NVIDIA GeForce RTX 4090 D vs Qualcomm Adreno 642 Full Specs

Summary

14,592 Shaders 2.52GHz	768 Shaders 550MHz
24GB GDDR6X1.01TB/s placeholder	Shared Memory25.6GB/s LPDDR5·LPDDR4X
Peak·FP32·FP16 73.54 TFLOPS	Peak·FP32·FP16 844.8 GFLOPS
Form Factor PCIe Card	Form Factor iGPU
TDP 450W	TDP 5W
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors -

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

GeForce RTX 4090 D2.35 POPSINT4 Tensor Sparse

x1392.87

Adreno 6421.69 TFLOPSFP16

x1

Show Top Score

Theoretical Performance

Clock Speed2520MHz UC·Base·Boost·OC	Clock Speed550MHz UC·Base·Boost·OC
Peak OPS 2.35 POPSINT4 Tensor Sparse	Peak OPS 1.69 TFLOPSFP16
Tensor FP8-16 588.3 TFLOPS FP8-16 Tensor Sparse 1.18 PFLOPS Tensor FP8-32 294.2 TFLOPS FP8-32 Tensor Sparse 588.3 TFLOPS	-
Tensor FP16-16 294.2 TFLOPS FP16-16 Tensor Sparse 588.3 TFLOPS Tensor FP16-32 147.1 TFLOPS FP16-32 Tensor Sparse 294.2 TFLOPS	-
BF16 73.54 TFLOPS Tensor BF16 147.1 TFLOPS BF16 Tensor Sparse 294.2 TFLOPS	-
Tensor TF32 73.54 TFLOPS	Tensor TF32 -
FP32 73.54 TFLOPS	FP32 844.8 GFLOPS
FP64 1.15 TFLOPS	FP64 211.2 GFLOPS
Tensor INT4 1.18 POPS	Tensor INT4 -
Tensor INT8 588.3 TOPS	-
Ray 170 TOPS	Ray -
Pixel Rate 443.5 GPixel/s	Pixel Rate 13.2 GPixel/s
Texture Rate 1.15 TTexel/s	Texture Rate 26.4 GTexel/s

Core Config

Shaders 14,592 Shaders	Shaders 768 Shaders
TMUs 456 TMUs	TMUs 48 TMUs
ROPs 176 ROPs	ROPs 24 ROPs
Tensor Cores 456 T-Cores	Tensor Cores -
RT Cores 114 RT-Cores	RT Cores -
SMs 114 SMs	EUs 6 EUs

Clocks

Base Clock 2.23GHz	Base Clock 490MHz
Boost Clock 2.52GHz	Boost Clock 550MHz

Cache

L1 64KB/SM Tex	L1 8KB/CU
L2 Cache 72MB shared	L2 Cache 128KB shared
L3 Cache -	L3 Cache 2MB shared

Memory

24GB GDDR6X placeholder	Shared Memory LPDDR5·LPDDR4X
Memory Bus 384-bit	Memory Bus 32-bit
Memory Speed 21GT/s	Memory Speed 6.4GT/s
Memory Bandwidth 1.01TB/s	Memory Bandwidth 25.6GB/s
ECC No	ECC No

Power & Thermals

TDP 450W	TDP 5W
Max Temp 90°C Max	Max Temp -

Video Output

Max Resolution 7680x4320	Max Resolution 2520x1080
Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 60Hz	Refresh Rate Calculator 1920x1080 Resolution1080p FHD Refresh Rate 78Hz
Multi-Monitor 4	Multi-Monitor 1
Adaptive Sync G-Sync FreeSync	Adaptive Sync -
DSC Supported	DSC Not Supported
HDCP HDCP 2.3	HDCP -

Ports

3x DisplayPort 1.4 1x HDMI 2.1

-

API Support

Shader Model 6.6	Shader Model -
DirectX DirectX 12 Direct3D 12_3	DirectX DirectX 12 Direct3D 12_1
OpenGL 4.6 OpenCL 3 Vulkan 1.3	OpenGL 3.2 OpenCL 2 Vulkan 1.1
CUDA 8.9 PureVideo HD VP12 VDPAU Feature Set L	-

Encoder

Encoder 2x NVENC 8	Encoder Hexagon 770
Codec - - - - - AVC (H.264) HEVC (H.265) AV1	Codec H.263 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) -

Decoder

Decoder NVDEC 5	Decoder Hexagon 770
Codec MPEG-1 MPEG-2 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) AV1	Codec MPEG-1 MPEG-2 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) -

Card

Form Factor PCIe Card	Form Factor iGPU
PCIe PCIe 4.0 x16 3-Slots	PCIe -
Height 137mm (5.39") Width 304mm (11.97") Depth 61mm (2.4")	-
Cooling Open-Air 2x Fans	Cooling Open-Air -
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors -

Chip

Manufacturer NVIDIA	Manufacturer Qualcomm
Chip Designer NVIDIA	Chip Designer Qualcomm
Architecture Ada Lovelace	Architecture Adreno 600
Family GeForce 40	Family Adreno 600
Branding	Branding
Codename NV182	Codename -
Chip Variant AD102-200-A1	Chip Variant -
Market Segment Desktop	Market Segment Smartphone
Release Date Dec 28, 2023	Release Date May 20, 2022

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 4N	Fabrication Node N6
Die Size 608mm²	Die Size -
Transistor Count 76.3B	Transistor Count -
Transistor Density 125.4 MTr/mm²	Transistor Density -

Images