AMD Radeon R9 370X vs AMD Radeon RX Vega 11 Comparison

AMD
RADEON

AMD Radeon R9 370X

CORE STATE Trinidad
VRAM 2 GB
CLOCK SPEED 1030 MHz
TDP 180 W
BUS WIDTH 256 bit
ARCHITECTURE GCN 1.0
nm
PROCESS 28 nm
LAUNCH DATE 2015
VS
AMD
RADEON

Radeon RX Vega 11

CORE STATE Picasso
VRAM System Shared
CLOCK SPEED 1400 MHz
TDP 15 W
BUS WIDTH System Shared
ARCHITECTURE GCN 5.0
nm
PROCESS 12 nm
LAUNCH DATE 2019

PERFORMANCE BENCHMARKS

geekbench_metal
12,676
17,086
geekbench_opencl
25,893
12,525
geekbench_vulkan
9,018
13,543

Analysis: AMD Radeon R9 370X vs AMD Radeon RX Vega 11

AMD Radeon R9 370X and AMD Radeon RX Vega 11 are two very different AMD graphics solutions separated by architecture, process node, and intended use case, yet their benchmark data reveals a surprisingly close overall contest. The R9 370X, a 2015 discrete card, wins the average benchmark score battle with 15,862 versus the Vega 11's 14,385, a 10.3% advantage, but the Vega 11 IGP claims victory in two of three individual tests. The R9 370X dominates in OpenCL compute with a 106.7% lead, while the Vega 11 counters with decisive wins in Metal and Vulkan, making the choice strictly dependent on the workload, not raw aggregate performance.

The Verdict

The data points to a clear split decision: pick the AMD Radeon R9 370X if your priority is raw compute throughput or legacy API performance, and pick the AMD Radeon RX Vega 11 if you are working within a modern, power-constrained system and value newer API support. The R9 370X delivers a massive 106.7% higher score in Geekbench OpenCL (25,893 vs 12,525), demonstrating its strength in general-purpose compute tasks. However, the Vega 11, despite being an integrated processor graphics unit, wins Geekbench Metal by 34.8% (17,086 vs 12,676) and Geekbench Vulkan by 50.2% (13,543 vs 9,018), indicating superior performance in modern graphics APIs. The R9 370X holds a higher percentile ranking at 58th versus the Vega 11's 56th, and its nearest rivals include the AMD Radeon RX 7700 (0.1% behind) and the NVIDIA GeForce RTX 3060 Ti (1.7% ahead), placing it in surprisingly modern company. The Vega 11, in contrast, trades blows with the NVIDIA GeForce GTX TITAN and GTX 965M, showing it is competitive with decade-old discrete cards despite being an IGP.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R9 370X has a higher average benchmark score of 15,862, which is 10.3% above the AMD Radeon RX Vega 11's average of 14,385.

Q: Why does the R9 370X win in OpenCL but lose in Metal and Vulkan?

A: The R9 370X scores 25,893 in Geekbench OpenCL, a 106.7% advantage over the Vega 11's 12,525, indicating superior compute performance. Conversely, the Vega 11 scores 17,086 in Metal and 13,543 in Vulkan, outperforming the R9 370X's 12,676 and 9,018 respectively, likely due to its newer GCN 5.0 architecture with better API optimization.

Q: How do their transistor densities compare?

A: The Vega 11, built on a 12 nm process, has a transistor density of 23.5M per mm², which is 78% higher than the R9 370X's 13.2M per mm², despite both having nearly identical die sizes (210 mm² vs 212 mm²).

Q: What are the power consumption differences?

A: The R9 370X has a TDP of 180 W and requires dual 6-pin power connectors with a suggested 450 W PSU, while the Vega 11 has a TDP of just 15 W, uses no power connectors, and has no suggested PSU, reflecting its integrated nature.

Q: What is the memory configuration of each GPU?

A: The R9 370X uses 2 GB of GDDR5 memory on a 256-bit bus with 179.2 GB/s bandwidth, whereas the Vega 11 relies on System Shared memory with a System Dependent bandwidth, which is a critical performance bottleneck for the IGP.

Q: Which GPU has better Vulkan API support?

A: The Vega 11 supports Vulkan 1.3, while the R9 370X supports Vulkan 1.2.170, and this is reflected in benchmarks where the Vega 11 scores 13,543 in Geekbench Vulkan, a 50.2% improvement over the R9 370X's 9,018.

