AMD Radeon HD 8790M vs AMD Radeon R7 M440 Comparison

AMD
RADEON

AMD Radeon HD 8790M

CORE STATE Mars
VRAM 2 GB
CLOCK SPEED 900 MHz
TDP —
BUS WIDTH 128 bit
ARCHITECTURE GCN 1.0
nm
PROCESS 28 nm
LAUNCH DATE 2013
VS
AMD
RADEON

Radeon R7 M440

CORE STATE Meso
VRAM 4 GB
CLOCK SPEED —
TDP —
BUS WIDTH 64 bit
ARCHITECTURE GCN 3.0
nm
PROCESS 28 nm
LAUNCH DATE 2016

PERFORMANCE BENCHMARKS

geekbench_opencl
5,017
5,214
geekbench_vulkan
6,365
5,751

Analysis: AMD Radeon HD 8790M vs AMD Radeon R7 M440

AMD Radeon HD 8790M and AMD Radeon R7 M440 are two end-of-life mobile GPUs from different generations, and the benchmark data shows a split decision. The R7 M440 takes the Geekbench OpenCL test, while the HD 8790M delivers a decisive victory in Geekbench Vulkan. Overall average scores place the HD 8790M slightly ahead, but the R7 M440 counters with a larger memory pool and a newer architecture. The data indicates neither GPU dominates outright; instead, the choice depends on whether the workload favors raw compute throughput or graphics API-specific performance.

Head-to-Head Benchmarks

The two GPUs split their two head-to-head benchmark comparisons exactly, with one win each. In the Geekbench OpenCL test, the AMD Radeon R7 M440 scores 5214, beating the AMD Radeon HD 8790M’s 5017 by a margin of 3.8%. This is a notable result because the HD 8790M has higher theoretical FP32 performance — 691.2 GFLOPS versus 570.2 GFLOPS — yet the R7 M440 still outperforms it in this compute-oriented workload. The R7 M440’s advantage here suggests its GCN 3.0 architecture extracts better efficiency from its shading units, despite having fewer of them (320 vs 384).

The reverse happens in the Geekbench Vulkan test, where the AMD Radeon HD 8790M scores 6365 against the R7 M440’s 5751. This is a substantial 10.7% lead for the older GPU, and it is the largest delta between the two in either test. The HD 8790M’s Vulkan score is also higher than its own OpenCL score by a wide margin (6365 vs 5017), indicating that its GCN 1.0 design responds particularly well to the Vulkan API. Meanwhile, the R7 M440’s Vulkan score (5751) is only slightly above its OpenCL score (5214), showing less API-specific scaling.

Looking at the average benchmark scores, the AMD Radeon HD 8790M achieves 5691, which is 3.8% higher than the R7 M440’s 5483. This overall average favors the HD 8790M, driven primarily by its strong Vulkan showing. In the context of their nearest rivals, the HD 8790M sits just 0.4% below the Intel Iris Pro Graphics P6300 (5712) and 0.5% below the NVIDIA GeForce GTX 670MX (5721), while leading the NVIDIA Quadro M500M by 1.6%. The R7 M440, by contrast, is 0.3% above the NVIDIA Quadro M4000 (5467) and 0.5% below the NVIDIA GeForce GTX 765M (5501), with a 0.7% lead over the AMD Radeon 610M (5444). These percentile positions — 33rd for the HD 8790M and 32nd for the R7 M440 — place both in the lower third of all GPUs, but the HD 8790M edges out its rival in overall standing.

Architecture Differences

The two GPUs come from different architectural generations and chip designs. The AMD Radeon HD 8790M uses the Mars chip built on GCN 1.0 architecture, while the R7 M440 uses the Meso chip on GCN 3.0. Both are fabricated on a 28 nm process at TSMC, but the die sizes and transistor counts differ significantly. The HD 8790M packs 950 million transistors into a 77 mm² die, yielding a transistor density of 12.3M per mm². The R7 M440 is a larger chip, with 1,550 million transistors on a 125 mm² die, giving a density of 12.4M per mm² — nearly identical density despite the size increase.

The memory subsystems are radically different. The HD 8790M comes with 2 GB of GDDR5 memory on a 128-bit bus, providing 64.00 GB/s of bandwidth. The R7 M440 instead offers 4 GB of DDR3 memory on a 64-bit bus, but only 14.40 GB/s of bandwidth — a 78% reduction in memory bandwidth. This is a critical architectural difference, as the R7 M440’s wider memory capacity cannot compensate for its much slower data transfer rate in bandwidth-sensitive tasks.

