AMD Radeon 880M vs AMD Radeon 890M Comparison

AMD
RADEON

AMD Radeon 880M

CORE STATE Strix Point
VRAM System Shared
CLOCK SPEED 2900 MHz
TDP 15 W
BUS WIDTH System Shared
ARCHITECTURE RDNA 3.5
nm
PROCESS 4 nm
LAUNCH DATE 2024
VS
AMD
RADEON

Radeon 890M

CORE STATE Strix Point
VRAM System Shared
CLOCK SPEED 2900 MHz
TDP 15 W
BUS WIDTH System Shared
ARCHITECTURE RDNA 3.5
nm
PROCESS 4 nm
LAUNCH DATE 2024

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
535
590
geekbench_opencl
31,285
37,254
geekbench_vulkan
40,006
40,808
passmark_directx_10
31
33
passmark_directx_11
73
73
passmark_directx_12
32
37
passmark_directx_9
97
97
passmark_g2d
969
979
passmark_g3d
7,615
8,076
passmark_gpu_compute
3,719
4,157

Analysis: AMD Radeon 880M vs AMD Radeon 890M

Head-to-Head Benchmarks

The AMD Radeon 890M is the clear winner across the entire benchmark suite, taking 10 out of 10 head-to-head tests against the AMD Radeon 880M. The largest margin comes in Passmark DirectX 12, where the 890M scores 37 versus 32, a 15.6% advantage. This is followed closely by Geekbench OpenCL, where the 890M posts 37254 against 31285, a 19.1% lead. These two results indicate that the 890M holds a substantial edge in both modern graphics API workloads and general compute tasks.

In the 3DMark Steel Nomad DX12 test, the 890M scores 590 while the 880M reaches 535, a 10.3% delta. This is a meaningful gap for a synthetic gaming workload that stresses ray tracing and modern rendering features. Passmark GPU Compute also favors the 890M significantly, with scores of 4157 versus 3719, an 11.8% improvement. The 890M's compute advantage is consistent with its larger shader array and higher texture throughput.

Smaller but still notable wins appear in Passmark DirectX 10, where the 890M leads 33 to 31 (6.5%), and Passmark G3D, where it scores 8076 against 7615 (6.1%). The Geekbench Vulkan test shows a narrower margin: 40808 versus 40006, a 2% delta. Passmark G2D is nearly identical at 979 versus 969, a 1% edge for the 890M. Two tests are exact ties: Passmark DirectX 11 at 73 for both, and Passmark DirectX 9 at 97 for both.

The overall average benchmark scores confirm the hierarchy. The 890M averages 9210 across all recorded tests, while the 880M averages 8436. That is a 774-point gap, roughly 9.2% higher for the 890M. In terms of percentile ranking against all GPUs, the 890M sits at the 45th percentile, while the 880M sits at the 43rd. The nearest rival for the 890M is the AMD Radeon Vega 8, which averages 9221, just 0.1% higher. The nearest rival for the 880M is the NVIDIA GeForce GTX 675MX, which averages 8427, 0.1% lower than the 880M's 8436.

Architecture Differences

Both GPUs share the same fundamental architecture: RDNA 3.5, built on TSMC's 4 nm process node. Both are part of the Navi III IGP (Strix Point Mobile) generation and use the Strix Point chip. The die size is identical at 233 mm², with 34,000 million transistors and a transistor density of 145.9 million per mm². Both are integrated graphics processors with a 15 W TDP, PCIe 4.0 x8 interface, and no dedicated power connectors.

The critical difference lies in the execution resources. The 890M has 1024 shading units, while the 880M has 768, a 33% increase in shader count. Texture mapping units also differ: 64 on the 890M versus 48 on the 880M, a 33% advantage. The ROP count is doubled on the 890M, which has 32 ROPs versus 16 on the 880M. Ray tracing cores follow the same pattern: 16 on the 890M versus 12 on the 880M, a 33% increase.

