AMD Radeon HD 8730M vs NVIDIA GeForce GTX 550 Ti Comparison

AMD
RADEON

AMD Radeon HD 8730M

CORE STATE Mars
VRAM 2 GB
CLOCK SPEED 700 MHz
TDP —
BUS WIDTH 128 bit
ARCHITECTURE GCN 1.0
nm
PROCESS 28 nm
LAUNCH DATE 2013
VS
NVIDIA
GEFORCE

GeForce GTX 550 Ti

CORE STATE GF116
VRAM 1024 MB
CLOCK SPEED —
TDP 116 W
BUS WIDTH 192 bit
ARCHITECTURE Fermi 2.0
nm
PROCESS 40 nm
LAUNCH DATE 2011

PERFORMANCE BENCHMARKS

geekbench_opencl
5,955
5,731

Analysis: AMD Radeon HD 8730M vs NVIDIA GeForce GTX 550 Ti

The AMD Radeon HD 8730M and the NVIDIA GeForce GTX 550 Ti are two end-of-life graphics processors from different eras and market segments. The data shows a single head-to-head benchmark result, with the AMD Radeon HD 8730M taking a narrow victory over the NVIDIA GeForce GTX 550 Ti. This comparison pits a 28 nm mobile chip from 2013 against a 40 nm desktop card from 2011, and the benchmark results reflect a close contest despite their architectural differences.

Head-to-Head Benchmarks

The only available benchmark comparison is the Geekbench OpenCL test. In this test, the AMD Radeon HD 8730M scores 5955 points, while the NVIDIA GeForce GTX 550 Ti scores 5731 points. This gives the AMD Radeon HD 8730M a 3.9% performance advantage. While this is a victory for the AMD part, the margin is relatively slim, indicating that the two GPUs are in a similar performance tier.

The AMD Radeon HD 8730M's score places it at the 34th percentile of all GPUs, while the NVIDIA GeForce GTX 550 Ti sits at the 33rd percentile. This suggests that in the broader landscape of graphics hardware, both cards are positioned at a comparable, modest level of performance. The 3.9% delta is reflected in their near-identical percentile rankings, underscoring that this is not a case of one card dominating the other.

Looking at the nearest rivals for each card provides additional context. The AMD Radeon HD 8730M's closest competitor is the NVIDIA Quadro K620M, which scores 5957 points, a 0% delta. The AMD Radeon HD 8750M scores 5970 points, putting it 0.3% ahead of the HD 8730M. The Intel UHD Graphics 730 trails slightly with a score of 5929, a 0.4% delta in favor of the AMD card. The NVIDIA Quadro K4000 is 0.5% ahead with a score of 5982.

For the NVIDIA GeForce GTX 550 Ti, the nearest rival is the NVIDIA GeForce GTX 670MX, which scores 5721 points, a 0.2% delta in favor of the GTX 550 Ti. The Intel Iris Pro Graphics P6300 scores 5712, a 0.3% delta. The AMD Radeon HD 8790M scores 5691, a 0.7% delta. The AMD Radeon R7 M465 is the only rival that beats it, scoring 5841 points, a 1.9% delta in favor of the R7 M465. These rival data points show that both cards are surrounded by a cluster of similarly performing GPUs, reinforcing that the 3.9% difference between them is meaningful but not overwhelming.

Architecture Differences

The architectural divide between these two GPUs is substantial. The AMD Radeon HD 8730M is built on the GCN 1.0 architecture, using a chip codenamed Mars. It is manufactured on a 28 nm process at TSMC. The NVIDIA GeForce GTX 550 Ti, in contrast, uses the Fermi 2.0 architecture with the GF116 chip, also fabricated by TSMC but on a larger 40 nm process node.

The transistor counts and die sizes differ significantly due to the process node disparity. The AMD chip packs 950 million transistors onto a die size of 77 mm², resulting in a transistor density of 12.3 million transistors per square millimeter. The NVIDIA chip has more transistors overall at 1,170 million, but its die is much larger at 238 mm², yielding a significantly lower transistor density of 4.9 million per square millimeter. This highlights the efficiency advantage of the newer 28 nm process.

