AMD FirePro W5170M vs NVIDIA GeForce GTX 980 Comparison

AMD
RADEON

AMD FirePro W5170M

CORE STATE Tropo
VRAM 2 GB
CLOCK SPEED 925 MHz
TDP
BUS WIDTH 128 bit
ARCHITECTURE GCN 1.0
nm
PROCESS 28 nm
LAUNCH DATE 2014
VS
NVIDIA
GEFORCE

GeForce GTX 980

CORE STATE GM204
VRAM 4 GB
CLOCK SPEED 1216 MHz
TDP 165 W
BUS WIDTH 256 bit
ARCHITECTURE Maxwell 2.0
nm
PROCESS 28 nm
LAUNCH DATE 2014

PERFORMANCE BENCHMARKS

geekbench_opencl
8,140
34,676
geekbench_vulkan
9,050
22,543
3dmark_3dmark_steel_nomad_dx12
N/A
474
geekbench_metal
N/A
15,163
passmark_directx_10
N/A
53
passmark_directx_11
N/A
83
passmark_directx_12
N/A
46
passmark_directx_9
N/A
164
passmark_g2d
N/A
792
passmark_g3d
N/A
11,095
passmark_gpu_compute
N/A
4,753

Analysis: AMD FirePro W5170M vs NVIDIA GeForce GTX 980

The benchmark data presents a decisive matchup: the NVIDIA GeForce GTX 980 outperforms the AMD FirePro W5170M by a substantial margin in every shared test. The GTX 980’s average benchmark score of 8167 places it in the 43rd percentile of all GPUs, while the FirePro W5170M’s average of 8595 puts it at the 44th percentile, a negligible overall difference that masks the massive gap in the individual compute tests. The FirePro W5170M’s scores are buoyed by its Geekbench Vulkan result, but the GTX 980’s sheer compute throughput in OpenCL makes the comparison one-sided.

Head-to-Head Benchmarks

The most glaring disparity appears in the Geekbench OpenCL test. The GTX 980 scores 34,676, while the FirePro W5170M manages only 8,140. This translates to a deltaPct of -76.5% for the AMD part, meaning the GTX 980 delivers roughly 4.26 times the raw compute performance in this workload. This result is consistent with the underlying silicon: the GTX 980’s FP32 throughput is listed at 4.981 TFLOPS, while the FirePro W5170M is limited to 1,184.0 GFLOPS. The GTX 980 also holds a commanding lead in memory bandwidth, with 224.4 GB/s versus the FirePro’s 72.00 GB/s, which directly impacts OpenCL workloads that are often bandwidth-bound.

The Vulkan test narrows the gap but does not change the outcome. The GTX 980 scores 22,543, while the FirePro W5170M scores 9,050, a deltaPct of -59.9%. While the relative deficit for the FirePro is smaller than in OpenCL, the absolute difference remains vast—the NVIDIA part is still nearly 2.5 times faster. The FirePro’s Vulkan score of 9,050 is its stronger result relative to its own average, but it does not close the chasm created by the GTX 980’s superior hardware resources.

It is notably the FirePro W5170M’s average benchmark score (8595) is actually higher than the GTX 980’s (8167), despite losing both head-to-head tests. This occurs because the GTX 980’s average includes several lower Passmark scores, such as 46 in DirectX 12 and 53 in DirectX 10, which drag its mean down. The FirePro W5170M, with only two benchmark entries, benefits from a smaller sample set. However, in the only tests where both cards appear, the GTX 980 wins decisively. The data does not support any interpretation where the FirePro W5170M is competitive in compute-heavy scenarios.

The Verdict

The data is unambiguous: the NVIDIA GeForce GTX 980 is the superior choice for any workload represented in these benchmarks. It wins both head-to-head tests, with a 76.5% advantage in OpenCL and a 59.9% advantage in Vulkan. The FirePro W5170M does not win a single benchmark in this comparison. For users prioritizing compute performance—whether for OpenCL-based rendering, Vulkan gaming, or general GPU compute—the GTX 980 is the only rational selection based on these figures.

