Radeon 8040S vs Radeon 660M
VS
AMD Radeon 8040S
Strix Halo
AMD Radeon 660M
Rembrandt
We compared two integrated laptop GPUs: the Radeon 8040S with 16 pipelines and 1024 shaders against the 3 years and 1 month older Radeon 660M that utilizes 6 pipelines and 384 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
Key differences
Reasons to consider the Radeon 8040S
- Performs significantly better (up to 3.4x) in 3DMark Steel Nomad Lite
- 3.8x higher maximum theoretical performance (5.7 vs 1.5 TFLOPS)
- Shows 3.1x higher average frame rate in modern games at QHD resolution – 28 vs 9 FPS
- Manufactured using a more efficient 4 nm process technology
- Achieves 2.6x more points in the GeekBench 6 Compute test (35K vs 14K)
- Has 2.7x more shading units (1024 vs 384)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 76 40 31 17 |
27 13 11 - |
| The Witcher 3 | 53 44 26 14 |
9 12 - - |
| Counter-Strike 2 | 84 60 39 15 |
28 17 13 - |
| Far Cry 6 | 61 49 35 16 |
20 16 9 - |
| Hogwarts Legacy | 33 26 20 10 |
10 - - - |
| CoD: Modern Warfare III | 49 41 31 15 |
18 15 13 - |
| Ghost of Tsushima | 33 25 18 10 |
13 - - - |
| Cyberpunk 2077 | 32 29 17 - |
9 9 - - |
| Shadow of the Tomb Raider | 65 55 32 17 |
17 14 11 - |
| 1080p High | 54 | 17 |
| 1080p Ultra | 41 | 12 |
| 1440p Ultra | 28 | 9 |
| 4K Ultra | 13 | - |
| Margin of Error | High | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | - | 1514 |
| Solar Bay | - | 6396 |
| Port Royal | - | 586 |
| Fire Strike | - | 4879 |
| Wild Life Extreme | - | 2676 |
| Night Raid | - | 18958 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 106.8 img/sec | 36 img/sec |
| Face Detection | 43.8 img/sec | 16.4 img/sec |
| Horizon Detection | 1.12 Gpixels/sec | 0.48 Gpixels/sec |
| Edge Detection | 1.17 Gpixels/sec | 0.65 Gpixels/sec |
| Gaussian Blur | 1.07 Gpixels/sec | 0.53 Gpixels/sec |
| Feature Matching | 0.5 Gpixels/sec | 0.18 Gpixels/sec |
| Stereo Matching | 163 Gpixels/sec | 46.5 Gpixels/sec |
| Particle Physics | 5820.4 FPS | 2056.5 FPS |
| API | OpenCL | OpenCL |
Passmark Graphics
G3D Mark Score
| G2D Mark | 1052 | 654 |
| DirectX 11 | 80 FPS | 47 FPS |
| DirectX 12 | 47 FPS | 23 FPS |
| GPU Compute | 5138 Ops/s | 1321 Ops/s |
Blender
Blender GPU
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | - | 1465 |
| Image Segmentation (HP) | - | 1706 |
| Image Super Resolution (Q) | - | 4266 |
| Face Detection (HP) | - | 5115 |
| Pose Estimation (Q) | - | 12992 |
| Text Classification (SP) | - | 1116 |
| Machine Translation (HP) | - | 1859 |
| Object Detection (SP) | - | 1574 |
| Depth Estimation (Q) | - | 6538 |
| Style Transfer (SP) | - | 26656 |
| Framework | - | ONNX |
| Backend | - | DirectML |
Specifications
Technical specifications of Radeon 8040S and Radeon 660MGeneral
| Vendor | Amd | Amd |
| Build | Integrated | Integrated |
| Released | January 7, 2025 | January 1, 2022 |
| Case | Laptop | Laptop |
| Purpose | Generic | Generic |
| Segment | Mid-range | Entry-level |
| Architecture | RDNA 3.5 | RDNA 2.0 |
| GPU Codename | Strix Halo | Rembrandt |
| Rival Equivalent | - GeForce RTX 3050 Laptop | - |
| Successor | - | - Radeon 8040S |
| Recommended CPU | - AMD Ryzen AI Max Pro 380 or above | - AMD Ryzen 5 6600H or above |
| Used in CPUs | - AMD Ryzen AI Max Pro 380 | - AMD Ryzen 5 150 - AMD Ryzen 5 7535U - AMD Ryzen 5 7535HS - AMD Ryzen 5 Pro 6650U - AMD Ryzen 5 6600U - AMD Ryzen 5 6600H |
Laptop GPU ranking (76th and 116th place)
Graphics Processing Unit
| Base Clock | 1295 MHz | 400 MHz |
| Boost Clock | 2800 MHz | 1800-1900 MHz (configurable) |
| Shading Units | 1024 | 384 |
| Texture Mapping Units (TMUs) | 64 | 24 |
| Render Output Units (ROPs) | 32 | 16 |
| Compute Units (Pipelines) | 16 | 6 |
| Tensor Cores | No | - |
| Ray-tracing Cores | 16 | 6 |
| L1 Cache | - | 128KB per cluster |
| L2 Cache | 2MB shared | 1024KB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 90 GPixel/s | 29-30 GPixel/s |
| Texture Fill Rate | 179 GTexel/s | 43-46 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 5.0 x16 | PCIe 4.0 x8 |
| TGP | 55 W | 15 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 6 nm |
| Die Size | 308 mm² | 208 mm² |
| Transistor Count | - | 13.1 billion |
| Transistor Density | - | 62.98 MTr/mm² |
| Max. Temperature | 100°C | - |
Memory
| Memory Type | System Shared | System Shared |
| ECC | No | No |
API
| DirectX | 12.2 | 12 |
| Vulkan | 1.4 | 1.2 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 2.0 |
| CUDA | No | - |
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
| DisplayPort | 2.1a | - |
Cast your vote
Total votes: 2