SteveBronder

#include <benchmark/benchmark.h>
#include <stan/math/mix.hpp>
#include <Eigen/Dense>
#include <utility>

template <typename T1, typename T2>
__attribute__ ((noinline, no_icf))  auto add_inner_const(const T1& A, const T2& B) {
  asm ("");
  return (A + B).eval();
}

SteveBronder

SteveBronder

// Code generated by %%NAME%% %%VERSION%%
#include <stan/model/model_header.hpp>
namespace sparse_model_namespace {

template <typename T, typename S>
std::vector<T> resize_to_match__(std::vector<T> &dst,
                                 const std::vector<S> &src) {
  dst.resize(src.size());
  return dst;

SteveBronder

library(cmdstanr)
library(data.table)
library(ggplot2)
library(ggridges)
library(rstan)
library(posterior)
set_cmdstan_path("~/your_cmdstan_path")
# statcomp/benchmarks is working directory
gp_lst = rstan::read_rdump("./gp_pois_regr/gp_pois_regr.data.R")

SteveBronder

---
high_dim_gauss
---
[turing]
Benchmark results
  Compilation time: 3.0011221113333337 (approximately)
  Running time: 2.4342513616666666 +/- 0.14597526149472717 (3 runs)
  Forward time: 0.000411603
  Gradient time (forwarddiff): 0.526029922
  Gradient time (reversediff): 0.00010086

SteveBronder

library(data.table)
library(ggplot2)
mat_mul_dt = fread("./mat_mul_bench.csv")
mat_mul_dt[1:25, bench := "old"]
mat_mul_dt[26:50, bench := "new"]
mm_strs = t(mat_mul_dt[, strsplit(Benchmark, "/")])
mat_mul_dt[, benchmark := mm_strs[, 1]]
mat_mul_dt[, rows := as.numeric(mm_strs[, 2])]
mat_mul_dt[, cols := as.numeric(mm_strs[, 3])]

SteveBronder

struct Arg {};

// Base class for RVO checking
struct S {
    S() { puts("\t\tDefault Constructor");}
    S(Arg) { puts("\t\tValue Constructor");}
    explicit S(int) {puts("\t\tExplicit Value Constructor (1)");}
    explicit S(int, int) { puts("\t\tExplicit Value Constructor (2)");}
    ~S() { puts("\t\tDestruct");}
    S(const S&) { puts("\t\tCopy construct");}

SteveBronder

library(gh)
library(data.table)

# Cycles through the PR pages grabbing useful info
all_prs = list()[30 * 12]
stan_math_prs = list()[30 * 12]  
for (i in 1:12) {
  stan_math_prs[[i]] = gh("GET https://api.github.com/repos/stan-dev/math/pulls?state=closed", type = "public", page = i)
}
for (i in 1:12) {

SteveBronder

SteveBronder

/**
 * \ingroup opencl
 * \defgroup opencl_kernel_generator OpenCL Kernel Generator
 *
 * The OpenCL kernel generator is used to combine multiple matrix operations into a
 * single OpenCL kernel. This is much simpler than writing multi-operation kernels by
 * hand.
 *
 * Because global GPU memory loads and stores are relativly slow compared to
 * calculations in a kernel, using one kernel for multiple operations is faster than using one kernel