Compute resources also differ. The HD 8790M has 384 shading units, 24 texture mapping units (TMUs), and 8 raster operations pipelines (ROPs). The R7 M440 has 320 shading units, 20 TMUs, and 8 ROPs. Consequently, the HD 8790M’s pixel rate is 7.200 GPixel/s versus 7.128 GPixel/s for the R7 M440, and its texture rate is 21.60 GTexel/s versus 17.82 GTexel/s. The HD 8790M also leads in FP32 throughput at 691.2 GFLOPS, while the R7 M440’s FP16 performance is identical to its FP32 at 570.2 GFLOPS (1:1 ratio), a feature the HD 8790M does not list.

Clock speeds are another divergence. The HD 8790M has a base clock of 850 MHz and a boost clock of 900 MHz, with memory running at 1000 MHz (4 Gbps effective). The R7 M440 has no listed base or boost clocks, but its memory runs at 900 MHz (1800 Mbps effective). The bus interface also differs: the HD 8790M uses MXM-A (3.0) and is a slot-width MXM Module, while the R7 M440 is an IGP (integrated graphics processor) on PCIe 3.0 x8. Both support DirectX 12, but at different feature levels — the HD 8790M at 12 (11_1) and the R7 M440 at 12 (12_0). Both support OpenGL 4.6 and Vulkan 1.2.170. Neither GPU has dedicated RT or tensor cores.

Where Each One Wins

The AMD Radeon R7 M440 is the clear winner in OpenCL compute workloads, as evidenced by its 3.8% higher score in that specific test. This suggests that applications leveraging OpenCL for general-purpose GPU computing — such as certain physics simulations, video encoding, or data-parallel tasks — will see better performance on the R7 M440. Its newer GCN 3.0 architecture likely contributes to this efficiency, even with fewer shading units and lower theoretical FLOPS. Additionally, the R7 M440’s 4 GB memory capacity is double that of the HD 8790M, which could matter for workloads that require larger datasets to be resident in VRAM, despite the much lower bandwidth.

The AMD Radeon HD 8790M wins decisively in Vulkan graphics performance, taking a 10.7% lead over the R7 M440. This is its strongest showing and indicates that games or applications built on the Vulkan API will run noticeably better on the HD 8790M. Its higher memory bandwidth (64.00 GB/s vs 14.40 GB/s) is likely a major factor here, as Vulkan workloads often stress texture streaming and buffer transfers. The HD 8790M also holds advantages in raw throughput metrics — higher pixel rate, texture rate, and FP32 performance — which benefit traditional rasterization and compute-heavy graphics tasks.

For overall average performance, the HD 8790M wins with a 5691 average score versus 5483, a 3.8% advantage. This makes it the better all-rounder in synthetic benchmarks. However, the R7 M440’s OpenCL win and larger memory capacity make it the better choice for specific compute scenarios or when memory capacity is the bottleneck. The R7 M440 also supports DirectX 12 at the full 12_0 feature level, whereas the HD 8790M only reaches 11_1, which could matter for newer DirectX 12 titles that rely on those features.

The Verdict

Pick the AMD Radeon HD 8790M if Vulkan performance is your priority. The data shows a 10.7% lead over the R7 M440 in the Geekbench Vulkan test, and its higher average benchmark score (5691 vs 5483) makes it the stronger overall performer. Its superior memory bandwidth (64.00 GB/s) and higher compute rates (691.2 GFLOPS, 21.60 GTexel/s) give it a clear edge in graphics-intensive tasks. The HD 8790M also holds a better percentile ranking at 33rd versus the R7 M440’s 32nd, reinforcing its status as the more capable GPU despite being older.

Choose the AMD Radeon R7 M440 if OpenCL compute workloads and memory capacity matter more. Its 3.8% OpenCL win over the HD 8790M demonstrates better compute efficiency in that API, and its 4 GB of VRAM is double the HD 8790M’s 2 GB, which can be decisive for certain data-heavy applications. The R7 M440’s GCN 3.0 architecture and DirectX 12 (12_0) support also make it more modern from a feature standpoint. However, its severely limited memory bandwidth (14.40 GB/s) and lower overall average score mean it is not the better general-purpose GPU. For most users, the HD 8790M’s Vulkan dominance and higher average score make it the safer recommendation, while the R7 M440 is the niche pick for compute-specific use.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon HD 8790M has an average benchmark score of 5691, which is 3.8% higher than the AMD Radeon R7 M440’s 5483.

Q: How do the two GPUs compare in Vulkan performance?

A: The AMD Radeon HD 8790M scores 6365 in Geekbench Vulkan, beating the AMD Radeon R7 M440’s 5751 by a significant 10.7% margin.

Q: Which GPU wins in OpenCL performance?

A: The AMD Radeon R7 M440 wins in Geekbench OpenCL with a score of 5214, compared to the AMD Radeon HD 8790M’s 5017, a 3.8% difference.

Q: What are the memory specifications of each GPU?

