AMD FirePro S7150 vs AMD Radeon RX 590 GME Comparison

AMD
RADEON

AMD FirePro S7150

CORE STATE Tonga
VRAM 8 GB
CLOCK SPEED —
TDP 150 W
BUS WIDTH 256 bit
ARCHITECTURE GCN 3.0
nm
PROCESS 28 nm
LAUNCH DATE 2016
VS
AMD
RADEON

Radeon RX 590 GME

CORE STATE Polaris 20
VRAM 8 GB
CLOCK SPEED 1420 MHz
TDP 175 W
BUS WIDTH 256 bit
ARCHITECTURE GCN 4.0
nm
PROCESS 14 nm
LAUNCH DATE 2020

PERFORMANCE BENCHMARKS

geekbench_opencl
26,543
36,294
geekbench_vulkan
29,690
60,508
3dmark_3dmark_steel_nomad_dx12
N/A
1,001

Analysis: AMD FirePro S7150 vs AMD Radeon RX 590 GME

Where Each One Wins

The recorded benchmark data splits cleanly between these two AMD cards, and the winner in both shared tests is the Radeon RX 590 GME. In the Geekbench OpenCL test, the RX 590 GME scores 36,294 against the FirePro S7150's 26,543, a 36.7% advantage. In Geekbench Vulkan, the gap is far larger: 60,508 versus 29,690, which works out to a 103.8% lead, meaning the RX 590 GME delivers more than double the Vulkan score.

That Vulkan result is the standout. A 103.8% delta is not a marginal edge; it suggests the RX 590 GME is in a different performance tier for compute workloads exposed through Vulkan. The OpenCL gap, while substantial at 36.7%, is more typical of a generational leap within the same vendor's lineup.

The FirePro S7150 has no test where it wins. Its best showing is in OpenCL, where it trails by just over a third, and its Vulkan score is less than half of the RX 590 GME's. The data does not indicate any workload category in the recorded benchmarks where the S7150 takes the lead.

For use-case planning, the RX 590 GME is the clear choice for any application that relies on OpenCL or Vulkan acceleration. The S7150, being a server-oriented FirePro part with no display outputs, still delivers respectable absolute scores, but it is consistently behind in every measured test. The percentile ranks echo this: the RX 590 GME sits at the 77th percentile among all GPUs, while the S7150 sits at the 73rd.

Architecture Differences

The two cards come from different GCN generations and different foundries. The Radeon RX 590 GME uses the Polaris 20 chip built on GCN 4.0 at GlobalFoundries' 14 nm process. The FirePro S7150 uses the Tonga chip on GCN 3.0, manufactured by TSMC on a 28 nm process. That process gap is significant: 14 nm versus 28 nm, and it helps explain the RX 590 GME's higher clock rates and efficiency.

Transistor counts differ as well. The RX 590 GME packs 5,700 million transistors on a 232 mm² die, giving a transistor density of 24.6M per mm². The FirePro S7150 has 5,000 million transistors spread across a much larger 366 mm² die, resulting in just 13.7M per mm². The newer process node allows Polaris 20 to fit more transistors in a smaller area.

Clock speeds tell a similar story. The RX 590 GME has a base clock of 1257 MHz and a boost clock of 1420 MHz. The S7150's base and boost clocks are not recorded in the database, but its memory clock is 1250 MHz with 5 Gbps effective, compared to the RX 590 GME's 2000 MHz memory clock at 8 Gbps effective. That memory speed difference feeds directly into bandwidth: 256.0 GB/s for the RX 590 GME versus 160.0 GB/s for the S7150.

Both cards have 8 GB of GDDR5 on a 256-bit bus, but the RX 590 GME's faster memory gives it a 96 GB/s bandwidth advantage. Compute resources also favor the RX 590 GME: 2304 shading units, 144 texture mapping units, and 32 ROPs, against the S7150's 2048 shading units, 128 TMUs, and 32 ROPs. The pixel rate is 45.44 GPixel/s for the RX 590 GME versus 29.44 GPixel/s for the S7150, and the texture rate is 204.5 GTexel/s versus 117.8 GTexel/s.

