AMD Radeon Pro 580X vs AMD Radeon RX 590 GME Comparison

Head-to-Head Benchmarks

The recorded data shows a split decision between these two AMD GPUs, with each claiming one benchmark victory. In Geekbench OpenCL, the AMD Radeon Pro 580X posts a score of 36,426 against the RX 590 GME's 36,294, a margin of just 0.4%. This is effectively a statistical tie, as the delta falls well within run-to-run variance for most workloads. The Pro 580X's edge here, while slim, does suggest that its lower clock speeds are not a handicap in compute-oriented OpenCL tasks, likely due to identical architecture and shading resources.

The more dramatic result appears in Geekbench Vulkan, where the RX 590 GME delivers 60,508 versus the Pro 580X's 40,115. That represents a 33.7% advantage for the RX 590 GME, a substantial gap that flips the overall head-to-head record to one win apiece. The Vulkan delta is far too large to attribute to clock differences alone, which points to driver optimization or thermal behavior under sustained API-level workloads. The Pro 580X's OpenCL win, by contrast, is narrow enough that it could reverse with different driver versions.

Contextualizing these scores against their nearest rivals helps clarify what each card is actually competing with. The Pro 580X's average benchmark score of 38,706 places it within 0% of the NVIDIA GeForce MX570 A (38,691), 0.9% ahead of the RTX 5080 Mobile (38,349), and 1.1% ahead of the MX570 (38,299). It also sits 1% behind the AMD Radeon Pro 575X (39,116). This cluster of scores indicates the Pro 580X is performing at a level consistent with mid-range mobile and entry desktop parts from NVIDIA's recent lineups.

The RX 590 GME's average benchmark score of 32,601 tells a different story. It is 0.2% ahead of the AMD FirePro S9300 X2 (32,540), 0.4% ahead of the Radeon RX 7900 GRE (32,456), and 0.7% ahead of the FirePro S10000 (32,388). It trails the NVIDIA T600 Mobile (32,849) by 0.8%. Notably, the RX 590 GME's average is dragged down by its 3DMark Steel Nomad DX12 score of 1,001, which is not a workload the Pro 580X was tested on. When isolating the shared Geekbench tests, the RX 590 GME's Vulkan result is the standout, while its OpenCL score is nearly identical to the Pro 580X.

The percentile rankings reinforce this mixed picture. The Pro 580X sits at the 82nd percentile among all GPUs, while the RX 590 GME sits at the 77th. That five-point percentile gap aligns with the average scores, but the Vulkan swing shows that API choice can radically reorder their relative positions. In OpenCL they are inseparable, in Vulkan the RX 590 GME is clearly superior.

Architecture Differences

Both cards are built on GCN 4.0 architecture using the same 14 nm process at GlobalFoundries, and both use the same transistor count of 5,700 million on a 232 mm² die. This results in an identical transistor density of 24.6M per mm². The fundamental silicon is therefore the same, but the implementation details diverge in ways that explain the benchmark behavior.

The Pro 580X uses the Ellesmere chip, while the RX 590 GME uses Polaris 20. Both are derivatives of the same GCN 4.0 design family, but the RX 590 GME carries higher factory clock settings. Its base clock is 1257 MHz and boost clock is 1420 MHz, compared to the Pro 580X's 1100 MHz base and 1200 MHz boost. That is a 15% higher base clock and an 18% higher boost clock. Memory clocks also differ: the RX 590 GME runs at 2000 MHz (8 Gbps effective) versus the Pro 580X's 1710 MHz (6.8 Gbps effective). The resulting memory bandwidth is 256.0 GB/s for the RX 590 GME versus 218.9 GB/s for the Pro 580X, a 17% advantage.