A: The AMD Radeon HD 8790M has 2 GB of GDDR5 memory on a 128-bit bus with 64.00 GB/s bandwidth. The AMD Radeon R7 M440 has 4 GB of DDR3 memory on a 64-bit bus with 14.40 GB/s bandwidth.

Q: Do both GPUs support the same DirectX version?

A: No. The AMD Radeon HD 8790M supports DirectX 12 (11_1), while the AMD Radeon R7 M440 supports DirectX 12 (12_0), a higher feature level.

Q: What are the transistor counts and die sizes?

A: The AMD Radeon HD 8790M has 950 million transistors on a 77 mm² die, while the AMD Radeon R7 M440 has 1,550 million transistors on a 125 mm² die. Both use a 28 nm TSMC process.

Specification Differences

| Specification | AMD Radeon HD 8790M | AMD Radeon R7 M440 |

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

| Chip | Mars | Meso |

| Architecture | GCN 1.0 | GCN 3.0 |

| Generation | Solar System (HD 8700M) | Gem System (R7 M400) |

| Transistors | 950 million | 1,550 million |

| Die Size | 77 mm² | 125 mm² |

| Transistor Density | 12.3M / mm² | 12.4M / mm² |

| Base Clock | 850 MHz | Not listed |

| Boost Clock | 900 MHz | Not listed |

| Memory Clock | 1000 MHz (4 Gbps effective) | 900 MHz (1800 Mbps effective) |

| Memory Size | 2 GB | 4 GB |

| Memory Type | GDDR5 | DDR3 |

| Memory Bus Width | 128 bit | 64 bit |

| Memory Bandwidth | 64.00 GB/s | 14.40 GB/s |

| Shading Units | 384 | 320 |

| TMUs | 24 | 20 |

| Pixel Rate | 7.200 GPixel/s | 7.128 GPixel/s |

| Texture Rate | 21.60 GTexel/s | 17.82 GTexel/s |

| FP32 Performance | 691.2 GFLOPS | 570.2 GFLOPS |

| FP16 Performance | Not listed | 570.2 GFLOPS (1:1) |

| Slot Width | MXM Module | IGP |

| Power Connectors | None | Not listed |

| Bus Interface | MXM-A (3.0) | PCIe 3.0 x8 |

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

| Release Date | 2013-03-31 | 2016-05-14 |

| Predecessor | London | Solar System |

| Successor | Gem System | Polaris Mobile |

DETAILED SPECIFICATIONS

SPECIFICATION
HD 8790M
R7 M440
Core Specs
Shading Units
384
320 -16.7%
Shaders
384
320 -16.7%
TMUs
24
20 -16.7%
ROPs
8
8 0.0%
Compute Units
6
5 -16.7%
Clocks
Base Clock
850 MHz
—
Boost Clock
900 MHz
—
GPU Clock
—
891 MHz
Memory Clock
1000 MHz 4 Gbps effective
900 MHz 1800 Mbps effective
Memory
Memory Size
2 GB
4 GB
VRAM (MB)
2,048
4,096 +100.0%
Memory Type
GDDR5
DDR3
Memory Bus
128 bit
64 bit
Bandwidth
64.00 GB/s
14.40 GB/s
Cache
L1 Cache
16 KB (per CU)
16 KB (per CU)
L2 Cache
256 KB
128 KB
Performance
Pixel Rate
7.200 GPixel/s
7.128 GPixel/s
Texture Rate
21.60 GTexel/s
17.82 GTexel/s
FP32 (TFLOPS)
691.2 GFLOPS
570.2 GFLOPS
FP64 (TFLOPS)
43.20 GFLOPS (1:16)
35.64 GFLOPS (1:16)
FP16 (TFLOPS)
—
570.2 GFLOPS (1:1)
Power
Power Connectors
None
—
Architecture
Architecture
GCN 1.0
GCN 3.0
GPU Name
Mars
Meso
Generation
Solar System (HD 8700M)
Gem System (R7 M400)
Process Size
28 nm
28 nm
Transistors
950 million
1,550 million
Die Size
77 mm²
125 mm²
Foundry
TSMC
TSMC
Density
12.3M / mm²
12.4M / mm²
API Support
DirectX
12 (11_1)
12 (12_0)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.2.170
OpenCL
2.1 (1.2)
2.1
Shader Model
6.5 (5.1)
6.5
Physical
Slot Width
MXM Module
IGP
Outputs
Portable Device Dependent
Portable Device Dependent
Bus Interface
MXM-A (3.0)
PCIe 3.0 x8
Other
Production
End-of-life
End-of-life
Predecessor
London
Solar System
Successor
Gem System
Polaris Mobile
View Radeon HD 8790M Details View Radeon R7 M440 Details