Improve parallelism of ICF.

This is the only place we use threads for ICF. The intention of this code
was to split an input vector into 256 shards and process them in parallel.
What the code was actually doing was to split an input into 257 shards,
process the first 256 shards in parallel, and the remaining one in serial.

That means this code takes ceil(256/n)+1 instead of ceil(256/n) where n
is the number of available CPU cores. The former converges to 2 while
the latter converges to 1.

This patches fixes the above issue.

llvm-svn: 303797

2 files changed, 4 insertions, 4 deletions

diff --git a/lld/COFF/ICF.cpp b/lld/COFF/ICF.cpp
index 3b7cc424f0a..aa080958fe1 100644
--- a/lld/COFF/ICF.cpp
+++ b/lld/COFF/ICF.cpp
@@ -193,9 +193,9 @@ void ICF::forEachClass(std::function<void(size_t, size_t)> Fn) {
   size_t NumShards = 256;
   size_t Step = Chunks.size() / NumShards;
   for_each_n(parallel::par, size_t(0), NumShards, [&](size_t I) {
-    forEachClassRange(I * Step, (I + 1) * Step, Fn);
+    size_t End = (I == NumShards - 1) ? Chunks.size() : (I + 1) * Step;
+    forEachClassRange(I * Step, End, Fn);
   });
-  forEachClassRange(Step * NumShards, Chunks.size(), Fn);
 }
 
 // Merge identical COMDAT sections.
diff --git a/lld/ELF/ICF.cpp b/lld/ELF/ICF.cpp
index 3722d4e3ed2..419ae681632 100644
--- a/lld/ELF/ICF.cpp
+++ b/lld/ELF/ICF.cpp
@@ -326,9 +326,9 @@ void ICF<ELFT>::forEachClass(std::function<void(size_t, size_t)> Fn) {
   size_t NumShards = 256;
   size_t Step = Sections.size() / NumShards;
   parallelForEachN(0, NumShards, [&](size_t I) {
-    forEachClassRange(I * Step, (I + 1) * Step, Fn);
+    size_t End = (I == NumShards - 1) ? Sections.size() : (I + 1) * Step;
+    forEachClassRange(I * Step, End, Fn);
   });
-  forEachClassRange(Step * NumShards, Sections.size(), Fn);
   ++Cnt;
 }