The FirePro W5170M’s only statistical edge is its higher average benchmark score (8595 vs. 8167), but this is misleading. The GTX 980’s average is pulled down by multiple low-scoring Passmark tests (DirectX 9: 164, DirectX 11: 83, DirectX 12: 46), which are not part of the head-to-head set. The FirePro W5170M has no such low scores in its limited benchmark history, but this does not translate into a single direct win. A buyer seeking maximum performance in the tested APIs should choose the GTX 980 without hesitation.

The GTX 980 also carries a higher percentile ranking among its own nearest rivals—it sits 0.4% ahead of the GTX 950M, 0.5% ahead of the Radeon R9 M360, and 0.8% ahead of the GeForce 945M. The FirePro W5170M, by contrast, is 1.1% behind the Quadro P2200 and only 0.4% ahead of the Intel Arc A380. Neither card is a top-tier performer globally, but the GTX 980’s head-to-head dominance over the FirePro W5170M is the defining fact.

FAQ

Q: Which GPU wins the Geekbench OpenCL benchmark?

A: The NVIDIA GeForce GTX 980 wins with a score of 34,676, compared to the AMD FirePro W5170M’s 8,140. The deltaPct is -76.5% for the FirePro W5170M.

Q: Is the AMD FirePro W5170M faster in any benchmark?

A: No. The FirePro W5170M loses both head-to-head tests: Geekbench OpenCL (8,140 vs. 34,676) and Geekbench Vulkan (9,050 vs. 22,543). It records zero wins in the comparison.

Q: How does the GTX 980 compare to its closest rivals?

A: The GTX 980’s average score of 8167 is 0.4% higher than the GeForce GTX 950M (8135), 0.5% higher than the Radeon R9 M360 (8129), and 0.8% higher than the GeForce 945M (8099).

Q: What is the GTX 980’s launch MSRP?

A: The GTX 980 has a launch MSRP of 549 USD. No pricing data is provided for the FirePro W5170M.

Q: Which GPU has a higher average benchmark score?

A: The AMD FirePro W5170M has a higher average of 8595, versus the GTX 980’s 8167. However, this is due to the GTX 980’s inclusion of low Passmark scores, not because the FirePro wins any head-to-head test.

Q: What is the GTX 980’s best individual benchmark result?

A: The GTX 980’s highest score is 34,676 in Geekbench OpenCL. Its lowest is 46 in Passmark DirectX 12.

Specification Differences

The two cards differ dramatically in nearly every measurable specification. The GTX 980 uses the GM204 chip with 5,200 million transistors on a 398 mm² die, while the FirePro W5170M uses the Tropo chip with 1,500 million transistors on a 123 mm² die. Clock speeds favor the GTX 980: its base is 1127 MHz and boost is 1216 MHz, versus the FirePro’s 900 MHz base and 925 MHz boost. Memory capacity is 4 GB for the GTX 980 and 2 GB for the FirePro W5170M, with bus widths of 256 bit and 128 bit, respectively.

The GTX 980 has 2048 shading units, 128 TMUs, and 64 ROPs, while the FirePro W5170M has 640 shading units, 40 TMUs, and 16 ROPs. Pixel rate is 77.82 GPixel/s for the GTX 980 versus 14.80 GPixel/s for the FirePro, and texture rates are 155.6 GTexel/s versus 37.00 GTexel/s. The GTX 980’s TDP is 165 W, requiring 2x 6-pin power connectors and a 450 W suggested PSU; the FirePro W5170M has no listed TDP and uses an MXM module with no power connectors. The GTX 980 is a dual-slot card measuring 267 mm in length, while the FirePro is a portable-device-dependent MXM-A (3.0) module.

Architecture Differences

The architectural gap is fundamental. The FirePro W5170M is built on GCN 1.0 architecture, while the GTX 980 uses Maxwell 2.0. Both are fabricated on a 28 nm process at TSMC, but the GTX 980’s die is more than three times larger (398 mm² vs. 123 mm²) and packs over 3.4 billion more transistors. The GTX 980’s transistor density is 13.1M / mm², slightly higher than the FirePro’s 12.2M / mm².

