused part from the Radeon RX 5000 series, while the R9 M390X is a mobile-oriented chip from the earlier GCN 3.0 generation. Benchmark results indicate the RX 5700 holds an overwhelming performance advantage in the tests where both were measured, yet the R9 M390X still holds relevance in its specific mobile niche, as reflected by its similar percentile ranking among all GPUs.

Where Each One Wins

The benchmark data presents a clear, one-sided picture in terms of raw performance. The AMD Radeon RX 5700 wins both head-to-head benchmark comparisons against the AMD Radeon R9 M390X. In the Geekbench Metal test, the RX 5700 scores 86079, which is 253.2% higher than the R9 M390X's 24373. Similarly, in the Geekbench Vulkan test, the RX 5700 achieves 64166, a 278.5% improvement over the R9 M390X's 16951. There are no benchmark wins for the R9 M390X in this data set.

However, the R9 M390X's "win" is not in raw speed but in its physical profile and power envelope, which makes it suitable for a different class of machine. The R9 M390X is an MXM Module with a 75 W TDP and no power connectors, indicating it is designed for portable devices where space and heat are constrained. The RX 5700, by contrast, is a dual-slot card with a 180 W TDP and requires both a 6-pin and an 8-pin power connector. Data shows the R9 M390X has a 66th percentile ranking among all GPUs, while the RX 5700 sits at the 67th percentile. This near-identical percentile suggests that while the R9 M390X is far slower in absolute terms, it was a high-performing part for its intended mobile use case, whereas the RX 5700 is a mid-to-high-tier desktop solution.

FAQ

Q: How much faster is the AMD Radeon RX 5700 than the R9 M390X in the Geekbench Metal benchmark?

A: The RX 5700 scores 86079, which is 253.2% higher than the R9 M390X's score of 24373.

Q: Which GPU has the higher average benchmark score?

A: The RX 5700 has an average benchmark score of 22170, while the R9 M390X has an average of 20662. The RX 5700's closest rival, the AMD Radeon RX 6700S, scores 22154, a delta of 0.1%, while the R9 M390X's closest rival, the AMD Radeon RX 5600 XT, scores 20713, a delta of -0.2%.

Q: Are these GPUs on the same manufacturing process?

A: No. The RX 5700 uses a 7 nm process at TSMC, while the R9 M390X uses a 28 nm process, also at TSMC.

Q: What is the difference in memory bandwidth between the two cards?

A: The RX 5700 has a memory bandwidth of 448.0 GB/s using 8 GB of GDDR6 memory on a 256-bit bus. The R9 M390X has 160.0 GB/s of bandwidth with 4 GB of GDDR5 memory on a 256-bit bus.

Q: Which GPU has a higher pixel rate?

A: The RX 5700 has a pixel rate of 110.4 GPixel/s, which is significantly higher than the R9 M390X's 23.14 GPixel/s.

Q: Do both GPUs support the same version of Vulkan?

A: No. The RX 5700 supports Vulkan 1.4, while the R9 M390X supports Vulkan 1.2.170.

Head-to-Head Benchmarks

The head-to-head data is limited to two tests, but the results are stark. In the Geekbench Metal benchmark, the AMD Radeon RX 5700 posts a score of 86079, absolutely dwarfing the AMD Radeon R9 M390X's 24373. This translates to a delta of 253.2% in favor of the RX 5700. For context, this is not a marginal lead; it is a multi-generational leap in compute capability. The RX 5700's Metal score is more than triple that of the R9 M390X, indicating that in any Metal-accelerated workload, the newer card will be vastly superior.

The second test, Geekbench Vulkan, shows an even larger relative gap. The RX 5700 scores 64166, while the R9 M390X scores 16951. The delta here is 278.5%, meaning the RX 5700 is nearly four times faster in this API. This suggests that the architectural improvements in RDNA 1.0 over GCN 3.0 are particularly effective in modern, low-level graphics APIs. The R9 M390X's Vulkan score of 16951 is less than the RX 5700's OpenCL score of 69603, further underscoring the performance chasm. While the R9 M390X shows a strong showing in Metal relative to its Vulkan score, the RX 5700 is simply in a different performance class in both tests.

