AMD Radeon R7 M370 vs NVIDIA GeForce GTX 675M Comparison

AMD
RADEON

AMD Radeon R7 M370

CORE STATE Litho
VRAM 2 GB
CLOCK SPEED 960 MHz
TDP —
BUS WIDTH 128 bit
ARCHITECTURE GCN 1.0
nm
PROCESS 28 nm
LAUNCH DATE 2015
VS
NVIDIA
GEFORCE

GeForce GTX 675M

CORE STATE GF114
VRAM 2 GB
CLOCK SPEED —
TDP 100 W
BUS WIDTH 256 bit
ARCHITECTURE Fermi 2.0
nm
PROCESS 40 nm
LAUNCH DATE 2012

PERFORMANCE BENCHMARKS

geekbench_opencl
7,063
6,946
geekbench_vulkan
6,465
N/A

Analysis: AMD Radeon R7 M370 vs NVIDIA GeForce GTX 675M

NVIDIA GeForce GTX 675M and AMD Radeon R7 M370 are both end-of-life mobile graphics solutions, but they represent different eras of GPU design. The data shows a single head-to-head benchmark result, with the AMD Radeon R7 M370 taking a narrow win in the Geekbench OpenCL test, scoring 7063 against the GTX 675M's 6946. This translates to a 1.7% delta in favor of the R7 M370, a margin that is statistically minor but does establish a performance pecking order. With the GTX 675M holding a 39th percentile ranking among all GPUs and the R7 M370 sitting at the 38th percentile, both parts are firmly in the entry-level segment of the mobile market, but the benchmark data suggests the newer AMD part has a slight edge in raw compute workloads.

Head-to-Head Benchmarks

The only direct comparison available is the Geekbench OpenCL test, which measures general-purpose compute performance. In this test, the AMD Radeon R7 M370 scores 7063 points, while the NVIDIA GeForce GTX 675M scores 6946 points. The delta is a modest 1.7% in favor of the AMD card, indicating that the two are essentially performance peers in this workload. The GTX 675M's nearest rivals in the database help contextualize its score: it sits just 1.1% behind the NVIDIA GeForce GTX 680M (which averages 7023), and it is within 1.3% of the NVIDIA T600 (7035). This places the GTX 675M in a tight cluster of similarly performing parts.

The R7 M370's position is equally telling. Its average benchmark score of 6764 is bolstered by a strong OpenCL result of 7063, but it also has a Vulkan score of 6465. When compared to its nearest rivals, the R7 M370 is 1% behind the AMD FirePro M5100 (6830) and 1% ahead of the NVIDIA GeForce GT 1010 (6698). The head-to-head delta of -1.7% from the perspective of the GTX 675M means that the R7 M370 is the clear, albeit narrow, winner in this metric. The data does not show a single benchmark win for the GTX 675M; all wins go to the R7 M370. This is a case where the newer architecture delivers a slight but measurable advantage in compute throughput, even though both cards target the same performance tier.

Where Each One Wins

Based strictly on the benchmark data, the AMD Radeon R7 M370 wins the only head-to-head comparison. The Geekbench OpenCL score of 7063 versus 6946 gives the AMD card a definitive, if thin, victory. This suggests that in compute-oriented tasks that leverage OpenCL, the R7 M370 is the more capable option. The R7 M370 also has a Vulkan benchmark score of 6465, which the GTX 675M lacks entirely, indicating that the AMD card has a functional advantage in Vulkan-based applications, whereas the GTX 675M has no recorded Vulkan performance data.

For the NVIDIA GeForce GTX 675M, there is no benchmark category where it emerges as the winner against the R7 M370. However, its score of 6946 is not far off the R7 M370's 7063, and the 1.7% delta is within the noise of typical run-to-run variance. The GTX 675M's rasterization-oriented specs, such as a higher pixel rate of 9.920 GPixel/s and a texture rate of 39.68 GTexel/s, suggest it may hold an advantage in traditional gaming workloads, but those metrics are not directly measured in the provided head-to-head tests. The data only supports a win for the R7 M370 in the OpenCL test, so that is the only definitive use-case advantage available.

Architecture Differences

The two GPUs come from different architectural generations and are built on different manufacturing processes. The NVIDIA GeForce GTX 675M is based on the GF114 chip using the Fermi 2.0 architecture, fabricated on a 40 nm process at TSMC. This is a large chip, with a die size of 332 mm² and 1,950 million transistors, resulting in a transistor density of 5.9 million per square millimeter. In contrast, the AMD Radeon R7 M370 uses the Litho chip with the GCN 1.0 architecture, built on a more modern 28 nm process at TSMC. The AMD chip is significantly smaller at 77 mm² and packs 950 million transistors, yielding a much higher transistor density of 12.3 million per square millimeter.

