AMD Radeon HD 8870M vs NVIDIA GeForce GTX 560 Comparison

AMD
RADEON

AMD Radeon HD 8870M

CORE STATE Venus
VRAM 2 GB
CLOCK SPEED 775 MHz
TDP —
BUS WIDTH 128 bit
ARCHITECTURE GCN 1.0
nm
PROCESS 28 nm
LAUNCH DATE 2013
VS
NVIDIA
GEFORCE

GeForce GTX 560

CORE STATE GF114
VRAM 1024 MB
CLOCK SPEED —
TDP 150 W
BUS WIDTH 256 bit
ARCHITECTURE Fermi 2.0
nm
PROCESS 40 nm
LAUNCH DATE 2011

PERFORMANCE BENCHMARKS

geekbench_opencl
8,462
9,058

Analysis: AMD Radeon HD 8870M vs NVIDIA GeForce GTX 560

The NVIDIA GeForce GTX 560 and AMD Radeon HD 8870M are two end-of-life graphics solutions from different eras, targeting different segments of the market. The data shows a clear, albeit modest, performance advantage for the desktop GTX 560 in the single available benchmark, but the AMD part counters with architectural and feature-set improvements that matter for modern software compatibility. The GTX 560 scores 9058 in Geekbench OpenCL, placing it in the 45th percentile of all GPUs, while the HD 8870M scores 8462, placing it in the 43rd percentile. This 7% delta in raw compute performance positions them as close competitors despite their generational and form-factor divide.

Head-to-Head Benchmarks

The only direct benchmark comparison available is Geekbench OpenCL, and the results show a decisive win for the NVIDIA GeForce GTX 560. It scores 9058 points compared to the AMD Radeon HD 8870M's 8462 points, yielding a 7% performance advantage for the NVIDIA card. This margin is not trivial; it represents a consistent lead in general-purpose compute workloads that rely on OpenCL acceleration. The GTX 560's nearest rivals in the database include the NVIDIA TITAN V CEO Edition, which it edges out by 0.2%, and the NVIDIA GeForce GTX 660, which it leads by 0.4%. It also sits 1.6% ahead of the AMD Radeon 550X, showing that its compute performance remains competitive even against much newer low-end parts.

On the other side, the AMD Radeon HD 8870M's 8462 score places it just 0.1% ahead of the NVIDIA GeForce MX330 and 0.3% ahead of the AMD Radeon 880M. It trails the Intel Arc A380 by 1.1%, which is a newer integrated solution with modern driver optimizations. The HD 8870M also sits 0.4% ahead of the NVIDIA GeForce GTX 675MX, a mobile part from the same era. These delta percentages are small, indicating that the HD 8870M's compute throughput is very much in line with its immediate peers, but the 7% gap to the GTX 560 is the largest difference in this comparison. When looking at the head-to-head data, the GTX 560 wins the sole benchmark, giving it a 1-0 record in wins, while the HD 8870M has zero wins.

Where Each One Wins

The NVIDIA GeForce GTX 560 wins outright in raw OpenCL compute performance. Its higher score of 9058 versus 8462 means it is the better choice for any workload that is heavily dependent on general-purpose GPU computing, such as video encoding, physics simulations, or OpenCL-accelerated rendering. The GTX 560 also benefits from a wider 256-bit memory bus, which provides a substantial bandwidth advantage of 128.0 GB/s compared to the HD 8870M's 72.00 GB/s. This bandwidth advantage is critical for memory-intensive tasks, and the data indicates the GTX 560 is the stronger performer in this regard.

The AMD Radeon HD 8870M, while losing the compute benchmark, wins in several qualitative and architectural areas that the data does not capture in raw scores. It has a higher pixel rate at 12.40 GPixel/s versus the GTX 560's 11.34 GPixel/s, suggesting it may be more efficient at fill-rate-bound tasks. It also features a newer PCIe 3.0 x16 interface, which offers double the bandwidth of the GTX 560's PCIe 2.0 x16 connection, though this is unlikely to impact discrete GPU performance significantly. More importantly, the HD 8870M supports Vulkan 1.2.170, while the GTX 560 has no Vulkan support listed. This makes the AMD card the clear winner for software titles that require Vulkan, as the NVIDIA card simply cannot run them. Its DirectX 12 (11_1) support is also slightly newer than the GTX 560's DirectX 12 (11_0), which could matter for certain modern API features.

