AMD Radeon 740M vs NVIDIA GeForce GTX 1080 Comparison

AMD
RADEON

AMD Radeon 740M

CORE STATE Phoenix2
VRAM System Shared
CLOCK SPEED 2800 MHz
TDP 45 W
BUS WIDTH System Shared
ARCHITECTURE RDNA 3.0
nm
PROCESS 4 nm
LAUNCH DATE 2024
VS
NVIDIA
GEFORCE

GeForce GTX 1080

CORE STATE GP104
VRAM 8 GB
CLOCK SPEED 1733 MHz
TDP 180 W
BUS WIDTH 256 bit
ARCHITECTURE Pascal
nm
PROCESS 16 nm
LAUNCH DATE 2016

PERFORMANCE BENCHMARKS

geekbench_opencl
10,172
51,204
geekbench_vulkan
15,568
30,398
3dmark_3dmark_steel_nomad_dx12
N/A
1,560
geekbench_metal
N/A
23,824
passmark_directx_10
N/A
93
passmark_directx_11
N/A
124
passmark_directx_12
N/A
55
passmark_directx_9
N/A
211
passmark_g2d
N/A
888
passmark_g3d
N/A
15,586
passmark_gpu_compute
N/A
7,614

Analysis: AMD Radeon 740M vs NVIDIA GeForce GTX 1080

The AMD Radeon 740M is an integrated graphics processor built on TSMC’s 4 nm process, while the NVIDIA GeForce GTX 1080 is a discrete, end-of-life add-in board from the GeForce 10-series. The data shows a stark contrast in raw performance, with the GTX 1080 winning both head-to-head benchmark tests, but the 740M counters with modern architecture features and dramatically lower power demands.

FAQ

Q: Which GPU is faster in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 1080 scores 51204, which is 80.1% ahead of the AMD Radeon 740M’s score of 10172. This is the largest performance gap between the two in any shared test.

Q: Does the AMD Radeon 740M support hardware ray tracing?

A: Yes. The 740M includes 4 RT cores as part of its RDNA 3.0 architecture. The NVIDIA GeForce GTX 1080, based on the older Pascal architecture, has no RT cores listed.

Q: What is the memory configuration of each card?

A: The Radeon 740M uses System Shared memory, meaning its size, type, and bus width are all system-dependent. The GTX 1080 features 8 GB of GDDR5X memory on a 256-bit bus, delivering 320.3 GB/s of bandwidth.

Q: How do their transistor counts and die sizes compare?

A: The Radeon 740M packs 20,900 million transistors on a 137 mm² die, giving a density of 152.6M transistors per mm². The GTX 1080 has 7,200 million transistors on a much larger 314 mm² die, with a density of 22.9M per mm².

Q: What is the performance percentile ranking for each GPU?

A: The Radeon 740M sits at the 53rd percentile among all GPUs, while the GTX 1080 is at the 51st percentile. Despite the GTX 1080’s dominant benchmark wins, their overall percentile standings are very close.

Q: Which GPU has a higher pixel fill rate?

A: The GTX 1080’s pixel rate is 110.9 GPixel/s, which is nearly five times the 740M’s 22.40 GPixel/s. The GTX 1080 also leads in texture rate with 277.3 GTexel/s versus 44.80 GTexel/s.

Where Each One Wins

The NVIDIA GeForce GTX 1080 is the clear performance winner in every direct comparison available. It wins both head-to-head tests: Geekbench OpenCL (51204 vs 10172) and Geekbench Vulkan (30398 vs 15568). Its strengths lie in raw throughput, with 2560 shading units, 160 TMUs, and 64 ROPs, which translate into 8.873 TFLOPS of FP32 performance. The GTX 1080 also has dedicated memory, with 8 GB of GDDR5X and 320.3 GB/s bandwidth, which is critical for high-resolution textures and sustained workloads.

