llvm.org GIT mirror llvm / e6aaf31
[llvm-mca][docs] Define IPC where it is first mentioned. NFC. Expand the abbreviation where it is first used, and use IPC elsewhere. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337739 91177308-0d34-0410-b5e6-96231b3b80d8 Matt Davis 1 year, 2 months ago
1 changed file(s) with 7 addition(s) and 7 deletion(s). Raw diff Collapse all Expand all
2020 when run on the target, but also help with diagnosing potential performance
2121 issues.
2222
23 Given an assembly code sequence, llvm-mca estimates the IPC, as well as
24 hardware resource pressure. The analysis and reporting style were inspired by
25 the IACA tool from Intel.
23 Given an assembly code sequence, llvm-mca estimates the Instructions Per Cycle
24 (IPC), as well as hardware resource pressure. The analysis and reporting style
25 were inspired by the IACA tool from Intel.
2626
2727 :program:`llvm-mca` allows the usage of special code comments to mark regions of
2828 the assembly code to be analyzed. A comment starting with substring
286286 The report is structured in three main sections. The first section collects a
287287 few performance numbers; the goal of this section is to give a very quick
288288 overview of the performance throughput. In this example, the two important
289 performance indicators are the predicted total number of cycles, and the
290 Instructions Per Cycle (IPC). IPC is probably the most important throughput
291 indicator. A big delta between the Dispatch Width and the computed IPC is an
292 indicator of potential performance issues.
289 performance indicators are the predicted total number of cycles, and the IPC.
290 IPC is probably the most important throughput indicator. A big delta between
291 the Dispatch Width and the computed IPC is an indicator of potential
292 performance issues.
293293
294294 The second section of the report shows the latency and reciprocal
295295 throughput of every instruction in the sequence. That section also reports