AMD Radeon HD 8790M vs NVIDIA GeForce GTX 560M Comparison

FAQ

Q: Which GPU has the higher average benchmark score in the database?

A: The AMD Radeon HD 8790M records an average benchmark score of 5691, while the NVIDIA GeForce GTX 560M posts 4855. The AMD part sits at the 33rd percentile among all GPUs, versus the 28th percentile for the NVIDIA part.

Q: How do the two compare in OpenCL performance?

A: The AMD Radeon HD 8790M scores 5017 in Geekbench OpenCL, which is 3.2% ahead of the NVIDIA GeForce GTX 560M's 4855. This is the only direct head-to-head test recorded.

Q: What is the transistor density difference between the two chips?

A: The AMD Radeon HD 8790M uses a 28 nm process with 950 million transistors on a 77 mm² die, giving a density of 12.3M transistors per mm². The NVIDIA GeForce GTX 560M uses a 40 nm process with 1,170 million transistors on a 238 mm² die, resulting in 4.9M transistors per mm².

Q: Which GPU supports Vulkan?

A: The AMD Radeon HD 8790M supports Vulkan 1.2.170, while the NVIDIA GeForce GTX 560M lists no Vulkan support in the database.

Q: What memory configuration does each card use?

A: The NVIDIA GeForce GTX 560M has 1536 MB of GDDR5 on a 192-bit bus with 60.00 GB/s bandwidth. The AMD Radeon HD 8790M has 2 GB of GDDR5 on a 128-bit bus with 64.00 GB/s bandwidth.

Q: Who are the closest rivals for each GPU?

A: For the NVIDIA GeForce GTX 560M, the nearest rival is the NVIDIA GeForce 940MX at 4844 (0.2% delta), followed by the AMD Radeon R6 M255DX at 4867 (-0.2% delta). For the AMD Radeon HD 8790M, the closest rival is the Intel Iris Pro Graphics P6300 at 5712 (-0.4% delta), with the NVIDIA GeForce GTX 550 Ti at 5731 (-0.7% delta) close behind.

Architecture Differences

The architectural gap between these two mobile GPUs is substantial, reflecting two different design philosophies and process generations.

The NVIDIA GeForce GTX 560M is built on the GF116 chip using the Fermi 2.0 architecture, fabricated on a 40 nm process at TSMC. It packs 1,170 million transistors into a 238 mm² die. The AMD Radeon HD 8790M uses the Mars chip with the GCN 1.0 architecture on a 28 nm process, also at TSMC, fitting 950 million transistors into just 77 mm². The density difference is stark: 12.3M transistors per mm² for the AMD chip versus 4.9M for the NVIDIA chip, showing how much more compact the newer process is.

The compute layouts diverge sharply. The NVIDIA part fields 192 shading units, 32 texture mapping units, and 24 ROPs. The AMD part counters with 384 shading units, 24 TMUs, and only 8 ROPs. This means AMD relies on a much wider shader array while NVIDIA allocates more of its die to texture and pixel processing. The pixel rate tells that story: the AMD card achieves 7.200 GPixel/s versus 6.200 GPixel/s for the NVIDIA card, despite having one-third the ROP count. The texture rate, however, favors NVIDIA at 24.80 GTexel/s versus 21.60 GTexel/s for AMD.

Memory architecture also differs fundamentally. The NVIDIA GeForce GTX 560M uses a 192-bit bus with 1536 MB of GDDR5 at 625 MHz (2.5 Gbps effective), yielding 60.00 GB/s of bandwidth. The AMD Radeon HD 8790M uses a narrower 128-bit bus but faster memory at 1000 MHz (4 Gbps effective), achieving 64.00 GB/s. The AMD card also has more capacity at 2 GB versus 1536 MB.

Clock behavior differs as well. The NVIDIA card lists no base or boost clock in the database, only its memory clock. The AMD card has a base clock of 850 MHz and a boost clock of 900 MHz, giving it a dynamic range that the Fermi part lacks. Floating-point throughput favors AMD: 691.2 GFLOPS versus 595.2 GFLOPS, a 16% advantage.

Feature support diverges on API level. Both support DirectX 12 and OpenGL 4.6, but the AMD card supports DirectX 12 (11_1) while the NVIDIA card is capped at 12 (11_0). The AMD Radeon HD 8790M also supports Vulkan 1.2.170, while the NVIDIA GeForce GTX 560M has no Vulkan entry.

The bus interface also differs: NVIDIA uses MXM-B (3.0), while AMD uses MXM-A (3.0). Both are MXM modules with no power connectors and portable-device-dependent display outputs. The NVIDIA card draws 75 W according to the database, while no TDP is listed for the AMD card. The production status for both is end-of-life.

Head-to-Head Benchmarks

The database records one direct head-to-head benchmark between these two GPUs: Geekbench OpenCL. The AMD Radeon HD 8790M scores 5017, beating the NVIDIA GeForce GTX 560M's 4855 by 3.2%. This is a modest but consistent margin, and it aligns with the average benchmark scores where the AMD card leads 5691 to 4855.

The 3.2% OpenCL lead for AMD is notable because the NVIDIA card's closest rival, the NVIDIA GeForce 940MX, scores 4844, meaning the GTX 560M sits nearly exactly at that level. The AMD card, by contrast, sits between the Intel Iris Pro Graphics P6300 at 5712 and the NVIDIA Quadro M500M at 5604, a higher performance tier overall.

