Difference between revisions of "SHA-3 Hardware Implementations"

From The ECRYPT Hash Function Website
m (High-Speed Implementations (FPGA): Added CubeHash results from Baldwin et al.)
m (High-Speed Implementations (FPGA): Added Groestl results from Baldwin et al.)
Line 66: Line 66:
 
|-
 
|-
 
| Grøstl-384/512  || [http://www.groestl.info/Groestl.pdf Submission document]  || [[#Fully_Autonomous_Implementation|Fully autonomous]]  || P & Q permutation in parallel  || Xilinx Spartan 3  || align="right"| 20233 slices  || align="right"| 5901 Mbit/s  || align="right"| 80.7 MHz
 
| Grøstl-384/512  || [http://www.groestl.info/Groestl.pdf Submission document]  || [[#Fully_Autonomous_Implementation|Fully autonomous]]  || P & Q permutation in parallel  || Xilinx Spartan 3  || align="right"| 20233 slices  || align="right"| 5901 Mbit/s  || align="right"| 80.7 MHz
 +
|-
 +
| Grøstl-384/512  || [http://eprint.iacr.org/2009/342.pdf Baldwin et al.]  || [[#Implementation_of_Core_Functionality|Core functionality]]  || P & Q permutation interleaved, S-box in BRAM  || Xilinx Spartan 3  || align="right"| 6313 slices  || align="right"| 2910 Mbit/s  || align="right"| 79.61 MHz
 
|-
 
|-
 
| Grøstl-384/512  || [http://www.groestl.info/Groestl.pdf Submission document]  || [[#Fully_Autonomous_Implementation|Fully autonomous]]  || P & Q permutation in parallel  || Xilinx Virtex 5  || align="right"| 5419 slices  || align="right"| 15395 Mbit/s  || align="right"| 210.5 MHz
 
| Grøstl-384/512  || [http://www.groestl.info/Groestl.pdf Submission document]  || [[#Fully_Autonomous_Implementation|Fully autonomous]]  || P & Q permutation in parallel  || Xilinx Virtex 5  || align="right"| 5419 slices  || align="right"| 15395 Mbit/s  || align="right"| 210.5 MHz

Revision as of 15:20, 15 July 2009

1 Important Information

This page summarizes key properties of reported hardware implementations of the SHA-3 candidates. This is work in progress. The implementations are categorized into FPGA and standard-cell ASIC implementations.

Note that the diversity of implementation scope, target technologies, and synthesis tools makes direct comparisions between different hardware implementation difficult. The more of these parameters agree, the more reasonable the comparison becomes.

The target technology should be as similar as possible. For FPGA implementation, it is desirable to compare implementations on the same target device (or at least on devices of the same FPGA family). For standard-cell ASIC implementation, at least the minimal gate length of the process (e.g., 0.13 µm) should agree. More ideally, the implementations use the same standard-cell library (which implies the use of the same process technology).

In order to facilitate the comparision of hardware modules with different implementation scopes, we classify them into three categories:

For suggestions regarding the structure of this site, let us know at sha3zoo-hardware@iaik.tugraz.at

1.1 Fully Autonomous Implementation

HW type self-cont.jpg

Such hardware implementations include the complete functionality of a SHA-3 candidate (or a specific version thereof). That means the input message can be loaded piecewise into the hardware module and it delivers the message digest as output. All hash calculations happen exclusively within the hardware module. If integrated in a system, the achievable throughput of a fully autonomous implementation depends on the speed of the hardware module itself and the speed of the (system dependent) data interface delivering the input message.


1.2 Implementation with External Memory

HW type ext-mem.jpg

These implementations use external memory to hold intermediate values during the hashing of a message. The implemented hardware itself normally consists of the core logic functionality of the hash function, some registers for short-lived temporary values, and possible a memory controller for access to the external memory. Such implementations can load the input message either over a dedicated interface (similar to a fully autonomous implementation) or from the external memory. In order to reach the maximal throughput of the hardware module, the external memory must be sufficiently fast.


1.3 Implementation of Core Functionality

HW type core-funct.jpg

Such implementations comprise only important parts of the hash function (e.g., the compression function), which normally allows to get a first-order estimate of the performance figures of full implementations.

2 High-Speed Implementations (FPGA)

Important note: The size and functionality of slices varies between FPGA families. A direct comparision of the slice count of implementations on different FPGA families is therefore problematic.