The AMD Radeon 740M wins in efficiency and integration. Its TDP is 45 W compared to the GTX 1080’s 180 W, and it requires no power connectors, whereas the GTX 1080 needs a single 8-pin connector. The 740M is an IGP, meaning it occupies no expansion slot and relies on motherboard-dependent display outputs. This makes it suitable for compact, low-power systems where the GTX 1080’s 267 mm length and dual-slot width would be impractical.

Architecture Differences

The architectural divide is generational. The Radeon 740M uses RDNA 3.0, built on a 4 nm process at TSMC, and belongs to the Navi III IGP (Phoenix) generation. The GTX 1080 uses the Pascal architecture, fabricated on a 16 nm process, also at TSMC, and is part of the GeForce 10-series. The 740M’s process advantage is clear: 152.6M transistors per mm² versus 22.9M for the GTX 1080, even though the 740M has nearly three times the raw transistor count (20,900 million vs 7,200 million).

Feature-wise, the 740M supports DirectX 12 Ultimate (12_2), while the GTX 1080 only reaches DirectX 12 (12_1). The 740M has 4 RT cores for ray tracing; the GTX 1080 has none. Both support OpenGL 4.6 and Vulkan 1.4. The 740M’s FP16 performance is 1:1 with its FP32 (2.867 TFLOPS), whereas the GTX 1080’s FP16 is severely reduced at 138.6 GFLOPS (1:64 ratio), indicating the GTX 1080 is optimized for FP32 workloads.

Specification Differences

The two GPUs differ in nearly every measurable specification. The 740M’s base clock is 800 MHz with a boost of 2800 MHz, while the GTX 1080 starts at 1607 MHz and boosts to 1733 MHz. Memory is a major split: the 740M uses System Shared memory with system-dependent bandwidth, while the GTX 1080 has 8 GB of GDDR5X on a 256-bit bus with 320.3 GB/s. The shading units differ drastically: 256 on the 740M versus 2560 on the GTX 1080. TMUs are 16 vs 160, and ROPs are 8 vs 64.

Power delivery is also different: the 740M is rated at 45 W TDP with no power connectors, while the GTX 1080 draws 180 W and requires a 1x 8-pin connector, with a suggested PSU of 450 W. The bus interface is PCIe 4.0 x8 for the 740M versus PCIe 3.0 x16 for the GTX 1080. The GTX 1080 has physical dimensions of 267 mm length, 112 mm height, and 40 mm width, whereas the 740M is an IGP with no listed dimensions. The release dates are 2024-01-30 for the 740M and 2016-05-26 for the GTX 1080.

Head-to-Head Benchmarks

Only two shared benchmarks exist in the data, and the GTX 1080 wins both decisively. In Geekbench OpenCL, the GTX 1080 scores 51204 against the 740M’s 10172, a delta of -80.1% for the AMD part. This means the GTX 1080 is roughly five times faster in this compute-oriented test. The result aligns with the massive gap in shading units (2560 vs 256) and FP32 throughput (8.873 TFLOPS vs 2.867 TFLOPS).

In Geekbench Vulkan, the gap narrows but remains substantial. The GTX 1080 scores 30398, while the 740M scores 15568, giving a delta of -48.8%. This smaller gap suggests the 740M’s RDNA 3.0 architecture is relatively more competitive in Vulkan, possibly due to better driver optimization or architectural efficiency per compute unit. Still, the GTX 1080’s score is nearly double.

Looking at the broader benchmark context, the 740M’s average benchmark score is 12870, while the GTX 1080’s is 11960. This is surprising given the GTX 1080’s head-to-head dominance. The 740M’s nearest rivals include the AMD Radeon RX 580 (12928, delta -0.4%) and the NVIDIA GeForce GTX 590 (12830, delta 0.3%). The GTX 1080’s rivals include the NVIDIA GeForce GTX 1660 (11680, delta 2.4%) and the AMD Radeon RX 7800 XT (11627, delta 2.9%). This implies that in a wide range of tests, the 740M performs comparably to mid-range discrete GPUs from several generations ago, despite losing the specific tests shared with the GTX 1080.