FAQ

Q: Which GPU has a higher Geekbench OpenCL score?

A: The NVIDIA GeForce GTX 560 scores 9058, which is 7% higher than the AMD Radeon HD 8870M's 8462. The GTX 560 wins this benchmark outright.

Q: Does the AMD Radeon HD 8870M support any modern graphics APIs that the GTX 560 lacks?

A: Yes. The HD 8870M supports Vulkan 1.2.170, while the GTX 560 has no Vulkan support listed. Both support DirectX 12, but the HD 8870M (11_1) has a slightly newer feature level than the GTX 560 (11_0).

Q: How does the memory bandwidth compare between these two cards?

A: The GTX 560 has a 256-bit memory bus and 128.0 GB/s bandwidth, while the HD 8870M has a 128-bit bus and 72.00 GB/s bandwidth. The GTX 560 has a significant 56 GB/s advantage in memory bandwidth.

Q: What is the process node difference between the two GPUs?

A: The NVIDIA GTX 560 is built on a 40 nm process at TSMC, while the AMD HD 8870M is built on a newer 28 nm process, also at TSMC. The HD 8870M has a higher transistor density of 12.2M / mm² compared to 5.9M / mm².

Q: Which GPU has a higher pixel fill rate?

A: The AMD Radeon HD 8870M has a higher pixel rate of 12.40 GPixel/s, compared to the NVIDIA GeForce GTX 560's 11.34 GPixel/s. This is one of the few performance metrics where the AMD card leads.

Q: What are the nearest rivals for each card based on average benchmark scores?

A: For the GTX 560, the nearest rivals are the NVIDIA TITAN V CEO Edition (0.2% slower), NVIDIA GeForce GTX 660 (0.4% slower), and AMD Radeon 550X (1.6% slower). For the HD 8870M, the nearest rivals are the NVIDIA GeForce MX330 (0.1% slower), AMD Radeon 880M (0.3% slower), and NVIDIA GeForce GTX 675MX (0.4% slower).

Specification Differences

The two cards differ in almost every core specification. The NVIDIA GeForce GTX 560 features 336 shading units, 56 texture mapping units (TMUs), and 32 raster operations pipelines (ROPs). In contrast, the AMD Radeon HD 8870M has 640 shading units, 40 TMUs, and only 16 ROPs. The GTX 560 has more TMUs and ROPs, which supports its higher texture rate of 45.36 GTexel/s compared to the HD 8870M's 31.00 GTexel/s. The HD 8870M has more shading units but a lower raw FP32 throughput at 992.0 GFLOPS versus the GTX 560's 1,088.6 GFLOPS.

Memory configurations are also distinct. The GTX 560 uses 1024 MB of GDDR5 on a 256-bit bus, while the HD 8870M uses 2 GB of GDDR5 on a 128-bit bus. The effective memory speed is 4 Gbps for the GTX 560 and 4.5 Gbps for the HD 8870M. The GTX 560's memory clock is listed as 1000 MHz, while the HD 8870M's base clock is 725 MHz with a boost clock of 775 MHz. The GTX 560 has a TDP of 150 W and requires a 450 W suggested power supply with dual 6-pin connectors, while the HD 8870M has no TDP, power connector, or suggested PSU listed, reflecting its mobile-oriented design. The GTX 560 is a dual-slot card measuring 210 mm in length, while the HD 8870M has no physical dimensions listed. The bus interface is PCIe 2.0 x16 for the GTX 560 and PCIe 3.0 x16 for the HD 8870M. The GTX 560 has 2x DVI and 1x mini-HDMI outputs, while the HD 8870M has no display outputs listed.

Architecture Differences

The architectural divide is significant. The NVIDIA GeForce GTX 560 is built on the Fermi 2.0 architecture, using the GF114 chip, while the AMD Radeon HD 8870M uses the GCN 1.0 architecture with the Venus chip. The GTX 560 is a desktop card from the GeForce 500 generation, while the HD 8870M is from the Solar System (HD 8800M) generation, targeting mobile platforms. The process node differs: the GTX 560 uses a 40 nm process, while the HD 8870M uses a more advanced 28 nm process, both fabricated by TSMC. This results in a major die size difference: the GTX 560 has a 332 mm² die with 1,950 million transistors, while the HD 8870M has a much smaller 123 mm² die with 1,500 million transistors. Consequently, the transistor density is far higher on the HD 8870M at 12.2M / mm² versus 5.9M / mm² for the GTX 560.