FP32 throughput is 6.543 TFLOPS for the RX 590 GME versus 3.768 TFLOPS for the S7150. The S7150 has a notable FP16 capability at 7.537 TFLOPS with a 2:1 ratio, while the RX 590 GME does FP16 at the same 6.543 TFLOPS as FP32, a 1:1 ratio. The S7150's higher FP16 rate is its only raw compute advantage, but it does not appear in the recorded benchmark results.

Power and physical design differ sharply. The RX 590 GME is a dual-slot card with a 175 W TDP and a single 8-pin power connector. The S7150 is a single-slot card with a 150 W TDP and a single 6-pin connector. Both recommend a 450 W power supply. The S7150 has no display outputs, reflecting its server role, while the RX 590 GME offers 1x HDMI 2.0b and 3x DisplayPort 1.4a. Both use PCIe 3.0 x16.

API support is close. Both support DirectX 12 (12_0) and OpenGL 4.6. The RX 590 GME supports Vulkan 1.3, while the S7150 supports Vulkan 1.2.170. The S7150 was released earlier, on 2016-01-31, and the RX 590 GME on 2020-03-08. Both are end-of-life. The RX 590 GME's predecessor is Arctic Islands and its successor is Vega; the S7150's predecessor is FirePro Terascale and its successor is Radeon Pro GCN.

Head-to-Head Benchmarks

The database contains two direct comparison tests between the RX 590 GME and the S7150, and both go to the RX 590 GME.

In Geekbench OpenCL, the RX 590 GME scores 36,294 against the S7150's 26,543. That is a 36.7% delta. For context, the RX 590 GME's average benchmark score across all tests is 32,601, and its nearest rival, the AMD FirePro S9300 X2, scores 32,540, just 0.2% behind. The S7150's average is 28,117, with its nearest rival, the NVIDIA GeForce GTX 980 Ti, at 28,020, a 0.3% gap.

In Geekbench Vulkan, the RX 590 GME scores 60,508, more than double the S7150's 29,690. The delta is 103.8%. This is the largest margin in the head-to-head set. The RX 590 GME's Vulkan score alone is higher than its own OpenCL score by a wide margin, and it is nearly double the S7150's OpenCL result.

Looking at the rival fields, the RX 590 GME's nearest competitors are all within a narrow band. The FirePro S9300 X2 is 0.2% behind, the Radeon RX 7900 GRE is 0.4% behind, the FirePro S10000 is 0.7% behind, and the NVIDIA T600 Mobile is 0.8% ahead. The S7150's rivals are similarly tight: the GTX 980 Ti is 0.3% ahead, the Radeon Pro W5500X is 0.5% ahead, the Radeon RX 7800M is 0.8% ahead, and the Radeon Pro Vega 20 is 1% ahead.

These rival deltas show that both cards sit in competitive segments, but the RX 590 GME's absolute scores are roughly 15% to 20% higher than the S7150's across averages. In the direct head-to-head tests, the RX 590 GME's wins are decisive, especially in Vulkan where the 103.8% delta dwarfs any of the single-digit rival gaps.

FAQ

Q: Which card wins in Geekbench OpenCL?

A: The AMD Radeon RX 590 GME wins with a score of 36,294 versus 26,543 for the AMD FirePro S7150, a 36.7% advantage.

Q: How large is the Vulkan performance gap?

A: The RX 590 GME scores 60,508 in Geekbench Vulkan, while the S7150 scores 29,690, giving the RX 590 GME a 103.8% lead.

Q: Do both cards have the same memory configuration?

A: Yes, both have 8 GB of GDDR5 on a 256-bit bus, but the RX 590 GME has 256.0 GB/s bandwidth while the S7150 has 160.0 GB/s.

Q: What is the process node difference?

A: The RX 590 GME uses a 14 nm process at GlobalFoundries, while the S7150 uses a 28 nm process at TSMC.

Q: Does the FirePro S7150 have any display outputs?

A: No, the S7150 has no display outputs, while the RX 590 GME has 1x HDMI 2.0b and 3x DisplayPort 1.4a.

Q: Which card has higher FP32 throughput?

