AMD Radeon R9 M380 vs NVIDIA GeForce RTX 5090 D V2 Comparison

AMD
RADEON

AMD Radeon R9 M380

CORE STATE Strato
VRAM 4 GB
CLOCK SPEED 1000 MHz
TDP —
BUS WIDTH 128 bit
ARCHITECTURE GCN 2.0
nm
PROCESS 28 nm
LAUNCH DATE 2015
VS
NVIDIA
GEFORCE

GeForce RTX 5090 D V2

CORE STATE GB202
VRAM 24 GB
CLOCK SPEED 2407 MHz
TDP 575 W
BUS WIDTH 384 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

geekbench_metal
18,476
N/A
geekbench_opencl
12,565
N/A
3dmark_3dmark_steel_nomad_dx12
N/A
16,504

Analysis: AMD Radeon R9 M380 vs NVIDIA GeForce RTX 5090 D V2

Head-to-Head Benchmarks

The two GPUs in this comparison come from entirely different eras, and the benchmark data reflects that divide. The NVIDIA GeForce RTX 5090 D V2 produces a 3DMark Steel Nomad DX12 score of 16,504, placing it at the 59th percentile among all GPUs. Its nearest rival, the NVIDIA T400, scores nearly identically at 16,508, a delta of 0%. The AMD Radeon PRO W7500 trails by a mere 0.5% at 16,415, and the NVIDIA RTX PRO 6000 Blackwell is 0.6% behind at 16,408. The AMD Radeon RX 5700 XT rounds out the rival group at 16,361, a 0.9% deficit. These razor-thin margins place the RTX 5090 D V2 in a dense cluster of professional and enthusiast cards where a single percentage point separates first from last.

The AMD Radeon R9 M380, by contrast, shows its strength in different workloads. Its Geekbench Metal score reaches 18,476, while its Geekbench OpenCL score comes in at 12,565. The average of its two benchmark results is 15,521, which puts it at the 58th percentile overall. Its nearest rival, the NVIDIA GeForce GTX 1080 Ti, scores 15,548 — a delta of -0.2%, meaning the R9 M380 actually edges out that legendary card by a hair. The AMD Radeon Pro W5500 sits 1% ahead at 15,679, while the NVIDIA GeForce RTX 2060 is 1.5% behind at 15,290. The NVIDIA GeForce GTX 580 trails by 1.6% at 15,283. Despite the age of its GCN architecture, the R9 M380 holds its ground against far more recent products in these aggregate scores.

Direct head-to-head benchmark comparisons between the two cards are absent from the data, so no single test pits them against each other. However, the average benchmark scores tell a clear story: the RTX 5090 D V2 averages 16,504 across its single benchmark, while the R9 M380 averages 15,521 across two. That is a 983-point gap, or roughly 6.3% in favor of the NVIDIA card. The percentile rankings are nearly identical — 59th versus 58th — which suggests that in the broader GPU landscape, both cards occupy a similar tier of overall performance, despite their massive architectural differences.

Architecture Differences

The NVIDIA GeForce RTX 5090 D V2 is built on the Blackwell 2.0 architecture using the GB202 chip, fabricated on a 5 nm process at TSMC. It packs 92,200 million transistors into a 750 mm² die, yielding a transistor density of 122.9 million per square millimeter. The AMD Radeon R9 M380 uses the older GCN 2.0 architecture with the Strato chip, manufactured on a 28 nm process, also at TSMC. Its transistor count is a comparatively tiny 2,080 million on a 160 mm² die, resulting in a density of just 13.0 million per square millimeter. The contrast is stark: the NVIDIA chip crams roughly 44 times more transistors into a die that is less than five times larger.

The compute resources diverge dramatically. The RTX 5090 D V2 features 21,760 shading units, 680 texture mapping units, and 176 render output units. It also includes 170 dedicated ray tracing cores and 680 tensor cores. The R9 M380 offers 768 shading units, 48 TMUs, and 16 ROPs, with no ray tracing or tensor core hardware at all. Pixel throughput on the NVIDIA card reaches 423.6 GPixel/s, versus 16.00 GPixel/s on the AMD part. Texture fill rates are 1,636.8 GTexel/s and 48.00 GTexel/s respectively. In raw FP32 compute, the RTX 5090 D V2 delivers 104.8 TFLOPS, while the R9 M380 manages just 1.536 TFLOPS.