Architecture Differences

The two GPUs represent distinct generations of AMD's Graphics Core Next (GCN) architecture, with the R9 370X based on GCN 1.0 and the Vega 11 based on GCN 5.0. This generational gap is reflected in their manufacturing processes: the R9 370X uses a 28 nm process at TSMC, while the Vega 11 uses a 12 nm process at GlobalFoundries. The process shrink allows the Vega 11 to pack 4,940 million transistors into a 210 mm² die, achieving a density of 23.5M transistors per mm², compared to the R9 370X's 2,800 million transistors on a 212 mm² die at 13.2M per mm². The Vega 11's chip is codenamed Picasso, while the R9 370X uses the Trinidad chip. The R9 370X belongs to the Pirate Islands (R9 300) generation, whereas the Vega 11 is from the Vega IGP (Picasso) generation, with predecessors of Volcanic Islands and GCN 3.0 IGP respectively. The R9 370X supports DirectX 12 (11_1) and Vulkan 1.2.170, while the Vega 11 supports DirectX 12 (12_1) and Vulkan 1.3, giving the IGP a newer API feature set. Both support OpenGL 4.6, but the Vega 11's newer GCN 5.0 architecture likely contributes to its superior Metal and Vulkan performance, while the R9 370X's older GCN 1.0 design excels in raw compute workloads.

Specification Differences

The specification disparity between these two GPUs is stark, beginning with their fundamental nature as a discrete card versus an integrated processor. The R9 370X has 1,280 shading units, 80 TMUs, and 32 ROPs, while the Vega 11 has 704 shading units, 44 TMUs, and only 8 ROPs, representing a 45% reduction in shaders and a 75% reduction in ROPs. Clock speeds differ dramatically: the R9 370X runs at a base of 980 MHz and boost of 1030 MHz, while the Vega 11 has a low 300 MHz base but a high 1400 MHz boost, reflecting its power-saving idle behavior and burst performance. Memory is a fundamental split, with the R9 370X using 2 GB of GDDR5 on a 256-bit bus with 179.2 GB/s bandwidth, whereas the Vega 11 uses System Shared memory with System Dependent bandwidth. The R9 370X achieves a pixel rate of 32.96 GPixel/s and texture rate of 82.40 GTexel/s, versus the Vega 11's 11.20 GPixel/s and 61.60 GTexel/s. FP32 performance favors the R9 370X at 2.637 TFLOPS versus 1.971 TFLOPS for the Vega 11, though the Vega 11 supports FP16 at 3.942 TFLOPS (2:1) while the R9 370X has no FP16 capability. Power consumption is an order of magnitude apart: 180 W TDP for the R9 370X versus 15 W for the Vega 11, with the former being dual-slot and the latter being an IGP with no dimensions listed.

Head-to-Head Benchmarks

The benchmark results reveal a clear pattern of specialization. In Geekbench OpenCL, the AMD Radeon R9 370X delivers a decisive victory with a score of 25,893, which is 106.7% higher than the Vega 11's 12,525, effectively doubling the IGP's compute output. This massive margin aligns with the R9 370X's superior shading units (1,280 vs 704), higher FP32 throughput (2.637 vs 1.971 TFLOPS), and dedicated GDDR5 memory with 179.2 GB/s bandwidth versus the Vega 11's system-dependent memory. However, the tables turn in Geekbench Metal, where the Vega 11 scores 17,086 against the R9 370X's 12,676, a 34.8% advantage for the IGP. This result is notable because the R9 370X has nearly twice the shading units, yet the Vega 11's newer GCN 5.0 architecture and support for DirectX 12 (12_1) versus 11_1 appears to translate into better API-level efficiency in Metal. The Vulkan test shows an even larger gap: the Vega 11 scores 13,543 versus the R9 370X's 9,018, a 50.2% difference, again favoring the newer architecture with Vulkan 1.3 support. The aggregate average benchmark score favors the R9 370X at 15,862 versus 14,385, a 10.3% difference, primarily driven by its OpenCL dominance. The R9 370X's nearest rival is the AMD Radeon RX 7700 with a delta of 0.1%, while the Vega 11's nearest rival is the NVIDIA GeForce GTX TITAN at 0.1%, indicating that both GPUs punch near their respective weight classes in the broader market.