API support differs in DirectX and Vulkan: the GTX 980 supports DirectX 12 (12_1) and Vulkan 1.4, while the FirePro W5170M supports DirectX 12 (11_1) and Vulkan 1.2.170. Both support OpenGL 4.6. The GTX 980 has a larger memory bus (256 bit vs. 128 bit) and higher effective memory speed (7 Gbps vs. 4.5 Gbps), resulting in a bandwidth of 224.4 GB/s versus 72.00 GB/s. The GTX 980 also has a richer display output suite (1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2), whereas the FirePro’s outputs are listed as "Portable Device Dependent."

Where Each One Wins

The NVIDIA GeForce GTX 980 wins in every tested scenario. In OpenCL compute, it is 76.5% ahead, making it the clear choice for general-purpose GPU computing, scientific simulation, or any workload that leverages OpenCL acceleration. Its 4.981 TFLOPS FP32 performance and 224.4 GB/s memory bandwidth provide the raw resources needed for demanding compute tasks. In Vulkan, it is 59.9% ahead, indicating superior performance in modern graphics APIs used by contemporary games and applications.

The AMD FirePro W5170M has no benchmark wins to claim. Its only statistical advantage is its higher average score (8595 vs. 8167), which is an artifact of the GTX 980’s low Passmark results. The FirePro’s nearest rivals—Intel Arc A380, Quadro P2200, Radeon HD 8870M, and GeForce MX330—are all within a 1.6% deltaPct range, suggesting it sits in a different performance class entirely. The GTX 980, despite its lower average, is the faster card in practice. For any user comparing these two specific products, the GTX 980 is the only viable option based on the available data. The FirePro W5170M might suffice for basic portable graphics where power consumption is unknown and the MXM form factor is required, but it cannot compete with the GTX 980’s compute and memory advantages.

DETAILED SPECIFICATIONS

SPECIFICATION
FirePro W5170M
GTX 980
Core Specs
Shading Units
640
2,048 +220.0%
Shaders
640
2,048 +220.0%
TMUs
40
128 +220.0%
ROPs
16
64 +300.0%
Compute Units
10
Clocks
Base Clock
900 MHz
1127 MHz
Boost Clock
925 MHz
1216 MHz
Memory Clock
1125 MHz 4.5 Gbps effective
1753 MHz 7 Gbps effective
Memory
Memory Size
2 GB
4 GB
VRAM (MB)
2,048
4,096 +100.0%
Memory Type
GDDR5
GDDR5
Memory Bus
128 bit
256 bit
Bandwidth
72.00 GB/s
224.4 GB/s
Cache
L1 Cache
16 KB (per CU)
48 KB (per SMM)
L2 Cache
256 KB
2 MB
Performance
Pixel Rate
14.80 GPixel/s
77.82 GPixel/s
Texture Rate
37.00 GTexel/s
155.6 GTexel/s
FP32 (TFLOPS)
1,184.0 GFLOPS
4.981 TFLOPS
FP64 (TFLOPS)
74.00 GFLOPS (1:16)
155.6 GFLOPS (1:32)
Power
TDP
165 W
TDP (W)
165
Suggested PSU
450 W
Power Connectors
None
2x 6-pin
Architecture
Architecture
GCN 1.0
Maxwell 2.0
GPU Name
Tropo
GM204
Generation
FirePro Mobile (Wx100M)
GeForce 900
Process Size
28 nm
28 nm
Transistors
1,500 million
5,200 million
Die Size
123 mm²
398 mm²
Foundry
TSMC
TSMC
Density
12.2M / mm²
13.1M / mm²
API Support
DirectX
12 (11_1)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.4
OpenCL
2.1 (1.2)
3.0
CUDA
5.2
Shader Model
6.5 (5.1)
6.8
Physical
Slot Width
MXM Module
Dual-slot
Length
267 mm 10.5 inches
Height
111 mm 4.4 inches
Outputs
Portable Device Dependent
1x DVI1x HDMI 2.03x DisplayPort 1.2
Bus Interface
MXM-A (3.0)
PCIe 3.0 x16
Other
Launch Price
549 USD
Production
End-of-life
End-of-life
Predecessor
FirePro Mobility
GeForce 700
Successor
Radeon Pro Mobile
GeForce 10
View FirePro W5170M Details View GeForce GTX 980 Details