AMD Radeon 890M vs AMD Radeon RX 550X Comparison

AMD
RADEON

AMD 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
VS
AMD
RADEON

Radeon RX 550X

CORE STATE Lexa
VRAM 4 GB
CLOCK SPEED 1183 MHz
TDP 50 W
BUS WIDTH 128 bit
ARCHITECTURE GCN 4.0
nm
PROCESS 14 nm
LAUNCH DATE 2018

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
590
N/A
geekbench_opencl
37,254
9,662
geekbench_vulkan
40,808
11,299
passmark_directx_10
33
N/A
passmark_directx_11
73
N/A
passmark_directx_12
37
N/A
passmark_directx_9
97
N/A
passmark_g2d
979
N/A
passmark_g3d
8,076
N/A
passmark_gpu_compute
4,157
N/A

Analysis: AMD Radeon 890M vs AMD Radeon RX 550X

The AMD Radeon RX 550X and the AMD Radeon 890M represent two very different eras of GPU design, and the benchmark data reflects a generational chasm. The 890M, a modern integrated processor, decisively outperforms the older discrete RX 550X in every shared benchmark test, making the comparison less about competition and more about the progression of technology. The recorded data shows that the 890M is not just faster; it is in a completely different performance class, despite being an IGP with a significantly lower power envelope.

Head-to-Head Benchmarks

The only direct comparisons available in the database are the Geekbench compute tests, and the results are stark. In Geekbench OpenCL, the AMD Radeon 890M scores 37,254 points, dwarfing the RX 550X’s 9,662 points. This represents a 74.1% advantage for the 890M, a margin so large that it effectively places the two GPUs in separate tiers. The RX 550X’s score places it near the 49th percentile of all GPUs, but the 890M’s raw score is nearly four times higher.

The Geekbench Vulkan test tells a similar story. The 890M posts a score of 40,808, while the RX 550X manages 11,299. This 72.3% delta in favor of the 890M confirms that the performance gap is consistent across different API workloads. The RX 550X’s best result is its Vulkan score, but even that peak is far below the 890M’s baseline. The 890M’s average benchmark score of 9,210 is actually lower than its Geekbench results because its overall average is pulled down by other tests, but the head-to-head data is unambiguous: the 890M wins both shared tests decisively.

Notably, the RX 550X has no wins in the head-to-head comparison. The data shows 0 wins for the RX 550X and 2 wins for the 890M. The 890M’s performance in these compute benchmarks is closer to dedicated desktop GPUs of an older generation, as its nearest rivals include the NVIDIA GeForce GTX 960, which it trails by only 0.7%, and the NVIDIA GeForce GTX 465, which it trails by 0.9%. This context shows that the 890M, despite being an integrated solution, punches well above its weight class.

Where Each One Wins

Given the benchmark results, the use-case split is heavily skewed toward the 890M. The 890M wins in raw compute performance, which translates directly to faster rendering, better frame rates in games, and quicker processing of GPU-accelerated tasks. Its Geekbench OpenCL and Vulkan scores indicate strong performance in both general-purpose compute and modern graphics APIs. The 890M also supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, making it suitable for the latest gaming titles and demanding creative applications. Its 16 ray tracing cores are a feature the RX 550X completely lacks, giving it a clear advantage in any workload that uses ray-traced effects.

The RX 550X, by contrast, has no benchmark wins to point to. Its advantage lies not in performance but in its role as a dedicated discrete GPU with its own memory. It has 4 GB of GDDR5 memory and a 128-bit bus, with a dedicated bandwidth of 96.00 GB/s, which is not dependent on system RAM. This makes it a functional option for systems where shared memory would be a bottleneck. However, the data does not show any scenario where the RX 550X outperforms the 890M. The 890M’s system-shared memory is "System Dependent" in bandwidth, but the sheer computational power of its 1,024 shading units overrides this potential weakness. The RX 550X’s only real "win" is its status as a low-power discrete card with a 50 W TDP, but the 890M operates at just 15 W, making it more efficient in absolute terms.

Architecture Differences

The architectural divide between these two GPUs is vast. The RX 550X is built on the GCN 4.0 architecture, using a chip codenamed Lexa, and is part of the Polaris (RX 500X) generation. It is manufactured on a 14 nm process at GlobalFoundries. The 890M, on the other hand, uses the RDNA 3.5 architecture with a Strix Point chip, part of the Navi III IGP generation, and is built on a 4 nm process at TSMC. This process node difference is critical: the 890M’s 4 nm node allows for far higher transistor density, 145.9M / mm² compared to the RX 550X’s 21.4M / mm². The 890M packs 34,000 million transistors into a 233 mm² die, while the RX 550X uses 2,200 million transistors on a 103 mm² die.

