AMD Radeon HD 8790M vs AMD Radeon Vega 10 Mobile Comparison

Head-to-Head Benchmarks

The database contains one direct comparison between these two mobile graphics solutions: the Geekbench OpenCL test. In this measured workload, the AMD Radeon Vega 10 Mobile scores 6476 points, while the AMD Radeon HD 8790M scores 5017 points. The delta is a decisive 29.1% in favor of the newer Vega IGP. This is not a marginal victory; it is a substantial performance gap that places the Vega 10 Mobile in a different competitive tier.

To contextualize that score, the Vega 10 Mobile sits at the 37th percentile among all GPUs in the database. Its nearest rivals are instructive: the NVIDIA Quadro M5000M scores 6481, which is 0.1% higher, and the NVIDIA GeForce GT 555M scores 6493, which is 0.3% higher. The Vega 10 Mobile essentially trades blows with those older discrete parts, landing just 0.6% behind the GeForce GTX 670M (6513) and 1.1% ahead of the NVIDIA RTX PRO 5000 72 GB Blackwell (6407). That last comparison is striking: a low-power integrated GPU from 2019 is within 1.1% of a modern workstation-class accelerator in this specific OpenCL test, though the database does not clarify how that result was obtained.

The HD 8790M, by contrast, sits at the 33rd percentile. Its nearest rivals cluster around its average score of 5691: the Intel Iris Pro Graphics P6300 is 0.4% behind (5712), the NVIDIA GeForce GTX 670MX is 0.5% behind (5721), and the NVIDIA GeForce GTX 550 Ti is 0.7% behind (5731). The only rival ahead is the NVIDIA Quadro M500M at 5604, which is 1.6% lower. In other words, the HD 8790M is surrounded by integrated and older discrete graphics, and it does not dominate any of them by a wide margin. The Vega 10 Mobile, on the other hand, is competitive with much more recent and higher-end parts.

The single head-to-head result leaves no ambiguity: the Vega 10 Mobile wins the only shared benchmark, with a 29.1% lead. The HD 8790M does not have a single win in the database across any recorded test.

Where Each One Wins

Based strictly on the recorded data, the Vega 10 Mobile wins the only benchmark where both are present. That means in OpenCL compute workloads, which often reflect general-purpose GPU acceleration, the Vega 10 Mobile is clearly superior. The 29.1% delta suggests that any application leveraging OpenCL for tasks like image processing, physics simulation, or data-parallel computation will favor the Vega 10 Mobile.

The HD 8790M does have a second benchmark entry that the Vega 10 Mobile lacks: a Geekbench Vulkan score of 6365. However, without a corresponding Vulkan result for the Vega 10 Mobile, the database cannot directly compare them in that API. The HD 8790M also has a dedicated memory subsystem with 2 GB of GDDR5 and a 128-bit bus, which may be relevant in scenarios where dedicated video memory matters, but no benchmark in the database isolates that advantage.

For gaming and graphics rendering, the Vega 10 Mobile's higher pixel rate (10.41 GPixel/s versus 7.200 GPixel/s) and texture rate (52.04 GTexel/s versus 21.60 GTexel/s) suggest it will handle rasterization workloads more effectively. The HD 8790M's higher base clock (850 MHz versus 300 MHz) does not compensate for its far lower shading unit count (384 versus 640) and texture units (24 versus 40). The data does not include frame-rate tests, so any gaming conclusion must be inferred from these raw throughput figures.

Architecture Differences

The two GPUs come from different eras of AMD's design philosophy. The Vega 10 Mobile uses the Raven-M chip built on GCN 5.0 architecture, fabricated on a 14 nm process at GlobalFoundries. It integrates 4,940 million transistors on a 210 mm² die, yielding a transistor density of 23.5 million per square millimeter. The HD 8790M uses the Mars chip based on GCN 1.0, fabricated on a 28 nm process at TSMC. It contains 950 million transistors on a 77 mm² die, with a density of 12.3 million per square millimeter. The Vega 10 Mobile is thus both larger and denser, reflecting five years of process and design advancement.

The Vega 10 Mobile is an integrated graphics processor (IGP) with system-shared memory, meaning it has no dedicated VRAM. Its memory type, bus width, and bandwidth are all listed as "System Shared" or "System Dependent". The HD 8790M is a discrete MXM module with 2 GB of GDDR5 memory on a 128-bit bus, delivering 64.00 GB/s of bandwidth. This is a fundamental architectural split: the Vega IGP relies on the host system's memory bandwidth, while the HD 8790M has its own fixed allocation.

Clock behavior also differs sharply. The Vega 10 Mobile has a base clock of 300 MHz and a boost clock of 1301 MHz, a wide dynamic range typical of power-managed integrated parts. The HD 8790M runs at a base of 850 MHz and boosts to 900 MHz, a narrow range suggesting a more static operating point. The Vega 10 Mobile's 640 shading units, 40 TMUs, and 8 ROPs outnumber the HD 8790M's 384 shading units, 24 TMUs, and 8 ROPs. The Vega part also supports FP16 at 3.331 TFLOPS with a 2:1 ratio, while the HD 8790M has no recorded FP16 capability. FP32 throughput is 1.665 TFLOPS for the Vega versus 691.2 GFLOPS for the HD, a 2.4x difference.