Specification Differences

The specification sheets for these two GPUs reveal fundamental differences in their design goals. The most obvious is process node: the RX 5700 is built on a 7 nm process, while the R9 M390X uses a 28 nm process. This leads to a massive difference in transistor density, with the RX 5700 packing 41.0M transistors per mm² versus the R9 M390X's 13.7M per mm². The RX 5700 has 10,300 million transistors on a 251 mm² die, while the R9 M390X has 5,000 million transistors on a larger 366 mm² die.

Clock speeds are another major differentiator. The RX 5700 has a base clock of 1465 MHz, a game clock of 1625 MHz, and a boost clock of 1725 MHz. The R9 M390X's base, game, and boost clocks are all listed as null in the data, though its memory clock is 1250 MHz (5 Gbps effective) compared to the RX 5700's 1750 MHz (14 Gbps effective). Memory capacity and type also differ: the RX 5700 has 8 GB of GDDR6, while the R9 M390X has 4 GB of GDDR5. Both use a 256-bit bus, but the RX 5700's bandwidth of 448.0 GB/s is nearly three times the R9 M390X's 160.0 GB/s.

Compute resources show the RX 5700 with 2304 shading units, 144 TMUs, and 64 ROPs. The R9 M390X has 2048 shading units, 128 TMUs, and only 32 ROPs. This ROP difference is significant for fill-rate-bound scenarios. The RX 5700's texture rate is 248.4 GTexel/s versus the R9 M390X's 92.54 GTexel/s. Power requirements are also starkly different: the RX 5700 has a 180 W TDP and requires a 450 W suggested PSU, while the R9 M390X has a 75 W TDP and needs no external power connectors. The RX 5700 uses PCIe 4.0 x16, while the R9 M390X uses PCIe 3.0 x16.

Architecture Differences

The architectural gap between these two GPUs is the root cause of their performance disparity. The RX 5700 is based on the RDNA 1.0 architecture, a ground-up redesign intended to improve efficiency and performance per clock. The R9 M390X uses the older GCN 3.0 architecture, which was designed for a different era of graphics workloads. The RX 5700's chip is Navi 10, while the R9 M390X uses the Amethyst chip. The RX 5700's generation is listed as "Navi (RX 5000)", while the R9 M390X is from the "Gem System (R9 M300)" generation.

The process node difference alone—7 nm versus 28 nm—explains a significant portion of the efficiency and performance gap. The RDNA 1.0 architecture also introduced a 2:1 FP16 ratio, with the RX 5700 achieving 15.90 TFLOPS FP16 versus its 7.949 TFLOPS FP32. The R9 M390X has a 1:1 ratio, with 2.961 TFLOPS for both FP16 and FP32. This indicates that the RX 5700 has dedicated hardware for half-precision compute that the R9 M390X lacks. The RX 5700 also supports PCIe 4.0, doubling the bus bandwidth available to the R9 M390X's PCIe 3.0 interface.

Feature support also differs. The RX 5700 supports DirectX 12 (12_1) and Vulkan 1.4, while the R9 M390X supports DirectX 12 (12_0) and Vulkan 1.2.170. Both support OpenGL 4.6, but the newer Vulkan version on the RX 5700 suggests better support for recent games and applications. The RX 5700 also features a dual-slot design with display outputs of 1x HDMI 2.0b and 3x DisplayPort 1.4a, while the R9 M390X is an MXM Module with display outputs that are "Portable Device Dependent," meaning they are determined by the laptop manufacturer.

The Verdict

The data is unambiguous: the AMD Radeon RX 5700 is the superior performer in every measurable benchmark category. Its scores in Geekbench Metal and Vulkan are 253.2% and 278.5% higher, respectively, than the R9 M390X. Its average benchmark score of 22170 is 1508 points higher than the R9 M390X's 20662. The RX 5700 also has a significantly higher pixel rate (110.4 GPixel/s vs 23.14 GPixel/s), texture rate (248.4 GTexel/s vs 92.54 GTexel/s), and FP32 throughput (7.949 TFLOPS vs 2.961 TFLOPS). The RX 5700 was released on 2019-07-06 with a launch MSRP of 349 USD, while the R9 M390X was released on 2015-05-04 with no launch MSRP listed.