These resource differences translate directly into throughput metrics. The 890M achieves a pixel rate of 92.80 GPixel/s, exactly double the 46.40 GPixel/s of the 880M. Texture rate is 185.6 GTexel/s versus 139.2 GTexel/s, a 33% advantage. Floating point performance, both FP32 and FP16, is 5.939 TFLOPS on the 890M versus 4.454 TFLOPS on the 880M, a 33% gap. Both GPUs report FP16 at a 1:1 ratio with FP32, meaning no dedicated half-rate path.

Clock speeds are identical: both have a base clock of 400 MHz and a boost clock of 2900 MHz. Memory configuration is also the same: system shared memory with system dependent bandwidth, and no dedicated VRAM. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The bus interface, display outputs (portable device dependent), and power connectors are all identical. Both were released on the same date, 2024-07-14, and both are classified as Active in production status.

Where Each One Wins

The 890M wins in every single recorded benchmark category, making the use-case split straightforward. For users running DirectX 12 workloads, whether synthetic benchmarks or modern games, the 890M's 15.6% lead in Passmark DirectX 12 is the strongest argument. The 3DMark Steel Nomad DX12 result, with a 10.3% advantage, reinforces this for ray-traced and next-gen rendering scenarios.

Compute-heavy tasks favor the 890M by a wide margin. The Geekbench OpenCL score of 37254 versus 31285 (19.1%) is the largest delta in the entire comparison. Passmark GPU Compute also shows an 11.8% edge. This makes the 890M the better choice for GPU-accelerated productivity, rendering, and any workload that leverages OpenCL or general compute APIs.

Vulkan performance is nearly a wash, with the 890M leading by only 2% (40808 versus 40006). Users who primarily target Vulkan will see a smaller benefit from choosing the 890M, though it still wins. Older DirectX 9 and DirectX 11 titles are complete ties at 97 and 73 respectively, so legacy gaming performance is identical. The 890M's advantage in DirectX 10 (6.5%) and G3D (6.1%) is moderate but consistent.

The 880M, while losing every test, remains competitive in specific scenarios. Its Vulkan score is within 2% of the 890M, and its DirectX 11 and DirectX 9 scores are exactly equal. For users running older games or Vulkan-based applications, the 880M offers nearly the same experience at a lower tier. The 880M's nearest rivals include the NVIDIA GeForce MX330 (0.3% lower) and the AMD Radeon HD 8870M (0.3% lower), placing it in the same performance class as those discrete mobile GPUs.

Specification Differences

The following specifications differ between the AMD Radeon 890M and the AMD Radeon 880M:

  • Shading Units: 1024 on the 890M, 768 on the 880M
  • Texture Mapping Units: 64 on the 890M, 48 on the 880M
  • Render Output Units: 32 on the 890M, 16 on the 880M
  • Ray Tracing Cores: 16 on the 890M, 12 on the 880M
  • Pixel Rate: 92.80 GPixel/s on the 890M, 46.40 GPixel/s on the 880M
  • Texture Rate: 185.6 GTexel/s on the 890M, 139.2 GTexel/s on the 880M
  • FP32 Performance: 5.939 TFLOPS on the 890M, 4.454 TFLOPS on the 880M
  • FP16 Performance: 5.939 TFLOPS on the 890M, 4.454 TFLOPS on the 880M

All other recorded specifications are identical: process node (4 nm), foundry (TSMC), transistor count (34,000 million), die size (233 mm²), base clock (400 MHz), boost clock (2900 MHz), memory type (system shared), TDP (15 W), bus interface (PCIe 4.0 x8), API support (DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4), and release date (2024-07-14).

FAQ

Q: Which GPU has more shading units?

A: The AMD Radeon 890M has 1024 shading units, while the AMD Radeon 880M has 768, a 33% difference.

Q: What is the largest benchmark margin between the two?

A: The Geekbench OpenCL test shows the biggest gap, with the 890M scoring 37254 versus 31285 for the 880M, a 19.1% advantage.

Q: Are there any benchmarks where the 880M wins?

A: No. The 890M wins all 10 head-to-head tests. Two tests are exact ties: Passmark DirectX 11 (73 for both) and Passmark DirectX 9 (97 for both).

Q: How do the two GPUs compare in ray tracing performance?

A: The 890M has 16 ray tracing cores versus 12 on the 880M. In the 3DMark Steel Nomad DX12 test, which includes ray tracing workloads, the 890M scores 590 versus 535, a 10.3% edge.