Both cards have identical compute resources: 2304 shading units, 144 texture mapping units, and 32 raster operation units. Neither has ray tracing cores or tensor cores. The higher clocks on the RX 590 GME translate directly to higher peak rates. Its pixel rate is 45.44 GPixel/s versus 38.40 GPixel/s on the Pro 580X. Texture rate is 204.5 GTexel/s versus 172.8 GTexel/s. FP32 throughput is 6.543 TFLOPS versus 5.530 TFLOPS, and FP16 is identical at a 1:1 ratio for both cards.

The power profiles differ as well. The Pro 580X is rated at 185 W TDP, while the RX 590 GME is rated at 175 W. Despite lower clocks, the Pro 580X draws slightly more power, which may reflect its integration into Apple MPX bus systems rather than standard PCIe. The RX 590 GME uses a PCIe 3.0 x16 interface and requires a single 8-pin power connector with a suggested 450 W PSU. The Pro 580X is an IGP (integrated graphics processor) form factor with an Apple MPX bus interface, meaning it is designed for specific Mac Pro configurations rather than general PC builds.

Display outputs also differ. The Pro 580X offers 2x HDMI 2.0b, while the RX 590 GME provides 1x HDMI 2.0b and 3x DisplayPort 1.4a. Both support DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The RX 590 GME's physical dimensions are recorded at 241 mm (9.5 inches) in length with a dual-slot width, whereas the Pro 580X's dimensions are not listed.

FAQ

Q: Which card has the higher average benchmark score?

A: The AMD Radeon Pro 580X has an average benchmark score of 38,706, which is 6,105 points higher than the RX 590 GME's 32,601. This places the Pro 580X at the 82nd percentile and the RX 590 GME at the 77th percentile among all GPUs.

Q: How do the two cards compare in OpenCL performance?

A: They are nearly identical in Geekbench OpenCL. The Pro 580X scores 36,426 and the RX 590 GME scores 36,294, a difference of only 0.4% in favor of the Pro 580X.

Q: Which card wins in Vulkan workloads?

A: The RX 590 GME wins decisively in Geekbench Vulkan with a score of 60,508, which is 33.7% higher than the Pro 580X's 40,115.

Q: Do the cards have different memory bandwidth?

A: Yes. The RX 590 GME has 256.0 GB/s of memory bandwidth from its 2000 MHz GDDR5 memory, while the Pro 580X has 218.9 GB/s from its 1710 MHz memory. Both use 8 GB of GDDR5 on a 256-bit bus.

Q: Are the compute units the same on both cards?

A: Yes. Both have 2304 shading units, 144 texture mapping units, and 32 ROPs. The difference is purely in clock speeds, not in the count of execution resources.

Q: What are the power connector requirements?

A: The RX 590 GME requires a single 8-pin power connector and a suggested 450 W PSU. The Pro 580X has no listed power connectors, as it uses an Apple MPX bus interface in an IGP form factor.

The Verdict

The data presents two cards that are architectural twins with different operating points. The Pro 580X is the higher-scoring card in aggregate benchmarks, with its 82nd percentile ranking and average score of 38,706 beating the RX 590 GME's 77th percentile and 32,601 average. However, the RX 590 GME's Vulkan performance is so dominant that it cannot be ignored.

For users whose workloads are primarily Vulkan-based, the RX 590 GME is the clear choice. Its 33.7% lead in Geekbench Vulkan is the largest recorded difference between the two cards, and its higher clocks (1257 MHz base, 1420 MHz boost) plus faster memory (256.0 GB/s) provide a theoretical basis for this advantage. The RX 590 GME also offers more display outputs (3x DisplayPort 1.4a plus 1x HDMI 2.0b) and uses a standard PCIe 3.0 x16 interface, making it compatible with typical desktop motherboards.

The Pro 580X, conversely, is the better pick for OpenCL compute tasks. Its 0.4% OpenCL lead is marginal, but its overall average score is 18.7% higher than the RX 590 GME's. This is driven by strong Vulkan performance of its own (40,115) combined with a solid OpenCL showing. The Pro 580X's Apple MPX interface and IGP form factor mean it is not a general-purpose retail card, but within its intended ecosystem it delivers competitive numbers.