Who should pick which? The answer depends entirely on the platform. For a desktop user building a new system or upgrading a PCIe 4.0-capable motherboard, the RX 5700 is the clear choice. Its 8 GB of GDDR6 memory, higher bandwidth, and modern RDNA 1.0 architecture make it suitable for current gaming and compute workloads. The data shows it sits at the 67th percentile of all GPUs, putting it in the same league as the NVIDIA GeForce RTX 5060 Mobile (which it trails by 1.2%) and the AMD Radeon RX 7700 XT (which it trails by 1.7%).

For a user with a legacy laptop that requires an MXM Module upgrade, the R9 M390X is the only option in this comparison, despite its vastly lower performance. Its 75 W TDP and lack of power connectors make it compatible with systems that cannot support a discrete desktop card. While its 66th percentile ranking is remarkably close to the RX 5700's 67th percentile, this is a reflection of its standing among all mobile and desktop GPUs, not an indication of comparable speed. The R9 M390X is a product of its time, and the data suggests it was a strong mobile option in its generation, but it cannot compete with the architectural and process node advantages of the RX 5700.

DETAILED SPECIFICATIONS

SPECIFICATION
R9 M390X
RX 5700
Core Specs
Shading Units
2,048
2,304 +12.5%
Shaders
2,048
2,304 +12.5%
TMUs
128
144 +12.5%
ROPs
32
64 +100.0%
Compute Units
32
36 +12.5%
Clocks
Base Clock
—
1465 MHz
Boost Clock
—
1725 MHz
GPU Clock
723 MHz
—
Game Clock
—
1625 MHz
Memory Clock
1250 MHz 5 Gbps effective
1750 MHz 14 Gbps effective
Memory
Memory Size
4 GB
8 GB
VRAM (MB)
4,096
8,192 +100.0%
Memory Type
GDDR5
GDDR6
Memory Bus
256 bit
256 bit
Bandwidth
160.0 GB/s
448.0 GB/s
Cache
L1 Cache
16 KB (per CU)
—
L2 Cache
512 KB
4 MB
Performance
Pixel Rate
23.14 GPixel/s
110.4 GPixel/s
Texture Rate
92.54 GTexel/s
248.4 GTexel/s
FP32 (TFLOPS)
2.961 TFLOPS
7.949 TFLOPS
FP64 (TFLOPS)
185.1 GFLOPS (1:16)
496.8 GFLOPS (1:16)
FP16 (TFLOPS)
2.961 TFLOPS (1:1)
15.90 TFLOPS (2:1)
Power
TDP
75 W
180 W
TDP (W)
75
180 +140.0%
Suggested PSU
—
450 W
Power Connectors
None
1x 6-pin + 1x 8-pin
Architecture
Architecture
GCN 3.0
RDNA 1.0
GPU Name
Amethyst
Navi 10
Generation
Gem System (R9 M300)
Navi (RX 5000)
Process Size
28 nm
7 nm
Transistors
5,000 million
10,300 million
Die Size
366 mm²
251 mm²
Foundry
TSMC
TSMC
Density
13.7M / mm²
41.0M / mm²
API Support
DirectX
12 (12_0)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.4
OpenCL
2.1
2.1
Shader Model
6.5
6.8
Physical
Slot Width
MXM Module
Dual-slot
Length
—
268 mm 10.6 inches
Height
—
111 mm 4.4 inches
Outputs
Portable Device Dependent
1x HDMI 2.0b3x DisplayPort 1.4a
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Other
Launch Price
—
349 USD
Production
End-of-life
End-of-life
Predecessor
Solar System
Vega
Successor
Polaris Mobile
Navi II
View Radeon R9 M390X Details View Radeon RX 5700 Details