The compute unit configurations also differ dramatically. The RX 550X has 512 shading units, 32 texture mapping units, and 16 render output units. The 890M doubles these numbers, with 1,024 shading units, 64 TMUs, and 32 ROPs. The 890M also includes 16 ray tracing cores, a feature absent from the older GCN architecture. Clock speeds tell a similar story: the RX 550X has a base clock of 1100 MHz and a boost of 1183 MHz, while the 890M has a base of 400 MHz but boosts to 2900 MHz. The 890M’s fill rates are correspondingly higher, with a pixel rate of 92.80 GPixel/s and a texture rate of 185.6 GTexel/s, versus 18.93 GPixel/s and 37.86 GTexel/s for the RX 550X. FP32 performance is 5.939 TFLOPS for the 890M versus 1,211.4 GFLOPS for the RX 550X. The memory subsystems are fundamentally different: the RX 550X uses dedicated GDDR5, while the 890M relies on system-shared memory, which is a major architectural divergence. The 890M also supports PCIe 4.0 x8, while the RX 550X is limited to PCIe 3.0 x8. The RX 550X is a dual-slot card with DVI, HDMI 2.0b, and DisplayPort 1.4a outputs, while the 890M is an IGP with outputs described as portable device dependent.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 550X has a higher average benchmark score of 10,481, compared to the 890M’s 9,210. However, this average is skewed because the RX 550X has only two benchmark entries, while the 890M has ten, including several lower-scoring Passmark tests. In the shared Geekbench tests, the 890M wins by a wide margin.

Q: How do the two GPUs compare in terms of ray tracing support?

A: The AMD Radeon 890M includes 16 ray tracing cores and supports DirectX 12 Ultimate (12_2). The AMD Radeon RX 550X has no ray tracing cores and only supports DirectX 12 (12_0), so it cannot handle hardware-accelerated ray tracing.

Q: What are the TDP differences between the two?

A: The AMD Radeon RX 550X has a TDP of 50 W and requires a suggested power supply of 250 W. The AMD Radeon 890M has a TDP of just 15 W and has no suggested power supply listed, as it is an integrated processor.

Q: Which GPU has more shading units?

A: The AMD Radeon 890M has 1,024 shading units, exactly double the 512 shading units found in the AMD Radeon RX 550X. The 890M also has double the TMUs (64 vs 32) and double the ROPs (32 vs 16).

Q: What is the difference in memory architecture?

A: The RX 550X uses 4 GB of dedicated GDDR5 memory with a 128-bit bus and 96.00 GB/s bandwidth. The 890M uses system-shared memory, so its size, bus width, and bandwidth are system dependent.

Q: How do the Geekbench scores differ?

A: In Geekbench OpenCL, the 890M scores 37,254 versus 9,662 for the RX 550X, a 74.1% difference. In Geekbench Vulkan, the 890M scores 40,808 versus 11,299 for the RX 550X, a 72.3% difference. The 890M wins both tests convincingly.

The Verdict

The data is clear: the AMD Radeon 890M is the superior GPU in every measured performance category. Its Geekbench OpenCL score is 74.1% higher and its Vulkan score is 72.3% higher than the RX 550X. The 890M’s nearest rivals in the database include the NVIDIA GeForce GTX 960 and GTX 465, which means it competes with older mid-range discrete cards, not with the RX 550X. The 890M’s performance, combined with its 15 W TDP and modern feature set including 16 ray tracing cores and DirectX 12 Ultimate support, makes it the obvious choice for anyone seeking performance.

The RX 550X, meanwhile, is an end-of-life product from 2018 with a 49th percentile ranking. Its only advantages are its dedicated 4 GB GDDR5 memory, which provides consistent bandwidth independent of the system, and its status as a dual-slot card with fixed display outputs. For users with older systems that lack the modern CPU architecture required for the 890M, the RX 550X might be a functional upgrade, but it offers no performance benefit over the 890M. The 890M is the definitive winner in this comparison, and the only reason to choose the RX 550X is if a discrete card is required for compatibility reasons. For any new build, the 890M is the clear recommendation based on the recorded data.

