Intel Arc A380E vs Intel Arc Pro B60 Dual Comparison

Intel
GPU

Intel Arc A380E

CORE STATE DG2-128
VRAM 6 GB
CLOCK SPEED 2000 MHz
TDP 75 W
BUS WIDTH 96 bit
ARCHITECTURE Xe-HPG
nm
PROCESS 6 nm
LAUNCH DATE 2024
VS
Intel
GPU

Arc Pro B60 Dual

CORE STATE BMG-G21
VRAM 24 GB
CLOCK SPEED 2400 MHz
TDP 400 W
BUS WIDTH 192 bit
ARCHITECTURE Xe2-HPG
nm
PROCESS 5 nm
LAUNCH DATE 2025

Analysis: Intel Arc A380E vs Intel Arc Pro B60 Dual

Intel Arc A380E and Intel Arc Pro B60 Dual represent two distinct generations of Intel's discrete GPU architecture, the Alchemist-based Arc 3 lineup and the Battlemage-based Pro series. The database shows a fundamental shift in positioning: the A380E is an entry-level, end-of-life part, while the B60 Dual is an active, high-performance workstation card. Without direct head-to-head benchmark scores, the analysis relies on the recorded specification data and architectural differences to establish performance expectations.

Head-to-Head Benchmarks

The database does not contain any recorded head-to-head benchmark scores for these two GPUs, and neither unit has a benchmark entry or a percentile rank beyond the median. The wins are therefore derived from the raw computational throughput and memory subsystem specifications.

The most significant advantage for the Intel Arc Pro B60 Dual is in raw compute throughput. Its FP32 performance is recorded at 12.29 TFLOPS, which is exactly three times the 4.096 TFLOPS of the A380E. This is a direct 200% advantage in single-precision floating-point operations. The FP16 figures follow the same pattern: the B60 Dual delivers 24.58 TFLOPS versus 8.192 TFLOPS on the A380E, again a 200% lead. This indicates that for any workload relying on shader or compute cores, the B60 Dual should complete tasks in roughly one-third of the time, assuming perfect scaling.

Memory bandwidth is another decisive win for the B60 Dual. It uses a 192-bit bus with GDDR6 memory at 19 Gbps effective, yielding 456.0 GB/s of bandwidth. The A380E uses a 96-bit bus at 15.5 Gbps effective, providing 186.0 GB/s. The B60 Dual's bandwidth is 2.45 times higher, a 145% increase. This matters for texture-heavy scenes, large data sets, and any operation that is memory-bound rather than compute-bound.

The texture and pixel throughput figures reinforce the gap. The B60 Dual achieves 384.0 GTexel/s and 192.0 GPixel/s, while the A380E achieves 128.0 GTexel/s and 64.00 GPixel/s. These are exactly 3x and 3x respectively, matching the FP32 ratio. The B60 Dual also has 20 ray tracing cores versus 8 on the A380E, and 2560 shading units versus 1024, a 2.5x increase in shading units and a 2.5x increase in ray tracing core count.

The only area where the A380E shows a relative advantage is in physical size and power delivery. The A380E has a 75 W TDP, while the B60 Dual is rated at 400 W. The A380E draws power through the PCIe slot with no external connectors, and its suggested power supply is 250 W. The B60 Dual requires a 16-pin connector and an 800 W power supply. In terms of efficiency, the A380E delivers 4.096 TFLOPS at 75 W, which is 0.0546 TFLOPS per watt. The B60 Dual delivers 12.29 TFLOPS at 400 W, which is 0.0307 TFLOPS per watt. The A380E is roughly 78% more power-efficient in raw FP32 per watt, but this does not compensate for the absolute performance deficit.

The Verdict

The recorded data indicates the Intel Arc Pro B60 Dual is the superior performer in every measurable computational category. It triples the FP32 and FP16 throughput, more than doubles the memory bandwidth, and provides 2.5 times the shading units and ray tracing cores. For any application that can utilize these resources, the B60 Dual is the clear choice. The A380E's only advantages are its lower power draw, smaller physical footprint, and a simpler power connector requirement.

The B60 Dual is positioned for professional workloads that demand high compute and large memory capacity. Its 24 GB memory size is four times the A380E's 6 GB, and its 456.0 GB/s bandwidth supports large data transfers. The A380E, with its 6 GB memory and 186.0 GB/s bandwidth, is suited for lighter tasks where the 75 W TDP and single-slot design are preferable.

The production status confirms this split: the A380E is end-of-life, while the B60 Dual is active. Users seeking a current, supported product with a longer lifecycle should select the B60 Dual. Users with a legacy system or strict power and space constraints might consider the A380E, but the data shows a massive performance gap that is unlikely to be bridged by any workload.

