Changes in / [d269894:d96becd]
- Files:
-
- 1 added
- 1 edited
Legend:
- Unmodified
- Added
- Removed
-
doc/theses/mubeen_zulfiqar_MMath/benchmarks.tex
rd269894 rd96becd 133 133 The aim of micro benchmark suite is to create a set of programs that can evaluate a memory allocator based on the performance matrices described in (FIX ME: local cite). These programs can be taken as a standard to benchmark an allocator's basic goals. These programs give details of an allocator's memory overhead and speed under a certain allocation pattern. The speed of the allocator is benchmarked in different ways. Similarly, false sharing happening in an allocator is also measured in multiple ways. These benchmarks evalute the allocator under a certain allocation pattern which is configurable and can be changed using a few knobs to benchmark observe an allocator's performance under a desired allocation pattern. 134 134 135 TO DO before writing furthur: Finalize figures 135 Micro Benchmark Suite benchmarks an allocator's performance by allocating dynamic objects and, then, measuring specifc matrices. The benchmark suite evaluates an allocator with a certain allocation pattern. Bnechmarks have different knobs that can be used to change allocation pattern and evaluate an allocator under desired conditions. These can be set by giving commandline arguments to the benchmark on execution. 136 137 Following is the list of avalable knobs. 138 139 *** FIX ME: Add knobs items after finalize 136 140 137 141 /subsection Memory Benchmark 142 Memory benchmark measures memory overhead of an allocator. It allocates a number of dynamic objects. Then, by reading /self/proc/maps, gets the total memory that the allocator has reuested from the OS. Finally, it calculates the memory head by taking the difference between the memory the allocator has requested from the OS and the memory that program has allocated. 143 *** FIX ME: Insert a figure of above benchmark with description 144 145 /subsubsection Relevant Knobs 146 *** FIX ME: Insert Relevant Knobs 147 138 148 /subsection Speed Benchmark 149 Speed benchmark calculates the runtime speed of an allocator's functions (FIX ME: cite allocator routines). It does by measuring the runtime of allocator routines in two different ways. 150 139 151 /subsubsection Speed Time 152 The time method does a certain amount of work by calling each routine of the allocator (FIX ME: cite allocator routines) a specific time. It calculates the total time it took to perform this workload. Then, it divides the time it took by the workload and calculates the average time taken by the allocator's routine. 153 *** FIX ME: Insert a figure of above benchmark with description 154 155 /subsubsubsection Relevant Knobs 156 *** FIX ME: Insert Relevant Knobs 157 140 158 /subsubsection Speed Workload 159 The worload method uses the opposite approach. It calls the allocator's routines for a specific amount of time and measures how much work was done during that time. Then, similar to the time method, it divides the time by the workload done during that time and calculates the average time taken by the allocator's routine. 160 *** FIX ME: Insert a figure of above benchmark with description 161 162 /subsubsubsection Relevant Knobs 163 *** FIX ME: Insert Relevant Knobs 141 164 142 165 /subsection Cache Scratch 166 Cache Scratch benchmark measures program induced allocator preserved passive false sharing (FIX ME CITE) in an allocator. It does so in two ways. 167 143 168 /subsubsection Cache Scratch Time 169 Cache Scratch Time allocates dynamic objects. Then, it benchmarks program induced allocator preserved passive false sharing (FIX ME CITE) in an allocator by measuring the time it takes to read/write these objects. 170 *** FIX ME: Insert a figure of above benchmark with description 171 172 /subsubsubsection Relevant Knobs 173 *** FIX ME: Insert Relevant Knobs 174 144 175 /subsubsection Cache Scratch Layout 176 Cache Scratch Layout also allocates dynamic objects. Then, it benchmarks program induced allocator preserved passive false sharing (FIX ME CITE) by using heap addresses returned by the allocator. It calculates how many objects were allocated to different threads on the same cache line. 177 *** FIX ME: Insert a figure of above benchmark with description 178 179 /subsubsubsection Relevant Knobs 180 *** FIX ME: Insert Relevant Knobs 145 181 146 182 /subsection Cache Thrash 183 Cache Thrash benchmark measures allocator induced passive false sharing (FIX ME CITE) in an allocator. It also does so in two ways. 184 147 185 /subsubsection Cache Thrash Time 186 Cache Thrash Time allocates dynamic objects. Then, it benchmarks allocator induced false sharing (FIX ME CITE) in an allocator by measuring the time it takes to read/write these objects. 187 *** FIX ME: Insert a figure of above benchmark with description 188 189 /subsubsubsection Relevant Knobs 190 *** FIX ME: Insert Relevant Knobs 191 148 192 /subsubsection Cache Thrash Layout 193 Cache Thrash Layout also allocates dynamic objects. Then, it benchmarks allocator induced false sharing (FIX ME CITE) by using heap addresses returned by the allocator. It calculates how many objects were allocated to different threads on the same cache line. 194 *** FIX ME: Insert a figure of above benchmark with description 195 196 /subsubsubsection Relevant Knobs 197 *** FIX ME: Insert Relevant Knobs 198 199 /section Results 200 *** FIX ME: add configuration details of memory allocators 201 202 /subsection Memory Benchmark 203 204 /subsubsection Relevant Knobs 205 206 /subsection Speed Benchmark 207 208 /subsubsection Speed Time 209 210 /subsubsubsection Relevant Knobs 211 212 /subsubsection Speed Workload 213 214 /subsubsubsection Relevant Knobs 215 216 /subsection Cache Scratch 217 218 /subsubsection Cache Scratch Time 219 220 /subsubsubsection Relevant Knobs 221 222 /subsubsection Cache Scratch Layout 223 224 /subsubsubsection Relevant Knobs 225 226 /subsection Cache Thrash 227 228 /subsubsection Cache Thrash Time 229 230 /subsubsubsection Relevant Knobs 231 232 /subsubsection Cache Thrash Layout 233 234 /subsubsubsection Relevant Knobs
Note: See TracChangeset
for help on using the changeset viewer.