The power draw is also worth noting. The Pro 580X has a higher TDP of 185 W despite lower clocks, while the RX 590 GME achieves higher performance at 175 W. This suggests the RX 590 GME has better power efficiency per unit of raw throughput, though the Pro 580X's integrated design may have different thermal constraints.

Neither card is a clear winner across all metrics. The head-to-head record is tied at one win each. The decision hinges on API preference and system compatibility. Vulkan users with standard PC slots should choose the RX 590 GME. OpenCL-centric workflows in Apple environments point to the Pro 580X.

Specification Differences

• Chip: Ellesmere (Pro 580X) versus Polaris 20 (RX 590 GME)
• Generation: Radeon Pro Mac (500X Series) versus Polaris (RX 500)
• Base clock: 1100 MHz versus 1257 MHz
• Boost clock: 1200 MHz versus 1420 MHz
• Memory clock: 1710 MHz (6.8 Gbps effective) versus 2000 MHz (8 Gbps effective)
• Bandwidth: 218.9 GB/s versus 256.0 GB/s
• Pixel rate: 38.40 GPixel/s versus 45.44 GPixel/s
• Texture rate: 172.8 GTexel/s versus 204.5 GTexel/s
• FP32: 5.530 TFLOPS versus 6.543 TFLOPS
• FP16: 5.530 TFLOPS (1:1) versus 6.543 TFLOPS (1:1)
• TDP: 185 W versus 175 W
• Slot width: IGP versus Dual-slot
• Power connectors: None listed versus 1x 8-pin
• Suggested PSU: None listed versus 450 W
• Bus interface: Apple MPX versus PCIe 3.0 x16
• Display outputs: 2x HDMI 2.0b versus 1x HDMI 2.0b, 3x DisplayPort 1.4a
• Length: Not listed versus 241 mm (9.5 inches)
• Release date: 2019-03-17 versus 2020-03-08
• Predecessor: None versus Arctic Islands
• Successor: None versus Vega
• Production status: End-of-life for both
• Launch MSRP: Not available for either

The process node, foundry, transistor count, die size, transistor density, memory size (8 GB), memory type (GDDR5), memory bus width (256 bit), shading units (2304), TMUs (144), ROPs (32), DirectX version, OpenGL version, and Vulkan version are identical.

Where Each One Wins

AMD Radeon Pro 580X wins in:

• Aggregate benchmark scoring: average of 38,706 versus 32,601
• Percentile ranking: 82nd versus 77th
• OpenCL performance: 36,426 versus 36,294, a 0.4% margin
• Apple MPX ecosystem compatibility: IGP form factor with 2x HDMI 2.0b outputs
• Higher TDP headroom at 185 W, which may allow sustained operation in certain chassis designs

AMD Radeon RX 590 GME wins in:

• Vulkan performance: 60,508 versus 40,115, a 33.7% advantage
• Clock speeds: 1257 MHz base and 1420 MHz boost versus 1100 MHz and 1200 MHz
• Memory bandwidth: 256.0 GB/s versus 218.9 GB/s
• Pixel rate: 45.44 GPixel/s versus 38.40 GPixel/s
• Texture rate: 204.5 GTexel/s versus 172.8 GTexel/s
• FP32 and FP16 throughput: 6.543 TFLOPS versus 5.530 TFLOPS
• Power efficiency: 175 W TDP for higher performance, versus 185 W for lower performance
• Standard PCIe 3.0 x16 compatibility with a single 8-pin connector
• Display output flexibility: 3x DisplayPort 1.4a plus 1x HDMI 2.0b
• Physical size: 241 mm length, dual-slot design for standard cases

The use-case split is clear. The Pro 580X serves OpenCL compute in Apple hardware, where its MPX bus integration and competitive scores matter more than raw clock speed. The RX 590 GME serves Vulkan gaming and general desktop use, where its higher clocks, faster memory, and standard PCIe interface deliver a decisive performance edge in the one workload where they directly compete.