Hash Function Name Reference Impl. Scope Impl. Details Technology Size Throughput Clock Frequency
BLAKE-32 Submission document Core functionality Compression function with 8 G function units Xilinx Virtex-II Pro 3091 slices 1724 Mbit/s 37.0 MHz
BLAKE-32 Submission document Core functionality Compression function with 8 G function units Xilinx Virtex 4 3087 slices 2235 Mbit/s 48.0 MHz
BLAKE-32 Submission document Core functionality Compression function with 8 G function units Xilinx Virtex 5 1694 slices 3103 Mbit/s 67.0 MHz
BLAKE-64 Submission document Core functionality Compression function with 8 G function units Xilinx Virtex-II Pro 11122 slices 1177 Mbit/s 17.0 MHz
BLAKE-64 Submission document Core functionality Compression function with 8 G function units Xilinx Virtex 4 11483 slices 1707 Mbit/s 25.0 MHz
BLAKE-64 Submission document Core functionality Compression function with 8 G function units Xilinx Virtex 5 4329 slices 2389 Mbit/s 35.0 MHz
CHI-224/256 Submission document Fully autonomous Iterative implementation Xilinx Virtex 2 1582 slices 3200 Mbit/s 126.0 MHz
CubeHash8/1-256 Baldwin et al. Core functionality 2 compression functions unrolled Xilinx Spartan 3 3268 slices 70 Mbit/s 37.9 MHz
CubeHash8/1-256 Baldwin et al. Core functionality 1 iterated compression function Xilinx Virtex 5 1178 slices 160 Mbit/s 166.8 MHz
Grøstl-224/256 Jungk et al. Fully autonomous P & Q permutation in parallel Xilinx Spartan 3 6136 slices 4520 Mbit/s 88.3 MHz
Grøstl-224/256 Submission document Fully autonomous P & Q permutation in parallel Xilinx Virtex 5 1722 slices 10276 Mbit/s 200.7 MHz
Grøstl-384/512 Submission document Fully autonomous P & Q permutation in parallel Xilinx Spartan 3 20233 slices 5901 Mbit/s 80.7 MHz
Grøstl-384/512 Baldwin et al. Core functionality P & Q permutation interleaved, S-box in BRAM Xilinx Spartan 3 6313 slices 2910 Mbit/s 79.61 MHz
Grøstl-384/512 Submission document Fully autonomous P & Q permutation in parallel Xilinx Virtex 5 5419 slices 15395 Mbit/s 210.5 MHz
Keccak Updated specification (v1.2) Fully autonomous Core (round function, state register) & IO buffer Altera Cyclone III 5776 LEs 7500 Mbit/s 133 MHz
Keccak Updated specification (v1.2) Fully autonomous Core (round function, state register) & IO buffer Altera Stratix III 4713 ALUTs 12400 Mbit/s 218 MHz
Keccak Joachim Strömbergson Fully autonomous Core (round function, state register) only Xilinx Spartan 3A 3393 slices 4800 Mbit/s 85 MHz
Keccak Updated specification (v1.2) Fully autonomous Core (round function, state register) & IO buffer Xilinx Virtex 5 1412 slices 6900 Mbit/s 122 MHz
MD6 Submission document Core functionality Compression function with 16 parallel steps Xilinx Virtex-II Pro 5313 slices 1232 Mbit/s 150.3 MHz
MD6 Submission document Core functionality Compression function with 32 parallel steps Xilinx Virtex-II Pro 7529 slices 1894 Mbit/s 141.6 MHz
MD6-256 Henzen et al. Fully autonomous Sequential mode (L=0), compression function with 16 parallel steps Xilinx Virtex-4 4465 slices 8440 Mbit/s 286 MHz
MD6-512 Henzen et al. Fully autonomous Sequential mode (L=0), compression function with 16 parallel steps Xilinx Virtex-4 4515 slices 5254 Mbit/s 286 MHz
Skein-256 Men Long Core functionality UBI component Xilinx Virtex 5 1001 slices 408.7 Mbit/s 114.9 MHz
Skein-256 Stefan Tillich Fully autonomous 8 Threefish rounds unrolled Xilinx Virtex 5 937 slices 1751 Mbit/s 68.4 MHz
Skein-256 Stefan Tillich Fully autonomous 8 Threefish rounds unrolled Xilinx Spartan 3 2421 slices 669 Mbit/s 26.14 MHz
Skein-512 Men Long Core functionality UBI component Xilinx Virtex 5 1877 slices 817.4 Mbit/s 114.9 MHz
Skein-512 Stefan Tillich Fully autonomous 8 Threefish rounds unrolled Xilinx Virtex 5 1632 slices 3535 Mbit/s 69.04 MHz
Skein-512 Stefan Tillich Fully autonomous 8 Threefish rounds unrolled Xilinx Spartan 3 4273 slices 1365 Mbit/s 26.66 MHz