Memory configurations also present a clear contrast. The AMD Radeon HD 8730M comes with 2 GB of DDR3 memory on a 128-bit bus, delivering a bandwidth of 28.80 GB/s. The NVIDIA GeForce GTX 550 Ti features 1024 MB of GDDR5 memory on a wider 192-bit bus, resulting in a much higher bandwidth of 98.50 GB/s. This is a major difference; the NVIDIA card has over three times the memory bandwidth, which can be critical in certain workloads.

The compute resources are organized differently as well. The AMD card has 384 shading units, 24 texture mapping units (TMUs), and 8 raster operation units (ROPs). The NVIDIA card has fewer shading units at 192, but more TMUs at 32 and more ROPs at 24. The pixel rate and texture rate reflect these configurations: the NVIDIA card achieves a higher pixel rate of 7.200 GPixel/s compared to the AMD card's 5.600 GPixel/s, and a higher texture rate of 28.80 GTexel/s versus 16.80 GTexel/s. In terms of raw floating-point performance, the NVIDIA card outputs 691.2 GFLOPS, while the AMD card outputs 537.6 GFLOPS.

The bus interface and power requirements differ as well. The AMD card uses PCIe 3.0 x8, while the NVIDIA card uses PCIe 2.0 x16. The NVIDIA GeForce GTX 550 Ti has a TDP of 116 W and requires a 300 W power supply and a 1x 6-pin power connector, and it is a dual-slot card. The AMD Radeon HD 8730M's TDP is not listed in the data, but it is a mobile part. The NVIDIA card also has listed dimensions of 210 mm in length. API support shows the AMD card supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170, while the NVIDIA card supports DirectX 12 (11_0) and OpenGL 4.6, with no Vulkan support listed.

Where Each One Wins

Based on the available data, the AMD Radeon HD 8730M wins the single benchmark test. Its 5955 score in Geekbench OpenCL is 3.9% higher than the NVIDIA card's 5731. This suggests that in compute-oriented OpenCL workloads, the AMD card has a slight edge.

However, the NVIDIA GeForce GTX 550 Ti holds advantages in other areas that are not directly measured by the Geekbench OpenCL test. Its memory bandwidth of 98.50 GB/s is vastly superior to the AMD card's 28.80 GB/s. This could translate to wins in texture-heavy or high-resolution scenarios where bandwidth is a limiting factor. The NVIDIA card's higher pixel rate of 7.200 GPixel/s and texture rate of 28.80 GTexel/s also indicate it may perform better in traditional rasterization tasks that rely on these specific throughput metrics.

The NVIDIA card also has a higher raw FP32 compute throughput at 691.2 GFLOPS compared to the AMD card's 537.6 GFLOPS. While the AMD card won the OpenCL benchmark, the NVIDIA card's theoretical peak performance is higher. This discrepancy suggests that the AMD architecture may be more efficient at translating its theoretical compute into actual benchmark scores, or that the specific workload of the Geekbench test favors the AMD design. The AMD card's support for Vulkan 1.2.170 is another point in its favor, as the NVIDIA card has no Vulkan support listed.

The Verdict

The benchmark data shows a narrow win for the AMD Radeon HD 8730M. It leads the NVIDIA GeForce GTX 550 Ti by 3.9% in Geekbench OpenCL. For users focused on that specific compute benchmark, the AMD Radeon HD 8730M is the superior choice based on the numbers.

However, the NVIDIA GeForce GTX 550 Ti is not without its merits. Its significantly higher memory bandwidth and rasterization throughput suggest it could be the better option for gaming scenarios that are bandwidth-limited or that rely heavily on pixel and texture processing. The data indicates that the NVIDIA card has a theoretical performance advantage in those areas, even if it loses the one benchmark that was recorded. The NVIDIA card also has a launch MSRP of 149 USD.

