perf(levm): try improve mulmod and addmod

[JereSalo]

Motivation

Description

• Try see if there's any improvement if we stop using U512 for these operations. We executed with a zkVM and we saw that it can be a bottleneck. This is experimental

WARNING: This is VERY experimental, it probably won't be merged so don't bother to review this for now haha

[github-actions]

Lines of code report

Total lines added: 9
Total lines removed: 0
Total lines changed: 9

Detailed view

+---------------------------------------------------------+-------+------+
| File                                                    | Lines | Diff |
+---------------------------------------------------------+-------+------+
| ethrex/crates/vm/levm/src/opcode_handlers/arithmetic.rs | 221   | +9   |
+---------------------------------------------------------+-------+------+

[github-actions]

Benchmark Results Comparison

No significant difference was registered for any benchmark run.

Detailed Results

Benchmark Results: BubbleSort

Command	Mean [s]	Min [s]	Max [s]	Relative
main_revm_BubbleSort	2.982 ± 0.067	2.946	3.170	1.00
main_levm_BubbleSort	3.201 ± 0.009	3.188	3.217	1.07 ± 0.02
pr_revm_BubbleSort	3.043 ± 0.018	3.015	3.068	1.02 ± 0.02
pr_levm_BubbleSort	3.243 ± 0.051	3.217	3.386	1.09 ± 0.03

Benchmark Results: ERC20Approval

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_ERC20Approval	968.4 ± 6.0	957.2	977.4	1.00
main_levm_ERC20Approval	1176.2 ± 18.8	1155.3	1213.2	1.21 ± 0.02
pr_revm_ERC20Approval	1002.8 ± 8.4	992.8	1022.3	1.04 ± 0.01
pr_levm_ERC20Approval	1161.1 ± 18.2	1149.5	1207.4	1.20 ± 0.02

Benchmark Results: ERC20Mint

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_ERC20Mint	131.8 ± 1.1	130.9	135.0	1.00
main_levm_ERC20Mint	170.5 ± 4.1	166.3	178.4	1.29 ± 0.03
pr_revm_ERC20Mint	136.9 ± 1.8	135.2	141.1	1.04 ± 0.02
pr_levm_ERC20Mint	170.0 ± 2.0	167.9	174.7	1.29 ± 0.02

Benchmark Results: ERC20Transfer

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_ERC20Transfer	231.7 ± 2.6	229.3	236.1	1.00
main_levm_ERC20Transfer	287.9 ± 2.8	283.7	294.5	1.24 ± 0.02
pr_revm_ERC20Transfer	243.2 ± 11.0	235.8	271.1	1.05 ± 0.05
pr_levm_ERC20Transfer	287.4 ± 1.7	285.1	290.1	1.24 ± 0.02

Benchmark Results: Factorial

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_Factorial	225.5 ± 3.2	223.1	231.5	1.00
main_levm_Factorial	275.6 ± 11.6	269.8	308.1	1.22 ± 0.05
pr_revm_Factorial	226.9 ± 8.5	221.4	248.8	1.01 ± 0.04
pr_levm_Factorial	274.8 ± 12.3	269.8	309.7	1.22 ± 0.06

Benchmark Results: FactorialRecursive

Command	Mean [s]	Min [s]	Max [s]	Relative
main_revm_FactorialRecursive	1.609 ± 0.030	1.566	1.652	1.00
main_levm_FactorialRecursive	8.629 ± 0.108	8.488	8.879	5.36 ± 0.12
pr_revm_FactorialRecursive	1.624 ± 0.028	1.584	1.684	1.01 ± 0.03
pr_levm_FactorialRecursive	8.618 ± 0.064	8.531	8.709	5.35 ± 0.11

Benchmark Results: Fibonacci

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_Fibonacci	203.9 ± 0.8	202.6	205.2	1.00 ± 0.00
main_levm_Fibonacci	268.7 ± 13.5	257.0	304.4	1.32 ± 0.07
pr_revm_Fibonacci	203.2 ± 0.5	202.5	203.9	1.00
pr_levm_Fibonacci	260.4 ± 3.0	257.3	267.5	1.28 ± 0.02

Benchmark Results: FibonacciRecursive

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_FibonacciRecursive	829.6 ± 8.9	817.2	841.6	1.10 ± 0.02
main_levm_FibonacciRecursive	754.8 ± 8.0	748.1	773.0	1.00
pr_revm_FibonacciRecursive	834.2 ± 8.1	826.2	850.2	1.11 ± 0.02
pr_levm_FibonacciRecursive	768.9 ± 26.7	731.4	832.7	1.02 ± 0.04

Benchmark Results: ManyHashes

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_ManyHashes	8.2 ± 0.0	8.2	8.3	1.00
main_levm_ManyHashes	9.6 ± 0.1	9.5	9.8	1.17 ± 0.01
pr_revm_ManyHashes	8.3 ± 0.1	8.2	8.6	1.01 ± 0.02
pr_levm_ManyHashes	9.6 ± 0.1	9.5	9.8	1.17 ± 0.01

Benchmark Results: MstoreBench

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_MstoreBench	262.3 ± 1.2	261.0	265.5	1.09 ± 0.03
main_levm_MstoreBench	241.8 ± 6.0	235.6	256.6	1.01 ± 0.04
pr_revm_MstoreBench	264.8 ± 3.9	260.9	272.1	1.10 ± 0.03
pr_levm_MstoreBench	240.0 ± 6.0	236.1	254.3	1.00

Benchmark Results: Push

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_Push	295.6 ± 3.9	292.2	303.6	1.01 ± 0.01
main_levm_Push	318.3 ± 1.6	317.2	322.7	1.08 ± 0.01
pr_revm_Push	294.1 ± 2.0	292.0	298.7	1.00
pr_levm_Push	314.8 ± 1.6	313.3	318.1	1.07 ± 0.01

Benchmark Results: SstoreBench_no_opt

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
main_revm_SstoreBench_no_opt	167.0 ± 6.4	161.0	176.7	1.89 ± 0.08
main_levm_SstoreBench_no_opt	89.8 ± 3.9	86.7	97.6	1.02 ± 0.05
pr_revm_SstoreBench_no_opt	165.5 ± 4.9	161.3	175.4	1.87 ± 0.06
pr_levm_SstoreBench_no_opt	88.4 ± 1.5	86.7	92.4	1.00