3 Low-Area Implementations (FPGA)

Hash Function Name Reference Impl. Scope Implementation Details Technology Size Throughput Clock Frequency
BLAKE-32 Submission document Core functionality Compression function with 1 G function unit Xilinx Virtex-II Pro 958 slices 371 Mbit/s 59.0 MHz
BLAKE-32 Submission document Core functionality Compression function with 1 G function unit Xilinx Virtex 4 960 slices 430 Mbit/s 68.0 MHz
BLAKE-32 Submission document Core functionality Compression function with 1 G function unit Xilinx Virtex 5 390 slices 575 Mbit/s 91.0 MHz
BLAKE-64 Submission document Core functionality Compression function with 1 G function unit Xilinx Virtex-II Pro 1802 slices 326 Mbit/s 36.0 MHz
BLAKE-64 Submission document Core functionality Compression function with 1 G function unit Xilinx Virtex 4 1856 slices 381 Mbit/s 42.0 MHz
BLAKE-64 Submission document Core functionality Compression function with 1 G function unit Xilinx Virtex 5 939 slices 533 Mbit/s 59.0 MHz
Grøstl-224/256 Jungk et al. Fully autonomous 64-bit datapath, P & Q permutation in parallel Xilinx Spartan 3 2486 slices 404 Mbit/s 63.2 MHz
Grøstl-224/256 Jungk et al. Fully autonomous 64-bit datapath, P & Q permutation in parallel Xilinx Virtex 2 Pro 2754 slices 512 Mbit/s 81.5 MHz
Keccak Updated specification (v1.2) Using external memory Small core using system memory Altera Stratix III 855 ALUTs 96.8 Mbit/s 366 MHz
Keccak Updated specification (v1.2) Using external memory Small core using system memory Altera Cyclone III 1559 LEs 47.8 Mbit/s 181 MHz
Keccak Updated specification (v1.2) Using external memory Small core using system memory Xilinx Virtex 5 444 slices 70.1 Mbit/s 265 MHz



4 High-Speed Implementations (ASIC)

Hash Function Name Reference Impl. Scope Implementation Details Technology Size Throughput Clock Frequency
AURORA-224/256 Submission document Fully autonomous One round of one MSM and one CPM in parallel with 1 cycle latency (Type-H1), table-lookup S-box 0.13 µm 35.02 kGates 10352 Mbit/s 363.9 MHz
AURORA-384/512 Submission document Fully autonomous One round of one MSM and two CPMs in parallel with 1 cycle latency (Type-H1), table-lookup S-box 0.13 µm 56.75 kGates 9132 Mbit/s 361.2 MHz
BLAKE-32 Submission document Core functionality Compression function with 8 G function units UMC 0.18 µm 58.30 kGates 5295 Mbit/s 114 MHz
BLAKE-32 Submission document Core functionality Compression function with 4 G function units UMC 0.18 µm 41.31 kGates 4153 Mbit/s 170 MHz
BLAKE-64 Submission document Core functionality Compression function with 8 G function units UMC 0.18 µm 132.47 kGates 5910 Mbit/s 87 MHz
BLAKE-64 Submission document Core functionality Compression function with 4 G function units UMC 0.18 µm 82.73 kGates 4810 Mbit/s 136 MHz
CHI-224/256 Submission document Fully autonomous Iterative implementation 0.13 µm 101.46 kGates 4800 Mbit/s 188 MHz
Fugue-256 Submission document Fully autonomous Four SMIX transformations parallel (SUPER4_P) IBM 90 nm 109.85 kGates 13913 Mbit/s 869.5 MHz
Grøstl-224/256 Grøstl website Fully autonomous One shared permutation for P & Q, one pipeline stage UMC 0.18 µm 58.4 kGates 6290 Mbit/s 270.2 MHz
Grøstl-384/512 Submission document Fully autonomous P & Q permutation in parallel UMC 0.18 µm 341 kGates 6225 Mbit/s 85.1 MHz
Keccak Updated specification (v1.2) Fully autonomous Core (round function, state register) & IO buffer ST 0.13 µm 48 kGates 29900 Mbit/s 526 MHz
Keccak Submission document Fully autonomous Core (round function, state register) only ST 0.13 µm 40 kGates 15000 Mbit/s 500 MHz
LANE-224/256 Submission document Fully autonomous Six permutation blocks in parallel (two full AES engines each) 0.13 µm 243.49 kGates 14191 Mbit/s 305 MHz
LANE-384/512 Submission document Fully autonomous Six permutation blocks in parallel (four full AES engines each) 0.13 µm 466.19 kGates 20958 Mbit/s 286 MHz
Lesamnta-256 Submission document Fully autonomous 90 nm 190.1 kGates 6026 Mbit/s 282.5 MHz
Lesamnta-512 Submission document Fully autonomous 90 nm 393 kGates 9992 Mbit/s 234.2 MHz
Luffa-224/256 Supporting document Fully autonomous Three permutation blocks in parallel (64 S-boxes, 4 MixWord blocks each) 0.13 µm 26.85 kGates 12642 Mbit/s 444 MHz
Luffa-384 Supporting document Fully autonomous Four permutation blocks in parallel (64 S-boxes, 4 MixWord blocks each) 0.13 µm 34.99 kGates 12642 Mbit/s 444 MHz
Luffa-512 Supporting document Fully autonomous Five permutation blocks in parallel (64 S-boxes, 4 MixWord blocks each) 0.13 µm 44.16 kGates 12642 Mbit/s 444 MHz
MD6 Submission document Core functionality Compression function with 48 parallel steps GPDSK 90 nm 145 kGates N/A 200 MHz
MD6 Submission document Using external memory Compression function with 16 parallel steps & memory control logic GPDSK 90 nm 105 kGates N/A 200 MHz
MD6-256 Henzen et al. Fully autonomous Sequential mode (L=0), compression function with 16 parallel steps 0.18 µm 69.78 kGates 16320 Mbit/s 552 MHz
MD6-512 Henzen et al. Fully autonomous Sequential mode (L=0), compression function with 16 parallel steps 0.18 µm 69.78 kGates 10103 Mbit/s 552 MHz
Skein-256 Stefan Tillich Fully autonomous 8 Threefish rounds unrolled UMC 0.18 µm 53.87 kGates 1762 Mbit/s 68.8 MHz
Skein-512 Stefan Tillich Fully autonomous 8 Threefish rounds unrolled UMC 0.18 µm 102.35 kGates 2501 Mbit/s 48.8 MHz