The core configurations differ substantially despite both having 384 shading units. The GTX 675M deploys 64 texture mapping units (TMUs) and 32 render output units (ROPs), while the R7 M370 has only 24 TMUs and 8 ROPs. This disparity explains the GTX 675M's higher pixel rate of 9.920 GPixel/s and texture rate of 39.68 GTexel/s, compared to the R7 M370's 7.680 GPixel/s and 23.04 GTexel/s. The GTX 675M also leads in raw FP32 compute performance, delivering 952.3 GFLOPS against the R7 M370's 737.3 GFLOPS, despite the AMD card having a higher memory clock. The R7 M370's clocks are explicitly listed with a base of 875 MHz and a boost of 960 MHz, whereas the GTX 675M has no base or boost clock listed. Memory configurations also differ: the GTX 675M uses a 256-bit bus with 96.00 GB/s of bandwidth, while the R7 M370 uses a 128-bit bus with 57.60 GB/s. Both cards have 2 GB of GDDR5 memory.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce GTX 675M has an average benchmark score of 6946, while the AMD Radeon R7 M370 has an average score of 6764. The GTX 675M's average is higher because it only has one recorded benchmark, whereas the R7 M370's average is pulled down by its Vulkan score of 6465.

Q: What is the performance difference in the head-to-head OpenCL test?

A: The AMD Radeon R7 M370 scores 7063, and the NVIDIA GeForce GTX 675M scores 6946. The delta is -1.7% from the GTX 675M's perspective, meaning the R7 M370 is 1.7% faster in this test.

Q: Do both GPUs support DirectX 12?

A: Yes, both support DirectX 12, but with different feature levels. The GTX 675M supports DirectX 12 (11_0), while the R7 M370 supports DirectX 12 (11_1). The R7 M370 also has Vulkan 1.2.170 support, while the GTX 675M has no listed Vulkan support.

Q: Which GPU has a higher memory bandwidth?

A: The NVIDIA GeForce GTX 675M has a memory bandwidth of 96.00 GB/s, which is significantly higher than the AMD Radeon R7 M370's 57.60 GB/s. This is due to the GTX 675M's 256-bit memory bus versus the R7 M370's 128-bit bus.

Q: How do the transistor counts compare?

A: The NVIDIA GeForce GTX 675M contains 1,950 million transistors on a 332 mm² die, while the AMD Radeon R7 M370 contains 950 million transistors on a 77 mm² die. The R7 M370 has a much higher transistor density of 12.3M per mm².

Q: What are the release dates for these GPUs?

A: The NVIDIA GeForce GTX 675M was released on March 21, 2012, and the AMD Radeon R7 M370 was released on May 4, 2015. Both are now end-of-life products.

Specification Differences

The following specifications differ between the two GPUs:

  • Chip: GF114 (NVIDIA) vs Litho (AMD)
  • Architecture: Fermi 2.0 (NVIDIA) vs GCN 1.0 (AMD)
  • Generation: GeForce 600M (NVIDIA) vs Gem System (R7 M300) (AMD)
  • Process Node: 40 nm (NVIDIA) vs 28 nm (AMD)
  • Transistors: 1,950 million (NVIDIA) vs 950 million (AMD)
  • Die Size: 332 mm² (NVIDIA) vs 77 mm² (AMD)
  • Transistor Density: 5.9M / mm² (NVIDIA) vs 12.3M / mm² (AMD)
  • Base Clock: Not listed (NVIDIA) vs 875 MHz (AMD)
  • Boost Clock: Not listed (NVIDIA) vs 960 MHz (AMD)
  • Memory Clock: 750 MHz / 3 Gbps effective (NVIDIA) vs 900 MHz / 3.6 Gbps effective (AMD)
  • Memory Bus Width: 256 bit (NVIDIA) vs 128 bit (AMD)
  • Memory Bandwidth: 96.00 GB/s (NVIDIA) vs 57.60 GB/s (AMD)
  • TMUs: 64 (NVIDIA) vs 24 (AMD)
  • ROPs: 32 (NVIDIA) vs 8 (AMD)
  • Pixel Rate: 9.920 GPixel/s (NVIDIA) vs 7.680 GPixel/s (AMD)
  • Texture Rate: 39.68 GTexel/s (NVIDIA) vs 23.04 GTexel/s (AMD)
  • FP32 Performance: 952.3 GFLOPS (NVIDIA) vs 737.3 GFLOPS (AMD)
  • TDP: 100 W (NVIDIA) vs not listed (AMD)
  • Slot Width: MXM Module (NVIDIA) vs not listed (AMD)
  • Power Connectors: None (NVIDIA) vs not listed (AMD)
  • Bus Interface: MXM-B (3.0) (NVIDIA) vs PCIe 3.0 x8 (AMD)
  • Display Outputs: Portable Device Dependent (NVIDIA) vs not listed (AMD)
  • DirectX Support: 12 (11_0) (NVIDIA) vs 12 (11_1) (AMD)
  • Vulkan Support: Not listed (NVIDIA) vs 1.2.170 (AMD)
  • Release Date: March 21, 2012 (NVIDIA) vs May 4, 2015 (AMD)
  • Predecessor: GeForce 500M (NVIDIA) vs Solar System (AMD)
  • Successor: GeForce 700M (NVIDIA) vs Polaris Mobile (AMD)