Memory subsystems are equally divergent. The RTX 5090 D V2 uses 24 GB of GDDR7 across a 384-bit bus, producing 1.34 TB/s of bandwidth. The R9 M380 has 4 GB of GDDR5 on a 128-bit bus, yielding 96.00 GB/s. That is a 14-fold difference in bandwidth. Clock speeds tell a different story in terms of process technology: the NVIDIA chip runs at a 2017 MHz base and 2407 MHz boost, while the AMD chip runs at 900 MHz base and 1000 MHz boost. The memory clocks are 1750 MHz (28 Gbps effective) versus 1500 MHz (6 Gbps effective). API support also differs, with the RTX 5090 D V2 supporting DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, while the R9 M380 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170.

The Verdict

The data points to two very different use cases. The NVIDIA GeForce RTX 5090 D V2 is a current, active product released on August 14, 2025, with a launch MSRP of 2,299 USD. It is designed for maximum compute throughput, with 104.8 TFLOPS of FP32 performance, 24 GB of GDDR7 memory, and support for ray tracing and tensor operations. Its 59th percentile ranking among all GPUs places it in the upper echelon of overall performance, even if its nearest rivals cluster closely. The AMD Radeon R9 M380 is an end-of-life mobile part from May 2015, with no ray tracing, no tensor cores, and a 4 GB GDDR5 frame buffer. Its 58th percentile ranking is remarkably high for a card of its age, but that ranking is based on aggregate scores across different test suites, not comparable workloads.

For a user seeking current-generation features like ray tracing, tensor acceleration, and high-bandwidth memory, the RTX 5090 D V2 is the only choice from the data. It also offers a larger memory pool, a wider bus, and dramatically higher fill rates. The R9 M380, however, demonstrates that older architectures can still compete in certain aggregate benchmark metrics. Its Geekbench Metal score of 18,476 exceeds its own OpenCL result by 47%, suggesting it performs particularly well in Apple's Metal API. The RTX 5090 D V2 has no Metal benchmark data, so cross-platform comparisons remain incomplete.

The practical verdict: the RTX 5090 D V2 is for workloads that demand the latest features and maximum raw throughput. The R9 M380 is a legacy part that holds up in specific API-bound tests, but its 4 GB memory limit and lack of modern acceleration features make it unsuitable for current high-end workloads. The percentile rankings being only one point apart (59 vs 58) is a statistical artifact of the different benchmark suites used, not evidence of comparable real-world performance.

Specification Differences

| Specification | NVIDIA GeForce RTX 5090 D V2 | AMD Radeon R9 M380 |

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

| Architecture | Blackwell 2.0 | GCN 2.0 |

| Process Node | 5 nm | 28 nm |

| Transistors | 92,200 million | 2,080 million |

| Die Size | 750 mm² | 160 mm² |

| Transistor Density | 122.9M / mm² | 13.0M / mm² |

| Base Clock | 2017 MHz | 900 MHz |

| Boost Clock | 2407 MHz | 1000 MHz |

| Memory Size | 24 GB | 4 GB |

| Memory Type | GDDR7 | GDDR5 |

| Memory Bus | 384 bit | 128 bit |

| Memory Bandwidth | 1.34 TB/s | 96.00 GB/s |

| Shading Units | 21,760 | 768 |

| TMUs | 680 | 48 |

| ROPs | 176 | 16 |

| RT Cores | 170 | None |

| Tensor Cores | 680 | None |

| Pixel Rate | 423.6 GPixel/s | 16.00 GPixel/s |

| Texture Rate | 1,636.8 GTexel/s | 48.00 GTexel/s |

| FP32 Compute | 104.8 TFLOPS | 1.536 TFLOPS |

| FP16 Compute | 104.8 TFLOPS (1:1) | Not specified |

| TDP | 575 W | Not specified |

| Bus Interface | PCIe 5.0 x16 | PCIe 3.0 x16 |

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

| Vulkan | 1.4 | 1.2.170 |

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

| Release Date | 2025-08-14 | 2015-05-04 |

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce RTX 5090 D V2 averages 16,504 across its single 3DMark Steel Nomad DX12 benchmark, while the AMD Radeon R9 M380 averages 15,521 across its Geekbench Metal and OpenCL tests. The NVIDIA card holds a 983-point advantage.