5 Low-Area Implementations (ASIC)

Hash Function Name Reference Impl. Scope Implementation Details Technology Size Throughput Clock Frequency
AURORA-224/256 Submission document Fully autonomous One round of one MSM or one CPM with 2 cycles latency (Type-H4) 0.13 µm 11.11 kGates 2179 Mbit/s 306.4 MHz
AURORA-384/512 Submission document Fully autonomous One round of one MSM or one CPM with 2 cycles latency (Type-H4) 0.13 µm 14.61 kGates 1191 Mbit/s 293.1 MHz
BLAKE-32 Submission document Core functionality Compression function with a single G function unit UMC 0.18 µm 10.54 kGates 253 Mbit/s 40 MHz
BLAKE-32 Submission document Core functionality Compression function with a half G function unit UMC 0.18 µm 9.89 kGates 127 Mbit/s 40 MHz
BLAKE-64 Submission document Core functionality Compression function with a single G function unit UMC 0.18 µm 20.61 kGates 181 Mbit/s 20 MHz
BLAKE-64 Submission document Core functionality Compression function with a half G function unit UMC 0.18 µm 19.46 kGates 91 Mbit/s 20 MHz
CHI-224/256 Submission document Fully autonomous Iterative implementation 0.13 µm 62.99 kGates 968 Mbit/s 38 MHz
Fugue-256 Submission document Fully autonomous One SMIX transformation (SUPER1_L) IBM 90 nm 59.22 kGates 2000 Mbit/s 500 MHz
Grøstl-224/256 Grøstl website Fully autonomous 64-bit datapath, P & Q permutation shared UMC 0.18 µm 17 kGates 645 Mbit/s 246.9 MHz
Keccak Updated specification (v1.2) Using external memory Small core using system memory ST 0.13 µm 6.5 kGates 176.4 Mbit/s(*) 666.7 MHz
Keccak Updated specification (v1.2) Using external memory Small core using system memory, clock freq. limited to 200 MHz ST 0.13 µm 5 kGates 52.9 Mbit/s(**) 200 MHz
LANE-224/256 Submission document Fully autonomous One permutation block (one S-box and MixColumns block) 0.13 µm 16.46 kGates 23.3 Mbit/s 100 MHz
Lesamnta-256 Submission document Fully autonomous 90 nm 20.7 kGates 336.9 Mbit/s 169.8 MHz
Lesamnta-512 Submission document Fully autonomous 90 nm 44.3 kGates 571.9 Mbit/s 144.1 MHz
Luffa-224/256 Supporting document Fully autonomous One permutation block (One S-box, one MixWord block) 0.13 µm 10.16 kGates 28.7 Mbit/s 100 MHz

(*) Estimation for 64-bit memory interface: (1024 bits/permutation) * (666.7 * 10^6 cycles/s) / (3870 cycles/permutation) = 176.41 * 10^6 bits/s
(**) Estimation for 64-bit memory interface: (1024 bits/permutation) * (200 * 10^6 cycles/s) / (3870 cycles/permutation) = 52.92 * 10^6 bits/s



6 Call for contributions

Implementers (both submitters and non-submitters): You have results that complement this site? Let us know at sha3zoo-hardware@iaik.tugraz.at