Q: What is the average benchmark score difference?

A: The 890M averages 9210 across all tests, while the 880M averages 8436. The 890M ranks at the 45th percentile of all GPUs, while the 880M ranks at the 43rd.

Q: Do the two GPUs have the same clock speeds?

A: Yes. Both have a base clock of 400 MHz and a boost clock of 2900 MHz. The performance difference comes entirely from execution resources, not clock speeds.

The Verdict

The data is unambiguous: the AMD Radeon 890M is the superior integrated GPU in every measured category. Its 33% advantage in shading units, texture mapping units, and ray tracing cores, combined with a doubled ROP count, produces consistent wins across all 10 benchmarks. The largest margins come in compute-heavy workloads (OpenCL 19.1%, GPU Compute 11.8%) and modern graphics APIs (DirectX 12 15.6%, 3DMark Steel Nomad 10.3%). For users who run current games, GPU-accelerated productivity, or any DirectX 12 workload, the 890M is the clear choice.

The AMD Radeon 880M is not without merit. Its Vulkan performance trails by only 2%, and its DirectX 11 and DirectX 9 scores are identical to the 890M. For legacy titles and Vulkan-based applications, the 880M delivers nearly the same experience. Its average benchmark score of 8436 places it just 0.1% above the NVIDIA GeForce GTX 675MX, making it a capable option for mainstream mobile workloads.

The 890M's average score of 9210 sits just 0.1% below the AMD Radeon Vega 8, placing it in the same performance tier as that established discrete-class part. Given that both GPUs share the same 15 W TDP, the same 4 nm process, and the same clock speeds, the 890M's additional execution resources come at no extra power cost. The decision is simple: choose the 890M for maximum performance, or choose the 880M if the target workload is exclusively older DirectX or Vulkan titles where the performance gap narrows to near zero.

DETAILED SPECIFICATIONS

SPECIFICATION
880M
890M
Core Specs
Shading Units
768
1,024 +33.3%
Shaders
768
1,024 +33.3%
TMUs
48
64 +33.3%
ROPs
16
32 +100.0%
Compute Units
12
16 +33.3%
Clocks
Base Clock
400 MHz
400 MHz
Boost Clock
2900 MHz
2900 MHz
Memory Clock
System Shared
System Shared
Memory
Memory Size
System Shared
System Shared
Memory Type
System Shared
System Shared
Memory Bus
System Shared
System Shared
Bandwidth
System Dependent
System Dependent
Cache
L1 Cache
128 KB per Array
128 KB per Array
L2 Cache
2 MB
2 MB
L0 Cache
32 KB per WGP
32 KB per WGP
Performance
Pixel Rate
46.40 GPixel/s
92.80 GPixel/s
Texture Rate
139.2 GTexel/s
185.6 GTexel/s
FP32 (TFLOPS)
4.454 TFLOPS
5.939 TFLOPS
FP64 (TFLOPS)
278.4 GFLOPS (1:16)
371.2 GFLOPS (1:16)
FP16 (TFLOPS)
4.454 TFLOPS (1:1)
5.939 TFLOPS (1:1)
AI/RT
RT Cores
12
16 +33.3%
Power
TDP
15 W
15 W
TDP (W)
15
15 0.0%
Power Connectors
None
None
Architecture
Architecture
RDNA 3.5
RDNA 3.5
GPU Name
Strix Point
Strix Point
Generation
Navi III IGP (Strix Point Mobile)
Navi III IGP (Strix Point Mobile)
Process Size
4 nm
4 nm
Transistors
34,000 million
34,000 million
Die Size
233 mm²
233 mm²
Foundry
TSMC
TSMC
Density
145.9M / mm²
145.9M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
2.1
Shader Model
6.8
6.8
Physical
Slot Width
IGP
IGP
Outputs
Portable Device Dependent
Portable Device Dependent
Bus Interface
PCIe 4.0 x8
PCIe 4.0 x8
Other
Production
Active
Active
Predecessor
Navi II IGP
Navi II IGP
View Radeon 880M Details View Radeon 890M Details