GPU Comparison
GPU
Intel Iris Pro Graphics 5200
CORE STATE
Haswell GT3e
VRAM
System Shared
CLOCK SPEED
1150 MHz
TDP
45 W
BUS WIDTH
System Shared
ARCHITECTURE
Generation 7.5
PROCESS
22 nm
LAUNCH DATE
2013
VS
GEFORCE
RTX A4000
CORE STATE
GA104
VRAM
16 GB
CLOCK SPEED
1560 MHz
TDP
140 W
BUS WIDTH
256 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2021
PERFORMANCE BENCHMARKS
geekbench_opencl
3dmark_3dmark_steel_nomad_dx12
geekbench_vulkan
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
DETAILED SPECIFICATIONS
SPECIFICATION
Iris Pro Graphics 5200
RTX A4000
Core Specs
Shading Units
320
6,144
+1820.0%
Shaders
320
6,144
+1820.0%
TMUs
40
192
+380.0%
ROPs
4
96
+2300.0%
SM Count
—
48
Execution Units
40
—
Clocks
Base Clock
200 MHz
735 MHz
Boost Clock
1150 MHz
1560 MHz
Memory Clock
System Shared
1750 MHz
14 Gbps effective
Memory
Memory Size
System Shared
16 GB
VRAM (MB)
—
16,384
Memory Type
System Shared
GDDR6
Memory Bus
System Shared
256 bit
Bandwidth
System Dependent
448.0 GB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
—
4 MB
Performance
Pixel Rate
4.600 GPixel/s
149.8 GPixel/s
Texture Rate
46.00 GTexel/s
299.5 GTexel/s
FP32 (TFLOPS)
736.0 GFLOPS
19.17 TFLOPS
FP64 (TFLOPS)
184.0 GFLOPS (1:4)
299.5 GFLOPS (1:64)
FP16 (TFLOPS)
—
19.17 TFLOPS (1:1)
AI/RT
RT Cores
—
48
Tensor Cores
—
192
Power
TDP
45 W
140 W
TDP (W)
45
140
+211.1%
Suggested PSU
—
300 W
Power Connectors
—
1x 6-pin
Architecture
Architecture
Generation 7.5
Ampere
GPU Name
Haswell GT3e
GA104
Generation
HD Graphics
(Haswell)
Workstation Ampere
(Ax000)
Process Size
22 nm
8 nm
Transistors
—
17,400 million
Die Size
—
392 mm²
Foundry
Intel
Samsung
Density
—
44.4M / mm²
API Support
DirectX
12 (11_1)
12 Ultimate (12_2)
OpenGL
4.3
4.6
Vulkan
1.0
1.4
OpenCL
1.2
3.0
CUDA
—
8.6
Shader Model
5.1
6.8
Physical
Slot Width
IGP
Single-slot
Length
—
241 mm
9.5 inches
Height
—
112 mm
4.4 inches
Outputs
Motherboard Dependent
4x DisplayPort 1.4a
Bus Interface
Ring Bus
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
—
Quadro Turing
Successor
—
Workstation Ada