OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 6
Code Issues Packages Projects Releases Wiki Activity
llvm-project/llvm/test/tools/llvm-profgen/Inputs
History
wlei b1a45c62f0 [llvm-profgen] Ignore branch count against outline function 
For some transformations like hot-cold split or coro split, it can outline its part of function ranges. Since sample loader is the early stage of backend and no split happens at that time, compiler can't recognize those function, so in llvm-profgen we should attribute the sample to the original function. This is already done for the body range samples since we use the symbols from dwarf which is created before the split.

But for branch samples, the call from master function to its outlined function is actually not a call to the original function, we shouldn't add head/callsie samples for it. So instead of dwarf symbol, we use the symbols from symbol table and ignore those functions with special suffixes(like `.cold` ,`.resume`) for accumulating the callsite/head samples.

Reviewed By: hoy, wenlei

Differential Revision: https://reviews.llvm.org/D110864
 		2021-10-07 14:03:34 -07:00
..
coroutine.perfbin [llvm-profgen] Ignore branch count against outline function 2021-10-07 14:03:34 -07:00
coroutine.perfscript [llvm-profgen] Ignore branch count against outline function 2021-10-07 14:03:34 -07:00
cs-interrupt.perfscript [CSSPGO][llvm-profgen] Ignore LBR records after interrupt transition 2021-06-18 12:13:53 -07:00
cs-invalid-ret-addr.perfscript [CSSPGO][llvm-profgen] Truncate stack samples with invalid return address. 2021-09-14 21:56:22 -07:00
cs-preinline-cost.perfbin [CSSPGO] Track and use context-sensitive post-optimization function size to drive global pre-inliner in llvm-profgen 2021-08-18 22:50:57 -07:00
cs-preinline-cost.perfscript [CSSPGO] Track and use context-sensitive post-optimization function size to drive global pre-inliner in llvm-profgen 2021-08-18 22:50:57 -07:00
func-split.perfbin [llvm-profgen] Ignore branch count against outline function 2021-10-07 14:03:34 -07:00
func-split.perfscript [llvm-profgen] Ignore branch count against outline function 2021-10-07 14:03:34 -07:00
inline-cs-noprobe.perfbin
…
inline-cs-noprobe.perfscript
…
inline-cs-pseudoprobe.perfbin [CSSPGO] Undoing the concept of dangling pseudo probe 2021-06-18 15:14:11 -07:00
inline-cs-pseudoprobe.perfscript
…
inline-noprobe.perfbin [AutoFDO][llvm-profgen] Profile generation for LBR(non-CS) sample 2021-09-24 13:55:34 -07:00
inline-noprobe.perfscript [AutoFDO][llvm-profgen] Profile generation for LBR(non-CS) sample 2021-09-24 13:55:34 -07:00
inline-noprobe2.perfbin [AutoFDO][llvm-profgen] Profile generation for LBR(non-CS) sample 2021-09-24 13:55:34 -07:00
inline-noprobe2.perfscript [AutoFDO][llvm-profgen] Profile generation for LBR(non-CS) sample 2021-09-24 13:55:34 -07:00
multi-load-segs.perfbin [CSSPGO][llvm-profgen] Allow multiple executable load segments. 2021-07-13 18:22:24 -07:00
multi-load-segs.perfscript [CSSPGO][llvm-profgen] Allow multiple executable load segments. 2021-07-13 18:22:24 -07:00
noinline-cs-noprobe.aggperfscript [llvm-profgen][CSSPGO] Support count based aggregated type of hybrid perf script 2021-08-03 17:56:35 -07:00
noinline-cs-noprobe.perfbin
…
noinline-cs-noprobe.perfscript
…
noinline-cs-pseudoprobe.aggperfscript [llvm-profgen][CSSPGO] Support count based aggregated type of hybrid perf script 2021-08-03 17:56:35 -07:00
noinline-cs-pseudoprobe.perfbin [CSSPGO] Undoing the concept of dangling pseudo probe 2021-06-18 15:14:11 -07:00
noinline-cs-pseudoprobe.perfscript
…
noprobe.aggperfscript [llvm-profgen] Support LBR only perf script 2021-08-31 13:28:17 -07:00
noprobe.mmap.perfscript [llvm-profgen] Support LBR only perf script 2021-08-31 13:28:17 -07:00
noprobe.perfbin [llvm-profgen] Support LBR only perf script 2021-08-31 13:28:17 -07:00
noprobe.perfscript [llvm-profgen] Ignore invalid perf line in LBR record 2021-09-24 13:44:57 -07:00
recursion-compression-noprobe.perfbin
…
recursion-compression-noprobe.perfscript
…
recursion-compression-pseudoprobe-nommap.perfscript [llvm-profgen] Support perf script without parsing MMap events 2021-08-03 10:01:07 -07:00
recursion-compression-pseudoprobe.perfbin [CSSPGO] Undoing the concept of dangling pseudo probe 2021-06-18 15:14:11 -07:00
recursion-compression-pseudoprobe.perfscript
…
symbolize.ll [CSSPGO][llvm-profgen] Allow multiple executable load segments. 2021-07-13 18:22:24 -07:00
symbolize.perfbin [CSSPGO][llvm-profgen] Allow multiple executable load segments. 2021-07-13 18:22:24 -07:00
truncated-pseudoprobe.ll [CSSPGO] Undoing the concept of dangling pseudo probe 2021-06-18 15:14:11 -07:00
truncated-pseudoprobe.perfbin [CSSPGO] Undoing the concept of dangling pseudo probe 2021-06-18 15:14:11 -07:00
truncated-pseudoprobe.perfscript [CSSPGO] Undoing the concept of dangling pseudo probe 2021-06-18 15:14:11 -07:00
unique-linkage-name-dwarf.perfbin
…
unique-linkage-name-dwarf.perfscript
…
unique-linkage-name-probe.perfbin [CSSPGO] Undoing the concept of dangling pseudo probe 2021-06-18 15:14:11 -07:00
unique-linkage-name-probe.perfscript
…