A: The RX 590 GME delivers 6.543 TFLOPS FP32, compared to 3.768 TFLOPS for the S7150. The S7150 does have higher FP16 at 7.537 TFLOPS, but the RX 590 GME does FP16 at 6.543 TFLOPS.

The Verdict

The data points to a single conclusion: the AMD Radeon RX 590 GME is the faster card in every recorded benchmark. Its OpenCL win is 36.7%, and its Vulkan win is 103.8%. The average benchmark score for the RX 590 GME is 32,601, versus 28,117 for the S7150, a difference of roughly 4,484 points, or about 16%.

The S7150's launch MSRP was 2,399 USD, but price considerations aside, the performance data does not favor it. The S7150 is a single-slot, 150 W server card with no display outputs, designed for compute density rather than interactive graphics. Its 7.537 TFLOPS FP16 rate is the one area where it exceeds the RX 590 GME on paper, but no recorded benchmark reflects that advantage.

The RX 590 GME is the pick for anyone needing OpenCL or Vulkan compute performance, and its dual-slot design, 175 W TDP, and display outputs make it a more versatile card overall. Its 77th percentile rank versus the S7150's 73rd confirms the score gap translates to a higher standing in the broader GPU field.

For a server deployment where single-slot density and lower power matter, the S7150 remains a functional option, but the benchmark data shows it is clearly outclassed by the newer Polaris part. The RX 590 GME wins both head-to-head tests, holds a higher average score, and sits in a higher percentile. There is no recorded scenario where the S7150 comes out ahead.

DETAILED SPECIFICATIONS

SPECIFICATION
FirePro S7150
RX 590 GME
Core Specs
Shading Units
2,048
2,304 +12.5%
Shaders
2,048
2,304 +12.5%
TMUs
128
144 +12.5%
ROPs
32
32 0.0%
Compute Units
32
36 +12.5%
Clocks
Base Clock
—
1257 MHz
Boost Clock
—
1420 MHz
GPU Clock
920 MHz
—
Memory Clock
1250 MHz 5 Gbps effective
2000 MHz 8 Gbps effective
Memory
Memory Size
8 GB
8 GB
VRAM (MB)
8,192
8,192 0.0%
Memory Type
GDDR5
GDDR5
Memory Bus
256 bit
256 bit
Bandwidth
160.0 GB/s
256.0 GB/s
Cache
L1 Cache
16 KB (per CU)
16 KB (per CU)
L2 Cache
512 KB
2 MB
Performance
Pixel Rate
29.44 GPixel/s
45.44 GPixel/s
Texture Rate
117.8 GTexel/s
204.5 GTexel/s
FP32 (TFLOPS)
3.768 TFLOPS
6.543 TFLOPS
FP64 (TFLOPS)
235.5 GFLOPS (1:16)
409.0 GFLOPS (1:16)
FP16 (TFLOPS)
7.537 TFLOPS (2:1)
6.543 TFLOPS (1:1)
Power
TDP
150 W
175 W
TDP (W)
150
175 +16.7%
Suggested PSU
450 W
450 W
Power Connectors
1x 6-pin
1x 8-pin
Architecture
Architecture
GCN 3.0
GCN 4.0
GPU Name
Tonga
Polaris 20
Generation
FirePro Server (Sx100)
Polaris (RX 500)
Process Size
28 nm
14 nm
Transistors
5,000 million
5,700 million
Die Size
366 mm²
232 mm²
Foundry
TSMC
GlobalFoundries
Density
13.7M / mm²
24.6M / mm²
API Support
DirectX
12 (12_0)
12 (12_0)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.3
OpenCL
2.1
2.1
Shader Model
6.5
6.7
Physical
Slot Width
Single-slot
Dual-slot
Length
241 mm 9.5 inches
241 mm 9.5 inches
Height
111 mm 4.4 inches
—
Outputs
No outputs
1x HDMI 2.0b3x DisplayPort 1.4a
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Launch Price
2,399 USD
—
Production
End-of-life
End-of-life
Predecessor
FirePro Terascale
Arctic Islands
Successor
Radeon Pro GCN
Vega
View FirePro S7150 Details View Radeon RX 590 GME Details