perf(l1,l2): optimize mulmod for zkVMs

[JereSalo]

Motivation

• Try to see if we can optimize mulmod becuase we've seen mainnet blocks in which it's an expensive operation

Description

• Optimize mulmod for SP1. This is in draft and has experimental changes but using a SP1 patched function (not in a pretty manner) yielded 57x in Mulmod in Block 23890684, which is great.

Closes #issue_number

[github-actions]

Lines of code report

Total lines added: 63
Total lines removed: 0
Total lines changed: 63

Detailed view

+---------------------------------------------------------+-------+------+
| File                                                    | Lines | Diff |
+---------------------------------------------------------+-------+------+
| ethrex/crates/vm/levm/src/opcode_handlers/arithmetic.rs | 275   | +63  |
+---------------------------------------------------------+-------+------+

[github-actions]

Benchmark Results Comparison

Benchmark Results: Fibonacci

Command	Mean [s]	Min [s]	Max [s]	Relative
main_revm_Fibonacci	247.3 ± 125.1	206.2	603.2	1.22 ± 0.62
main_levm_Fibonacci	251.9 ± 3.3	247.7	259.2	1.24 ± 0.02
pr_revm_Fibonacci	202.3 ± 1.5	200.9	205.8	1.00

Detailed Results

Benchmark Results: BubbleSort

Command	Mean [s]	Min [s]	Max [s]	Relative
main_revm_BubbleSort	3.017 ± 0.027	2.994	3.085	1.00
main_levm_BubbleSort	3.160 ± 0.027	3.128	3.225	1.05 ± 0.01
pr_revm_BubbleSort	3.023 ± 0.046	2.978	3.110	1.00 ± 0.02
pr_levm_BubbleSort	3.133 ± 0.021	3.109	3.162	1.04 ± 0.01

Benchmark Results: ERC20Approval

Command	Mean [s]	Min [s]	Max [s]	Relative
main_revm_ERC20Approval	1.017 ± 0.010	1.008	1.035	1.01 ± 0.01
main_levm_ERC20Approval	1.093 ± 0.017	1.078	1.135	1.09 ± 0.02
pr_revm_ERC20Approval	1.002 ± 0.006	0.994	1.015	1.00
pr_levm_ERC20Approval	1.084 ± 0.016	1.069	1.121	1.08 ± 0.02

Benchmark Results: ERC20Mint

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_ERC20Mint	135.7 ± 1.6	133.9	138.0	1.00
main_levm_ERC20Mint	160.6 ± 1.4	158.7	162.6	1.18 ± 0.02
pr_revm_ERC20Mint	135.9 ± 2.3	134.7	142.3	1.00 ± 0.02
pr_levm_ERC20Mint	159.3 ± 1.0	157.9	161.2	1.17 ± 0.02

Benchmark Results: ERC20Transfer

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_ERC20Transfer	244.3 ± 4.1	240.4	253.7	1.04 ± 0.02
main_levm_ERC20Transfer	280.1 ± 2.6	275.5	283.2	1.19 ± 0.01
pr_revm_ERC20Transfer	234.8 ± 1.8	231.2	238.5	1.00
pr_levm_ERC20Transfer	280.2 ± 4.3	274.9	289.4	1.19 ± 0.02

Benchmark Results: Factorial

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_Factorial	223.1 ± 1.0	221.4	225.4	1.00 ± 0.01
main_levm_Factorial	272.8 ± 2.6	269.3	278.5	1.23 ± 0.01
pr_revm_Factorial	222.7 ± 0.9	221.5	224.5	1.00
pr_levm_Factorial	273.5 ± 2.1	271.2	276.8	1.23 ± 0.01

Benchmark Results: FactorialRecursive

Command	Mean [s]	Min [s]	Max [s]	Relative
main_revm_FactorialRecursive	1.658 ± 0.041	1.596	1.713	1.00
main_levm_FactorialRecursive	8.578 ± 0.063	8.483	8.668	5.17 ± 0.13
pr_revm_FactorialRecursive	1.659 ± 0.031	1.609	1.700	1.00 ± 0.03
pr_levm_FactorialRecursive	8.483 ± 0.079	8.368	8.628	5.12 ± 0.14

Benchmark Results: Fibonacci

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_Fibonacci	247.3 ± 125.1	206.2	603.2	1.22 ± 0.62
main_levm_Fibonacci	251.9 ± 3.3	247.7	259.2	1.24 ± 0.02
pr_revm_Fibonacci	202.3 ± 1.5	200.9	205.8	1.00
pr_levm_Fibonacci	260.9 ± 6.4	249.0	273.7	1.29 ± 0.03

Benchmark Results: FibonacciRecursive

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_FibonacciRecursive	864.6 ± 9.4	855.0	883.7	1.19 ± 0.02
main_levm_FibonacciRecursive	725.8 ± 5.1	719.3	736.2	1.00
pr_revm_FibonacciRecursive	850.8 ± 7.9	842.1	866.7	1.17 ± 0.01
pr_levm_FibonacciRecursive	727.9 ± 9.6	719.2	754.0	1.00 ± 0.02

Benchmark Results: ManyHashes

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_ManyHashes	8.8 ± 0.1	8.7	9.0	1.00 ± 0.01
main_levm_ManyHashes	9.2 ± 0.1	9.0	9.5	1.05 ± 0.02
pr_revm_ManyHashes	8.8 ± 0.1	8.7	8.9	1.00
pr_levm_ManyHashes	9.1 ± 0.1	9.1	9.3	1.04 ± 0.01

Benchmark Results: MstoreBench

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_MstoreBench	252.1 ± 1.7	250.4	255.1	1.08 ± 0.01
main_levm_MstoreBench	237.4 ± 5.4	233.2	251.6	1.01 ± 0.02
pr_revm_MstoreBench	255.3 ± 7.4	250.3	272.1	1.09 ± 0.03
pr_levm_MstoreBench	234.2 ± 1.8	231.8	238.3	1.00

Benchmark Results: Push

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_Push	284.1 ± 0.5	283.3	285.0	1.00
main_levm_Push	302.8 ± 1.5	301.1	305.6	1.07 ± 0.01
pr_revm_Push	286.0 ± 1.5	284.5	288.8	1.01 ± 0.01
pr_levm_Push	295.5 ± 13.5	290.0	333.7	1.04 ± 0.05

Benchmark Results: SstoreBench_no_opt

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_SstoreBench_no_opt	166.0 ± 2.4	161.0	168.0	1.84 ± 0.06
main_levm_SstoreBench_no_opt	91.0 ± 3.0	88.1	98.8	1.01 ± 0.04
pr_revm_SstoreBench_no_opt	167.4 ± 6.0	161.2	182.5	1.85 ± 0.08
pr_levm_SstoreBench_no_opt	90.3 ± 2.4	88.0	96.5	1.00