The Verdict

The benchmark data clearly favors the AMD Radeon R7 M370 in the only direct comparison available, with a 1.7% lead in Geekbench OpenCL. If you are choosing strictly on compute performance, the R7 M370 is the safer pick. It also offers Vulkan support, which the GTX 675M lacks, making it a more modern option for applications that leverage that API. The R7 M370's higher clock speeds and newer 28 nm process node contribute to its efficiency, though its smaller memory bus and lower bandwidth are notable drawbacks for memory-intensive tasks.

However, the NVIDIA GeForce GTX 675M should not be dismissed. Its higher FP32 compute rating of 952.3 GFLOPS, superior pixel rate of 9.920 GPixel/s, and texture rate of 39.68 GTexel/s indicate that it is built for traditional rasterization workloads. The GTX 675M also has double the memory bandwidth (96.00 GB/s vs 57.60 GB/s), which could make it better suited for high-resolution textures. The data shows the GTX 675M is competitive, sitting within 1.1% of the GTX 680M, a more powerful part. For users prioritizing raw OpenCL compute, the R7 M370 is the pick. For users who value memory bandwidth and higher fill rates, the GTX 675M has the spec sheet advantage, even if the single benchmark test does not confirm its superiority. Choose the R7 M370 for a slight compute edge and API compatibility; choose the GTX 675M for its architectural strengths in pixel and texture processing.

DETAILED SPECIFICATIONS

SPECIFICATION
R7 M370
GTX 675M
Core Specs
Shading Units
384
384 0.0%
Shaders
384
384 0.0%
TMUs
24
64 +166.7%
ROPs
8
32 +300.0%
Compute Units
6
—
SM Count
—
8
Clocks
Base Clock
875 MHz
—
Boost Clock
960 MHz
—
GPU Clock
—
620 MHz
Shader Clock
—
1240 MHz
Memory Clock
900 MHz 3.6 Gbps effective
750 MHz 3 Gbps effective
Memory
Memory Size
2 GB
2 GB
VRAM (MB)
2,048
2,048 0.0%
Memory Type
GDDR5
GDDR5
Memory Bus
128 bit
256 bit
Bandwidth
57.60 GB/s
96.00 GB/s
Cache
L1 Cache
16 KB (per CU)
64 KB (per SM)
L2 Cache
256 KB
512 KB
Performance
Pixel Rate
7.680 GPixel/s
9.920 GPixel/s
Texture Rate
23.04 GTexel/s
39.68 GTexel/s
FP32 (TFLOPS)
737.3 GFLOPS
952.3 GFLOPS
FP64 (TFLOPS)
46.08 GFLOPS (1:16)
79.36 GFLOPS (1:12)
Power
TDP
—
100 W
TDP (W)
—
100
Power Connectors
—
None
Architecture
Architecture
GCN 1.0
Fermi 2.0
GPU Name
Litho
GF114
Generation
Gem System (R7 M300)
GeForce 600M
Process Size
28 nm
40 nm
Transistors
950 million
1,950 million
Die Size
77 mm²
332 mm²
Foundry
TSMC
TSMC
Density
12.3M / mm²
5.9M / mm²
API Support
DirectX
12 (11_1)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.2.170
—
OpenCL
2.1 (1.2)
1.1
CUDA
—
2.1
Shader Model
6.5 (5.1)
5.1
Physical
Slot Width
—
MXM Module
Outputs
—
Portable Device Dependent
Bus Interface
PCIe 3.0 x8
MXM-B (3.0)
Other
Production
End-of-life
End-of-life
Predecessor
Solar System
GeForce 500M
Successor
Polaris Mobile
GeForce 700M
View Radeon R7 M370 Details View GeForce GTX 675M Details