Architecture Differences

The two GPUs come from different architectural generations. The A380E uses the Xe-HPG architecture, specifically the DG2-128 chip, and belongs to the Alchemist (Arc 3) generation. The B60 Dual uses the Xe2-HPG architecture, based on the BMG-G21 chip, and belongs to the Battlemage (Pro Series) generation.

The manufacturing process differs: the A380E is built on a 6 nm node at TSMC, while the B60 Dual uses a 5 nm node at the same foundry. The transistor counts reflect the scale difference. The A380E has 7,200 million transistors on a 157 mm² die, giving a density of 45.9 million transistors per square millimeter. The B60 Dual has 19,600 million transistors on a 272 mm² die, for a density of 72.1 million per square millimeter. The newer 5 nm process and larger die allow the B60 Dual to pack nearly three times the transistors.

The memory subsystem is a major architectural divergence. The A380E uses a 96-bit bus with 6 GB of GDDR6. The B60 Dual uses a 192-bit bus with 24 GB of GDDR6, quadrupling the capacity and doubling the bus width. The effective memory clock is also higher on the B60 Dual: 19 Gbps versus 15.5 Gbps.

The compute resources scale accordingly. The B60 Dual has 2560 shading units, 160 texture mapping units, and 80 render output units. The A380E has 1024 shading units, 64 TMUs, and 32 ROPs. The ray tracing core count is 20 on the B60 Dual versus 8 on the A380E.

The bus interface differs: the A380E uses PCIe 4.0 x8, while the B60 Dual uses PCIe 5.0 x8. This doubles the potential host bandwidth for the B60 Dual, which is relevant for data transfer and CPU-GPU communication. Display outputs also differ: the A380E has four DisplayPort 2.0 connectors, while the B60 Dual has four mini-DisplayPort 2.1 connectors.

The APIs supported are identical: both offer DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Intel Arc Pro B60 Dual has an FP32 throughput of 12.29 TFLOPS, which is exactly three times the 4.096 TFLOPS of the Intel Arc A380E.

Q: How much memory does each GPU have?

A: The Intel Arc A380E has 6 GB of GDDR6 on a 96-bit bus. The Intel Arc Pro B60 Dual has 24 GB of GDDR6 on a 192-bit bus, four times the capacity and double the bus width.

Q: What is the memory bandwidth difference?

A: The Intel Arc Pro B60 Dual provides 456.0 GB/s of bandwidth, while the Intel Arc A380E provides 186.0 GB/s. The B60 Dual's bandwidth is 2.45 times higher.

Q: Are the power requirements significantly different?

A: Yes. The Intel Arc A380E has a 75 W TDP, requires no external power connectors, and suggests a 250 W power supply. The Intel Arc Pro B60 Dual has a 400 W TDP, requires a single 16-pin power connector, and suggests an 800 W power supply.

Q: Which GPU has more ray tracing cores?

A: The Intel Arc Pro B60 Dual has 20 ray tracing cores, compared to 8 on the Intel Arc A380E. This is a 2.5x increase.

Q: Are both GPUs currently in production?

A: No. The Intel Arc A380E is marked as end-of-life, while the Intel Arc Pro B60 Dual is marked as active in the database.

Where Each One Wins

The Intel Arc Pro B60 Dual wins in all raw performance categories. It has three times the FP32 and FP16 throughput, three times the pixel and texture fill rates, and 2.5 times the shading units and ray tracing cores. It also has four times the memory capacity and 2.45 times the memory bandwidth. The larger 24 GB frame buffer is suited for large 3D scenes, high-resolution textures, and compute workloads that require substantial data residency.

The B60 Dual's 192-bit memory bus and 456.0 GB/s bandwidth support multi-display setups and high-resolution output without bandwidth saturation. Its PCIe 5.0 x8 interface provides double the host link speed of the A380E's PCIe 4.0 x8, which reduces data transfer bottlenecks for streaming assets.

The Intel Arc A380E wins in power efficiency and physical integration. Its 75 W TDP allows it to run without auxiliary power connectors, and its single-slot design at 254 mm length, 127 mm height, and 20 mm width fits in compact chassis. The B60 Dual is a dual-slot card at 300 mm length, 110 mm height, and 40 mm width, requiring more space and a robust power delivery system.

The A380E also has a lower suggested power supply rating at 250 W versus 800 W, making it compatible with modest system power budgets. The A380E's 6 GB memory may be sufficient for lighter graphics tasks or legacy applications that do not demand high capacity.