The GTX 560's architecture lacks a listed boost clock, running at a fixed memory clock of 1000 MHz. The HD 8870M has a base clock of 725 MHz and a boost clock of 775 MHz. The HD 8870M's GCN architecture provides support for Vulkan 1.2.170, which is absent from the GTX 560's feature set. Both support DirectX 12, but the HD 8870M's feature level of 11_1 is newer than the GTX 560's 11_0. The GTX 560's predecessor is the GeForce 400 series and its successor is the GeForce 600 series, while the HD 8870M's predecessor is "London" and its successor is "Gem System". The GTX 560 was released on 2011-05-16, while the HD 8870M came later on 2013-03-31.

The Verdict

The data points to a straightforward choice for compute-heavy tasks: the NVIDIA GeForce GTX 560 is the faster card. Its 7% lead in Geekbench OpenCL and significantly higher memory bandwidth (128.0 GB/s versus 72.00 GB/s) make it the superior option for raw throughput. It also has a higher texture rate and more ROPs, which are beneficial for traditional rasterization workloads. If you are working with OpenCL-based applications and need the maximum performance from these two legacy parts, the GTX 560 is the clear winner.

However, the AMD Radeon HD 8870M should be the pick for users prioritizing software compatibility and modern API support. Its Vulkan 1.2.170 support is a decisive factor, as the GTX 560 cannot run Vulkan titles at all. The HD 8870M also has a higher pixel rate and doubles the VRAM capacity at 2 GB versus 1 GB, which can be a practical advantage for texture-heavy workloads at lower resolutions. Its smaller die size and newer process node indicate a more efficient design, and its PCIe 3.0 interface is a generational improvement. For a system running modern Linux or Windows software that relies on Vulkan, the HD 8870M is the only viable choice. The GTX 560 is the performance pick; the HD 8870M is the compatibility pick.

DETAILED SPECIFICATIONS

SPECIFICATION
HD 8870M
GTX 560
Core Specs
Shading Units
640
336 -47.5%
Shaders
640
336 -47.5%
TMUs
40
56 +40.0%
ROPs
16
32 +100.0%
Compute Units
10
—
SM Count
—
7
Clocks
Base Clock
725 MHz
—
Boost Clock
775 MHz
—
GPU Clock
—
810 MHz
Shader Clock
—
1620 MHz
Memory Clock
1125 MHz 4.5 Gbps effective
1000 MHz 4 Gbps effective
Memory
Memory Size
2 GB
1024 MB
VRAM (MB)
2,048
1,024 -50.0%
Memory Type
GDDR5
GDDR5
Memory Bus
128 bit
256 bit
Bandwidth
72.00 GB/s
128.0 GB/s
Cache
L1 Cache
16 KB (per CU)
64 KB (per SM)
L2 Cache
256 KB
512 KB
Performance
Pixel Rate
12.40 GPixel/s
11.34 GPixel/s
Texture Rate
31.00 GTexel/s
45.36 GTexel/s
FP32 (TFLOPS)
992.0 GFLOPS
1,088.6 GFLOPS
FP64 (TFLOPS)
62.00 GFLOPS (1:16)
90.72 GFLOPS (1:12)
Power
TDP
—
150 W
TDP (W)
—
150
Suggested PSU
—
450 W
Power Connectors
—
2x 6-pin
Architecture
Architecture
GCN 1.0
Fermi 2.0
GPU Name
Venus
GF114
Generation
Solar System (HD 8800M)
GeForce 500
Process Size
28 nm
40 nm
Transistors
1,500 million
1,950 million
Die Size
123 mm²
332 mm²
Foundry
TSMC
TSMC
Density
12.2M / mm²
5.9M / 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 x16
PCIe 2.0 x16
Other
Launch Price
—
199 USD
Production
End-of-life
End-of-life
Predecessor
London
GeForce 400
Successor
Gem System
GeForce 600
View Radeon HD 8870M Details View GeForce GTX 560 Details