The choice between these two cards depends on the workload. The AMD Radeon HD 8730M is the winner in the single available benchmark and offers modern API support including Vulkan. The NVIDIA GeForce GTX 550 Ti offers superior memory bandwidth and higher theoretical pixel and texture rates. The data does not provide a clear winner for all scenarios, but for the specific test measured, the AMD Radeon HD 8730M comes out ahead.

FAQ

Q: Which GPU has a higher Geekbench OpenCL score?

A: The AMD Radeon HD 8730M scores 5955, which is 3.9% higher than the NVIDIA GeForce GTX 550 Ti's score of 5731.

Q: How do the memory bandwidths of the two cards compare?

A: The NVIDIA GeForce GTX 550 Ti has a memory bandwidth of 98.50 GB/s, which is significantly higher than the AMD Radeon HD 8730M's 28.80 GB/s.

Q: What are the process nodes for each GPU?

A: The AMD Radeon HD 8730M is built on a 28 nm process, while the NVIDIA GeForce GTX 550 Ti is built on a 40 nm process.

Q: Does the NVIDIA GeForce GTX 550 Ti support Vulkan?

A: No, the NVIDIA GeForce GTX 550 Ti has no Vulkan support listed, while the AMD Radeon HD 8730M supports Vulkan 1.2.170.

Q: What is the transistor density of each chip?

A: The AMD Radeon HD 8730M has a transistor density of 12.3 million transistors per mm², while the NVIDIA GeForce GTX 550 Ti has a density of 4.9 million transistors per mm².

Q: Which card has a higher pixel rate?

A: The NVIDIA GeForce GTX 550 Ti has a higher pixel rate of 7.200 GPixel/s, compared to the AMD Radeon HD 8730M's 5.600 GPixel/s.

DETAILED SPECIFICATIONS

SPECIFICATION
HD 8730M
GTX 550 Ti
Core Specs
Shading Units
384
192 -50.0%
Shaders
384
192 -50.0%
TMUs
24
32 +33.3%
ROPs
8
24 +200.0%
Compute Units
6
—
SM Count
—
4
Clocks
Base Clock
650 MHz
—
Boost Clock
700 MHz
—
GPU Clock
—
900 MHz
Shader Clock
—
1800 MHz
Memory Clock
900 MHz 1800 Mbps effective
1026 MHz 4.1 Gbps effective
Memory
Memory Size
2 GB
1024 MB
VRAM (MB)
2,048
1,024 -50.0%
Memory Type
DDR3
GDDR5
Memory Bus
128 bit
192 bit
Bandwidth
28.80 GB/s
98.50 GB/s
Cache
L1 Cache
16 KB (per CU)
64 KB (per SM)
L2 Cache
256 KB
384 KB
Performance
Pixel Rate
5.600 GPixel/s
7.200 GPixel/s
Texture Rate
16.80 GTexel/s
28.80 GTexel/s
FP32 (TFLOPS)
537.6 GFLOPS
691.2 GFLOPS
FP64 (TFLOPS)
33.60 GFLOPS (1:16)
57.60 GFLOPS (1:12)
Power
TDP
—
116 W
TDP (W)
—
116
Suggested PSU
—
300 W
Power Connectors
—
1x 6-pin
Architecture
Architecture
GCN 1.0
Fermi 2.0
GPU Name
Mars
GF116
Generation
Solar System (HD 8700M)
GeForce 500
Process Size
28 nm
40 nm
Transistors
950 million
1,170 million
Die Size
77 mm²
238 mm²
Foundry
TSMC
TSMC
Density
12.3M / mm²
4.9M / mm²
API Support
DirectX
12 (11_1)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.2.170
—
OpenCL
2.1 (1.2)
1.1
CUDA
—
2.1
Shader Model
6.5 (5.1)
5.1
Physical
Slot Width
—
Dual-slot
Length
—
210 mm 8.3 inches
Outputs
—
2x DVI1x mini-HDMI 1.3a
Bus Interface
PCIe 3.0 x8
PCIe 2.0 x16
Other
Launch Price
—
149 USD
Production
End-of-life
End-of-life
Predecessor
London
GeForce 400
Successor
Gem System
GeForce 600
View Radeon HD 8730M Details View GeForce GTX 550 Ti Details