Specification Differences

| Specification | AMD Radeon RX 550X | AMD Radeon 890M |

| :--- | :--- | :--- |

| Architecture | GCN 4.0 | RDNA 3.5 |

| Generation | Polaris (RX 500X) | Navi III IGP (Strix Point Mobile) |

| Process Node | 14 nm | 4 nm |

| Foundry | GlobalFoundries | TSMC |

| Transistors | 2,200 million | 34,000 million |

| Die Size | 103 mm² | 233 mm² |

| Transistor Density | 21.4M / mm² | 145.9M / mm² |

| Base Clock | 1100 MHz | 400 MHz |

| Boost Clock | 1183 MHz | 2900 MHz |

| Memory Size | 4 GB | System Shared |

| Memory Type | GDDR5 | System Shared |

| Memory Bus Width | 128 bit | System Shared |

| Memory Bandwidth | 96.00 GB/s | System Dependent |

| Shading Units | 512 | 1024 |

| TMUs | 32 | 64 |

| ROPs | 16 | 32 |

| RT Cores | None | 16 |

| Pixel Rate | 18.93 GPixel/s | 92.80 GPixel/s |

| Texture Rate | 37.86 GTexel/s | 185.6 GTexel/s |

| FP32 Performance | 1,211.4 GFLOPS | 5.939 TFLOPS |

| FP16 Performance | 1,211.4 GFLOPS (1:1) | 5.939 TFLOPS (1:1) |

| TDP | 50 W | 15 W |

| Slot Width | Dual-slot | IGP |

| Suggested PSU | 250 W | None |

| Bus Interface | PCIe 3.0 x8 | PCIe 4.0 x8 |

| DirectX Support | 12 (12_0) | 12 Ultimate (12_2) |

| Vulkan Support | 1.3 | 1.4 |

| Display Outputs | 1x DVI, 1x HDMI 2.0b, 1x DisplayPort 1.4a | Portable Device Dependent |

| Production Status | End-of-life | Active |

| Release Date | 2018-12-15 | 2024-07-14 |

| Predecessor | Polaris | Navi II IGP |

| Successor | Vega | None |

DETAILED SPECIFICATIONS

SPECIFICATION
890M
RX 550X
Core Specs
Shading Units
1,024
512 -50.0%
Shaders
1,024
512 -50.0%
TMUs
64
32 -50.0%
ROPs
32
16 -50.0%
Compute Units
16
8 -50.0%
Clocks
Base Clock
400 MHz
1100 MHz
Boost Clock
2900 MHz
1183 MHz
Memory Clock
System Shared
1500 MHz 6 Gbps effective
Memory
Memory Size
System Shared
4 GB
VRAM (MB)
4,096
Memory Type
System Shared
GDDR5
Memory Bus
System Shared
128 bit
Bandwidth
System Dependent
96.00 GB/s
Cache
L1 Cache
128 KB per Array
16 KB (per CU)
L2 Cache
2 MB
512 KB
L0 Cache
32 KB per WGP
Performance
Pixel Rate
92.80 GPixel/s
18.93 GPixel/s
Texture Rate
185.6 GTexel/s
37.86 GTexel/s
FP32 (TFLOPS)
5.939 TFLOPS
1,211.4 GFLOPS
FP64 (TFLOPS)
371.2 GFLOPS (1:16)
75.71 GFLOPS (1:16)
FP16 (TFLOPS)
5.939 TFLOPS (1:1)
1,211.4 GFLOPS (1:1)
AI/RT
RT Cores
16
Power
TDP
15 W
50 W
TDP (W)
15
50 +233.3%
Suggested PSU
250 W
Power Connectors
None
None
Architecture
Architecture
RDNA 3.5
GCN 4.0
GPU Name
Strix Point
Lexa
Generation
Navi III IGP (Strix Point Mobile)
Polaris (RX 500X)
Process Size
4 nm
14 nm
Transistors
34,000 million
2,200 million
Die Size
233 mm²
103 mm²
Foundry
TSMC
GlobalFoundries
Density
145.9M / mm²
21.4M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (12_0)
OpenGL
4.6
4.6
Vulkan
1.4
1.3
OpenCL
2.1
2.1
Shader Model
6.8
6.7
Physical
Slot Width
IGP
Dual-slot
Length
145 mm 5.7 inches
Outputs
Portable Device Dependent
1x DVI1x HDMI 2.0b1x DisplayPort 1.4a
Bus Interface
PCIe 4.0 x8
PCIe 3.0 x8
Other
Production
Active
End-of-life
Predecessor
Navi II IGP
Polaris
Successor
Vega
View Radeon 890M Details View Radeon RX 550X Details