The average benchmark score gap is wider than the OpenCL gap. The AMD card's average of 5691 includes a Geekbench Vulkan score of 6365, a test the NVIDIA card does not have recorded. That Vulkan result lifts AMD's average substantially, showing strength in modern API workloads.

In terms of rasterization fundamentals, the AMD card wins pixel throughput with 7.200 GPixel/s versus 6.200 GPixel/s, an advantage of roughly 16%. The NVIDIA card wins texture throughput with 24.80 GTexel/s versus 21.60 GTexel/s, an advantage of roughly 15%. These are complementary strengths: AMD pushes pixels, NVIDIA pushes texels.

The FP32 compute race goes to AMD at 691.2 GFLOPS versus 595.2 GFLOPS, a 16% lead. Memory bandwidth slightly favors AMD at 64.00 GB/s, while the NVIDIA card trails at 60.00 GB/s.

The overall picture from the data is that the AMD Radeon HD 8790M wins the single recorded head-to-head test and the average benchmark score, while the NVIDIA GeForce GTX 560M holds its own in texture rate and matches its rivals within a fraction of a percent. The GTX 560M's delta to the GeForce 940MX is 0.2%, essentially a tie.

The Verdict

The AMD Radeon HD 8790M is the faster GPU by the data. It wins the only head-to-head benchmark test, holds a higher average benchmark score by 836 points, sits five percentile slots higher among all GPUs, and delivers superior FP32 throughput, pixel rate, memory bandwidth, and Vulkan support.

The NVIDIA GeForce GTX 560M is not without merit. It wins texture throughput at 24.80 GTexel/s, matches its nearest rival within 0.2%, and delivers solid OpenCL performance within 3.2% of the AMD card. Its 32 TMUs and 24 ROPs give it a balanced rasterization profile.

For users prioritizing modern API support and raw shader throughput, the AMD Radeon HD 8790M is the clear choice. Its GCN 1.0 architecture with 384 shading units and 900 MHz boost clock shows in the benchmark results. The Vulkan score of 6365 confirms its capability in contemporary workloads.

For users who need texture-heavy performance or who are constrained by the 75 W power envelope of the NVIDIA part, the GeForce GTX 560M remains competitive. Its 1,170 million transistors on a larger die give it texture rate advantages that matter in specific workloads.

The database points to the AMD Radeon HD 8790M as the stronger overall mobile GPU, with the NVIDIA GeForce GTX 560M occupying a lower performance percentile but offering specific strengths in texturing and a tighter power figure.

Specification Differences

| Specification | NVIDIA GeForce GTX 560M | AMD Radeon HD 8790M |

|---|---|---|

| Architecture | Fermi 2.0 | GCN 1.0 |

| Process Node | 40 nm | 28 nm |

| Transistors | 1,170 million | 950 million |

| Die Size | 238 mm² | 77 mm² |

| Transistor Density | 4.9M / mm² | 12.3M / mm² |

| Base Clock | Not listed | 850 MHz |

| Boost Clock | Not listed | 900 MHz |

| Memory Clock | 625 MHz (2.5 Gbps effective) | 1000 MHz (4 Gbps effective) |

| Memory Size | 1536 MB | 2 GB |

| Memory Bus Width | 192 bit | 128 bit |

| Memory Bandwidth | 60.00 GB/s | 64.00 GB/s |

| Shading Units | 192 | 384 |

| TMUs | 32 | 24 |

| ROPs | 24 | 8 |

| Pixel Rate | 6.200 GPixel/s | 7.200 GPixel/s |

| Texture Rate | 24.80 GTexel/s | 21.60 GTexel/s |

| FP32 | 595.2 GFLOPS | 691.2 GFLOPS |

| TDP | 75 W | Not listed |

| Bus Interface | MXM-B (3.0) | MXM-A (3.0) |

| DirectX | 12 (11_0) | 12 (11_1) |

| Vulkan | Not listed | 1.2.170 |

| Release Date | 2011-05-29 | 2013-03-31 |

| Predecessor | GeForce 400M | London |

| Successor | GeForce 600M | Gem System |

Where Each One Wins

The AMD Radeon HD 8790M wins in shader-heavy and modern API workloads. Its 384 shading units and 900 MHz boost clock drive FP32 performance to 691.2 GFLOPS, a 16% lead over the NVIDIA card. The OpenCL head-to-head result of 5017 versus 4855 confirms this advantage in compute tasks. Vulkan support at version 1.2.170 gives it access to a wider range of modern workloads, evidenced by its Geekbench Vulkan score of 6365. The pixel rate of 7.200 GPixel/s outpaces the NVIDIA card despite having fewer ROPs. Memory bandwidth of 64.00 GB/s edges out the NVIDIA card, and the 2 GB capacity offers more headroom for texture data. The 33rd percentile ranking reflects a higher performance tier overall.

The NVIDIA GeForce GTX 560M wins in texture throughput and rasterization balance. Its 32 TMUs produce a texture rate of 24.80 GTexel/s, a 15% lead over the AMD card. The 192-bit memory bus provides a wider path for texture fetches, even at lower clock speeds. The 24 ROPs and 6.200 GPixel/s pixel rate offer solid fill performance for its class. Its OpenCL score of 4855 places it within 0.2% of the GeForce 940MX, showing competitive standing among its immediate rivals. The 75 W TDP makes it a known quantity for power-constrained designs, while the AMD card lists no TDP in the database. The 28th percentile ranking places it slightly below the AMD card but still within a competitive range for legacy workloads.