API support favors the newer part as well: the Vega 10 Mobile supports DirectX 12 (12_1) and Vulkan 1.3, while the HD 8790M supports DirectX 12 (11_1) and Vulkan 1.2.170. Both list OpenGL 4.6. The Vega 10 Mobile also has a lower TDP at 10 W, whereas the HD 8790M's TDP is not recorded in the database. The Vega part is an IGP with no power connectors; the HD 8790M is an MXM module also without power connectors.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The AMD Radeon Vega 10 Mobile scores 6476 in Geekbench OpenCL, which is 29.1% higher than the AMD Radeon HD 8790M's score of 5017.

Q: Does the HD 8790M have any benchmark where it beats the Vega 10 Mobile?

A: No. The database records one head-to-head benchmark (Geekbench OpenCL), and the Vega 10 Mobile wins it. The HD 8790M has a separate Vulkan score of 6365, but there is no corresponding Vulkan score for the Vega 10 Mobile to compare.

Q: How does the Vega 10 Mobile compare to its nearest rivals?

A: The Vega 10 Mobile is 0.1% behind the NVIDIA Quadro M5000M, 0.3% behind the NVIDIA GeForce GT 555M, 0.6% behind the NVIDIA GeForce GTX 670M, and 1.1% ahead of the NVIDIA RTX PRO 5000 72 GB Blackwell in average benchmark scores.

Q: What memory configuration does each GPU use?

A: The Vega 10 Mobile uses system-shared memory with no dedicated VRAM, while the HD 8790M has 2 GB of GDDR5 on a 128-bit bus with 64.00 GB/s bandwidth.

Q: Which GPU has more shading units?

A: The Vega 10 Mobile has 640 shading units, compared to 384 for the HD 8790M.

Q: What are the release dates for these GPUs?

A: The Vega 10 Mobile was released on 2019-01-07, while the HD 8790M was released on 2013-03-31.

Specification Differences

| Specification | AMD Radeon Vega 10 Mobile | AMD Radeon HD 8790M |

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

| Architecture | GCN 5.0 | GCN 1.0 |

| Chip | Raven-M | Mars |

| Process Node | 14 nm | 28 nm |

| Foundry | GlobalFoundries | TSMC |

| Transistors | 4,940 million | 950 million |

| Die Size | 210 mm² | 77 mm² |

| Transistor Density | 23.5M / mm² | 12.3M / mm² |

| Base Clock | 300 MHz | 850 MHz |

| Boost Clock | 1301 MHz | 900 MHz |

| Memory Size | System Shared | 2 GB |

| Memory Type | System Shared | GDDR5 |

| Memory Bus Width | System Shared | 128 bit |

| Memory Bandwidth | System Dependent | 64.00 GB/s |

| Shading Units | 640 | 384 |

| TMUs | 40 | 24 |

| ROPs | 8 | 8 |

| Pixel Rate | 10.41 GPixel/s | 7.200 GPixel/s |

| Texture Rate | 52.04 GTexel/s | 21.60 GTexel/s |

| FP32 | 1.665 TFLOPS | 691.2 GFLOPS |

| FP16 | 3.331 TFLOPS (2:1) | null |

| TDP | 10 W | null |

| Slot Width | IGP | MXM Module |

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

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

| Vulkan | 1.3 | 1.2.170 |

| Release Date | 2019-01-07 | 2013-03-31 |

| Predecessor | GCN 3.0 IGP | London |

| Successor | Navi II IGP | Gem System |

The Verdict

The data points to a clear recommendation for most use cases: the AMD Radeon Vega 10 Mobile is the stronger GPU. It wins the only shared benchmark by 29.1%, has more than double the FP32 throughput (1.665 TFLOPS versus 691.2 GFLOPS), higher pixel and texture rates, more shading units, and a smaller process node. Its 10 W TDP also suggests it operates within a tight power envelope, which is typical for an integrated part.

The HD 8790M is not without merit, but its advantages are narrow. It has dedicated 2 GB GDDR5 memory with 64.00 GB/s bandwidth, which can be beneficial if the host system's shared memory is slow or limited. Its higher base clock of 850 MHz versus 300 MHz might indicate more predictable performance in lightly-threaded workloads, but that does not translate into a benchmark win in the database.

For users who need raw compute performance, modern API support (Vulkan 1.3, DirectX 12_1), and lower power consumption, the Vega 10 Mobile is the obvious choice. For those constrained to a system with an MXM slot and requiring dedicated VRAM, the HD 8790M remains a functional option, but it is a legacy part from 2013 with a 33rd percentile standing. The Vega 10 Mobile, despite being an IGP, punches well above its class, landing within 0.6% of the GeForce GTX 670M and ahead of the RTX PRO 5000 72 GB Blackwell. The verdict from the recorded measurements is unambiguous: the Vega 10 Mobile is the superior performer.