The Verdict

The data is unambiguous for raw performance: the NVIDIA GeForce GTX 1080 is the superior GPU in every head-to-head test. It delivers 80.1% higher OpenCL scores and 48.8% higher Vulkan scores. Anyone needing maximum compute throughput, high pixel rates, or dedicated 8 GB of fast GDDR5X memory should choose the GTX 1080. Its 110.9 GPixel/s pixel rate and 277.3 GTexel/s texture rate dwarf the 740M’s figures.

However, the AMD Radeon 740M is not without a case. Its 45 W TDP is a quarter of the GTX 1080’s 180 W, it requires no external power, and it is an integrated solution with no slot footprint. For a compact, power-efficient build where the CPU already provides the platform, the 740M offers modern features like ray tracing and DirectX 12 Ultimate, which the GTX 1080 lacks. The 740M’s higher transistor density (152.6M / mm²) and smaller die (137 mm²) also point to a more modern, efficient design.

The GTX 1080 is end-of-life, while the 740M is active production. The GTX 1080 also had a launch MSRP of 599 USD, which is noted for historical context only. Ultimately, the choice depends on the workload: the GTX 1080 is for those who need brute force in legacy or FP32-heavy applications; the 740M is for those who prioritize efficiency, modern API support, and integration over raw speed. The benchmark data favors the GTX 1080 in raw scores, but the 740M’s architectural advantages and power profile make it a compelling alternative for specific use cases.

DETAILED SPECIFICATIONS

SPECIFICATION
740M
GTX 1080
Core Specs
Shading Units
256
2,560 +900.0%
Shaders
256
2,560 +900.0%
TMUs
16
160 +900.0%
ROPs
8
64 +700.0%
Compute Units
4
—
SM Count
—
20
Clocks
Base Clock
800 MHz
1607 MHz
Boost Clock
2800 MHz
1733 MHz
Memory Clock
System Shared
1251 MHz 10 Gbps effective
Memory
Memory Size
System Shared
8 GB
VRAM (MB)
—
8,192
Memory Type
System Shared
GDDR5X
Memory Bus
System Shared
256 bit
Bandwidth
System Dependent
320.3 GB/s
Cache
L1 Cache
128 KB per Array
48 KB (per SM)
L2 Cache
2 MB
2 MB
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
22.40 GPixel/s
110.9 GPixel/s
Texture Rate
44.80 GTexel/s
277.3 GTexel/s
FP32 (TFLOPS)
2.867 TFLOPS
8.873 TFLOPS
FP64 (TFLOPS)
179.2 GFLOPS (1:16)
277.3 GFLOPS (1:32)
FP16 (TFLOPS)
2.867 TFLOPS (1:1)
138.6 GFLOPS (1:64)
AI/RT
RT Cores
4
—
Power
TDP
45 W
180 W
TDP (W)
45
180 +300.0%
Suggested PSU
—
450 W
Power Connectors
None
1x 8-pin
Architecture
Architecture
RDNA 3.0
Pascal
GPU Name
Phoenix2
GP104
Generation
Navi III IGP (Phoenix)
GeForce 10
Process Size
4 nm
16 nm
Transistors
20,900 million
7,200 million
Die Size
137 mm²
314 mm²
Foundry
TSMC
TSMC
Density
152.6M / mm²
22.9M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
3.0
CUDA
—
6.1
Shader Model
6.8
6.8
Physical
Slot Width
IGP
Dual-slot
Length
—
267 mm 10.5 inches
Height
—
112 mm 4.4 inches
Outputs
Motherboard Dependent
1x DVI1x HDMI 2.03x DisplayPort 1.4a
Bus Interface
PCIe 4.0 x8
PCIe 3.0 x16
Other
Launch Price
—
599 USD
Production
Active
End-of-life
Predecessor
Navi II IGP
GeForce 900
Successor
Navi III IGP
GeForce 20
View Radeon 740M Details View GeForce GTX 1080 Details