Q: How does the R9 M380 compare to its nearest rival, the GTX 1080 Ti?

A: The R9 M380's average score of 15,521 is 0.2% higher than the NVIDIA GeForce GTX 1080 Ti's 15,548, meaning the older AMD card edges out that rival in aggregate benchmark performance.

Q: Does the RTX 5090 D V2 support ray tracing?

A: Yes, it includes 170 dedicated ray tracing cores as part of its Blackwell 2.0 architecture. The AMD Radeon R9 M380 has no ray tracing cores at all.

Q: What is the memory bandwidth difference between the two cards?

A: The RTX 5090 D V2 offers 1.34 TB/s of bandwidth from 24 GB of GDDR7 on a 384-bit bus. The R9 M380 provides 96.00 GB/s from 4 GB of GDDR5 on a 128-bit bus — a roughly 14-fold difference.

Q: Which card is currently in production?

A: The NVIDIA GeForce RTX 5090 D V2 has an active production status, while the AMD Radeon R9 M380 is marked as end-of-life.

Q: How do their percentile rankings compare?

A: The RTX 5090 D V2 sits at the 59th percentile among all GPUs, while the R9 M380 is at the 58th percentile. Despite vastly different architectures and ages, both rank within one percentage point of each other in their respective benchmark pools.

DETAILED SPECIFICATIONS

SPECIFICATION
R9 M380
RTX 5090 D V2
Core Specs
Shading Units
768
21,760 +2733.3%
Shaders
768
21,760 +2733.3%
TMUs
48
680 +1316.7%
ROPs
16
176 +1000.0%
Compute Units
12
—
SM Count
—
170
Clocks
Base Clock
900 MHz
2017 MHz
Boost Clock
1000 MHz
2407 MHz
Memory Clock
1500 MHz 6 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
4 GB
24 GB
VRAM (MB)
4,096
24,576 +500.0%
Memory Type
GDDR5
GDDR7
Memory Bus
128 bit
384 bit
Bandwidth
96.00 GB/s
1.34 TB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
256 KB
96 MB
Performance
Pixel Rate
16.00 GPixel/s
423.6 GPixel/s
Texture Rate
48.00 GTexel/s
1,636.8 GTexel/s
FP32 (TFLOPS)
1.536 TFLOPS
104.8 TFLOPS
FP64 (TFLOPS)
96.00 GFLOPS (1:16)
1.637 TFLOPS (1:64)
FP16 (TFLOPS)
—
104.8 TFLOPS (1:1)
AI/RT
RT Cores
—
170
Tensor Cores
—
680
Power
TDP
—
575 W
TDP (W)
—
575
Suggested PSU
—
950 W
Power Connectors
—
1x 16-pin
Architecture
Architecture
GCN 2.0
Blackwell 2.0
GPU Name
Strato
GB202
Generation
Gem System (R9 M300)
GeForce 50
Process Size
28 nm
5 nm
Transistors
2,080 million
92,200 million
Die Size
160 mm²
750 mm²
Foundry
TSMC
TSMC
Density
13.0M / mm²
122.9M / mm²
API Support
DirectX
12 (12_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.4
OpenCL
2.1
3.0
CUDA
—
12.0
Shader Model
6.5
6.9
Physical
Slot Width
—
Dual-slot
Length
—
304 mm 12 inches
Height
—
137 mm 5.4 inches
Outputs
—
1x HDMI 2.1b3x DisplayPort 2.1b
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Other
Launch Price
—
2,299 USD
Production
End-of-life
Active
Predecessor
Solar System
GeForce 40
Successor
Polaris Mobile
GeForce 60
View Radeon R9 M380 Details View GeForce RTX 5090 D V2 Details