Where Each One Wins

AMD Radeon R9 370X wins decisively in compute-heavy workloads, as evidenced by its 106.7% lead in Geekbench OpenCL. This makes it the superior choice for applications that leverage general-purpose GPU computing, such as rendering, scientific simulation, or any task that uses OpenCL acceleration. The R9 370X also holds the overall average benchmark crown at 15,862 versus 14,385, and its higher pixel rate (32.96 vs 11.20 GPixel/s) and texture rate (82.40 vs 61.60 GTexel/s) suggest better fill-rate-bound performance in legacy rasterization scenarios. Its nearest rivals include the AMD Radeon RX 7700 and NVIDIA GeForce RTX 3060 Ti, placing it in the company of modern mid-range discrete GPUs in aggregate score. The R9 370X is also the only one of the two with a launch MSRP, listed at 199 USD, though its end-of-life status and 180 W power draw are notable trade-offs.

AMD Radeon RX Vega 11 wins in modern graphics API benchmarks, taking Geekbench Metal by 34.8% (17,086 vs 12,676) and Geekbench Vulkan by 50.2% (13,543 vs 9,018). This makes it the better option for users running applications that utilize Metal (e.g., macOS environments) or Vulkan (modern games and engines), where its GCN 5.0 architecture and DirectX 12 (12_1) support provide tangible benefits. The Vega 11's 15 W TDP and integrated nature make it ideal for low-power, compact systems where a discrete card is impractical. Its FP16 capability of 3.942 TFLOPS (2:1) is an advantage over the R9 370X's lack of FP16, potentially benefiting certain machine learning or media workloads. The Vega 11 also offers newer API support with Vulkan 1.3 and DirectX 12 (12_1), future-proofing it for software that requires these standards. Its nearest rivals include the NVIDIA GeForce GTX TITAN and Intel Iris Xe MAX Graphics, showing it competes with older discrete cards and modern IGPs, respectively.

DETAILED SPECIFICATIONS

SPECIFICATION
R9 370X
RX Vega 11
Core Specs
Shading Units
1,280
704 -45.0%
Shaders
1,280
704 -45.0%
TMUs
80
44 -45.0%
ROPs
32
8 -75.0%
Compute Units
24
11 -54.2%
Clocks
Base Clock
980 MHz
300 MHz
Boost Clock
1030 MHz
1400 MHz
Memory Clock
1400 MHz 5.6 Gbps effective
System Shared
Memory
Memory Size
2 GB
System Shared
VRAM (MB)
2,048
—
Memory Type
GDDR5
System Shared
Memory Bus
256 bit
System Shared
Bandwidth
179.2 GB/s
System Dependent
Cache
L1 Cache
16 KB (per CU)
—
L2 Cache
512 KB
—
Performance
Pixel Rate
32.96 GPixel/s
11.20 GPixel/s
Texture Rate
82.40 GTexel/s
61.60 GTexel/s
FP32 (TFLOPS)
2.637 TFLOPS
1.971 TFLOPS
FP64 (TFLOPS)
164.8 GFLOPS (1:16)
123.2 GFLOPS (1:16)
FP16 (TFLOPS)
—
3.942 TFLOPS (2:1)
Power
TDP
180 W
15 W
TDP (W)
180
15 -91.7%
Suggested PSU
450 W
—
Power Connectors
2x 6-pin
None
Architecture
Architecture
GCN 1.0
GCN 5.0
GPU Name
Trinidad
Picasso
Generation
Pirate Islands (R9 300)
Vega IGP (Picasso)
Process Size
28 nm
12 nm
Transistors
2,800 million
4,940 million
Die Size
212 mm²
210 mm²
Foundry
TSMC
GlobalFoundries
Density
13.2M / mm²
23.5M / mm²
API Support
DirectX
12 (11_1)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.3
OpenCL
2.1 (1.2)
2.1
Shader Model
6.5 (5.1)
6.7
Physical
Slot Width
Dual-slot
IGP
Length
221 mm 8.7 inches
—
Height
111 mm 4.4 inches
—
Outputs
2x DVI1x HDMI 1.4a1x DisplayPort 1.2
Motherboard Dependent
Bus Interface
PCIe 3.0 x16
IGP
Other
Launch Price
199 USD
—
Production
End-of-life
End-of-life
Predecessor
Volcanic Islands
GCN 3.0 IGP
Successor
Arctic Islands
Vega II IGP
View Radeon R9 370X Details View Radeon RX Vega 11 Details