Add SIMD RK methods to NonStiffODE benchmarks

- Add OrdinaryDiffEqSIMDRK package dependency (v1.4.0)
- Add MER5v2, MER6v2, and RK6v4 methods to FitzhughNagumo benchmark
- Add MER5v2, MER6v2, and RK6v4 methods to LotkaVolterra benchmark
- Add MER5v2, MER6v2, and RK6v4 methods to RigidBody benchmark
- Add MER5v2, MER6v2, and RK6v4 methods to linear benchmark
- These SIMD methods provide improved performance for static array problems

Author: ChrisRackauckas

benchmarks/NonStiffODE/FitzhughNagumo_wpd.jmd

@@ -10,7 +10,7 @@ The purpose of this is to see how the errors scale on a standard nonlinear probl
 ```julia
 using OrdinaryDiffEq, ParameterizedFunctions, ODEInterface,
       ODEInterfaceDiffEq, LSODA, Sundials, DiffEqDevTools,
-      StaticArrays
+      StaticArrays, OrdinaryDiffEqSIMDRK
 using Plots;
 gr()
 
@@ -46,7 +46,10 @@ setups = [Dict(:alg=>DP5())
           Dict(:alg=>Tsit5())
           Dict(:alg=>Vern6())
           Dict(:alg=>Tsit5(), :prob_choice => 2)
-          Dict(:alg=>Vern6(), :prob_choice => 2)]
+          Dict(:alg=>Vern6(), :prob_choice => 2)
+          Dict(:alg=>MER5v2(), :prob_choice => 2)
+          Dict(:alg=>MER6v2(), :prob_choice => 2)
+          Dict(:alg=>RK6v4(), :prob_choice => 2)]
 wp = WorkPrecisionSet(probs, abstols, reltols, setups; appxsol = test_sol,
     save_everystep = false, numruns = 100, maxiters = 1000)
 plot(wp)

benchmarks/NonStiffODE/LotkaVolterra_wpd.jmd

@@ -9,7 +9,7 @@ The purpose of this problem is to test the performance on easy problems. Since i
 
 ```julia
 using OrdinaryDiffEq, ParameterizedFunctions, ODEInterfaceDiffEq, LSODA,
-      Sundials, DiffEqDevTools, StaticArrays
+      Sundials, DiffEqDevTools, StaticArrays, OrdinaryDiffEqSIMDRK
 
 f = @ode_def LotkaVolterra begin
     dx = a*x - b*x*y
@@ -43,7 +43,10 @@ setups = [Dict(:alg=>DP5())
           Dict(:alg=>Tsit5())
           Dict(:alg=>Vern6())
           Dict(:alg=>Tsit5(), :prob_choice => 2)
-          Dict(:alg=>Vern6(), :prob_choice => 2)]
+          Dict(:alg=>Vern6(), :prob_choice => 2)
+          Dict(:alg=>MER5v2(), :prob_choice => 2)
+          Dict(:alg=>MER6v2(), :prob_choice => 2)
+          Dict(:alg=>RK6v4(), :prob_choice => 2)]
 wp = WorkPrecisionSet(probs, abstols, reltols, setups; appxsol = test_sol,
     save_everystep = false, maxiters = 10000, numruns = 100)
 plot(wp)