Specification Differences

The two GPUs differ across nearly every specification field. The process node is 6 nm for the A380E and 5 nm for the B60 Dual, both from TSMC. The transistor count is 7,200 million versus 19,600 million, and the die size is 157 mm² versus 272 mm². Transistor density is 45.9 million per mm² on the A380E and 72.1 million per mm² on the B60 Dual.

The base clock is identical at 2000 MHz, but the boost clock differs: 2000 MHz on the A380E and 2400 MHz on the B60 Dual. The memory clock is 1937 MHz (15.5 Gbps effective) on the A380E and 2375 MHz (19 Gbps effective) on the B60 Dual.

The memory configuration is 6 GB GDDR6 on a 96-bit bus for the A380E, versus 24 GB GDDR6 on a 192-bit bus for the B60 Dual. Bandwidth is 186.0 GB/s versus 456.0 GB/s.

Compute resources: the A380E has 1024 shading units, 64 TMUs, 32 ROPs, and 8 ray tracing cores. The B60 Dual has 2560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores.

Pixel rate is 64.00 GPixel/s versus 192.0 GPixel/s, and texture rate is 128.0 GTexel/s versus 384.0 GTexel/s. FP32 is 4.096 TFLOPS versus 12.29 TFLOPS, and FP16 is 8.192 TFLOPS versus 24.58 TFLOPS.

The TDP is 75 W versus 400 W. Slot width is single-slot versus dual-slot. Power connectors are none versus 1x 16-pin. Suggested PSU is 250 W versus 800 W.

The bus interface is PCIe 4.0 x8 for the A380E and PCIe 5.0 x8 for the B60 Dual. Display outputs are 4x DisplayPort 2.0 versus 4x mini-DisplayPort 2.1.

Dimensions: the A380E is 254 mm long, 127 mm high, and 20 mm wide. The B60 Dual is 300 mm long, 110 mm high, and 40 mm wide.

Production status is end-of-life for the A380E and active for the B60 Dual. The release dates are March 31, 2024 for the A380E and September 4, 2025 for the B60 Dual. The A380E has a predecessor listed as Xe Graphics and a successor as Battlemage, while the B60 Dual has no predecessor or successor listed. The launch MSRP for the B60 Dual is 1,199 USD.

DETAILED SPECIFICATIONS

SPECIFICATION
A380E
Pro B60 Dual
Core Specs
Shading Units
1,024
2,560 +150.0%
Shaders
1,024
2,560 +150.0%
TMUs
64
160 +150.0%
ROPs
32
80 +150.0%
Execution Units
128
20 -84.4%
Clocks
Base Clock
2000 MHz
2000 MHz
Boost Clock
2000 MHz
2400 MHz
Memory Clock
1937 MHz 15.5 Gbps effective
2375 MHz 19 Gbps effective
Memory
Memory Size
6 GB
24 GB
VRAM (MB)
6,144
24,576 +300.0%
Memory Type
GDDR6
GDDR6
Memory Bus
96 bit
192 bit
Bandwidth
186.0 GB/s
456.0 GB/s
Cache
L2 Cache
4 MB
10 MB
Performance
Pixel Rate
64.00 GPixel/s
192.0 GPixel/s
Texture Rate
128.0 GTexel/s
384.0 GTexel/s
FP32 (TFLOPS)
4.096 TFLOPS
12.29 TFLOPS
FP64 (TFLOPS)
1,024.0 GFLOPS (1:4)
3.072 TFLOPS (1:4)
FP16 (TFLOPS)
8.192 TFLOPS (2:1)
24.58 TFLOPS (2:1)
AI/RT
RT Cores
8
20 +150.0%
XMX Cores
128
160 +25.0%
Power
TDP
75 W
400 W
TDP (W)
75
400 +433.3%
Suggested PSU
250 W
800 W
Power Connectors
None
1x 16-pin
Architecture
Architecture
Xe-HPG
Xe2-HPG
GPU Name
DG2-128
BMG-G21
Generation
Alchemist (Arc 3)
Battlemage (Pro Series)
Process Size
6 nm
5 nm
Transistors
7,200 million
19,600 million
Die Size
157 mm²
272 mm²
Foundry
TSMC
TSMC
Density
45.9M / mm²
72.1M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
Shader Model
6.6
6.6
Physical
Slot Width
Single-slot
Dual-slot
Length
254 mm 10 inches
300 mm 11.8 inches
Height
127 mm 5 inches
110 mm 4.3 inches
Outputs
4x DisplayPort 2.0
4x mini-DisplayPort 2.1
Bus Interface
PCIe 4.0 x8
PCIe 5.0 x8
Other
Launch Price
1,199 USD
Production
End-of-life
Active
Predecessor
Xe Graphics
Successor
Battlemage
View Arc A380E Details View Arc Pro B60 Dual Details