diff options
| author | Chris Lattner <sabre@nondot.org> | 2011-01-02 07:58:36 +0000 |
|---|---|---|
| committer | Chris Lattner <sabre@nondot.org> | 2011-01-02 07:58:36 +0000 |
| commit | cf078f2b20899a3a19fb2044cc08dff409f13276 (patch) | |
| tree | 10d9344a15babd779c7bf7ceb7385c7f78d6e2e6 /lib/Target/README.txt | |
| parent | c9e152b778715afc5cdfdb98cb0e98757ed827d8 (diff) | |
Allow loop-idiom to run on multiple BB loops, but still only scan the loop
header for now for memset/memcpy opportunities. It turns out that loop-rotate
is successfully rotating loops, but *DOESN'T MERGE THE BLOCKS*, turning "for
loops" into 2 basic block loops that loop-idiom was ignoring.
With this fix, we form many *many* more memcpy and memsets than before, including
on the "history" loops in the viterbi benchmark, which look like this:
for (j=0; j<MAX_history; ++j) {
history_new[i][j+1] = history[2*i][j];
}
Transforming these loops into memcpy's speeds up the viterbi benchmark from
11.98s to 3.55s on my machine. Woo.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122685 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Target/README.txt')
| -rw-r--r-- | lib/Target/README.txt | 8 |
1 files changed, 0 insertions, 8 deletions
diff --git a/lib/Target/README.txt b/lib/Target/README.txt index 4e374e59d6d..f047d087cbf 100644 --- a/lib/Target/README.txt +++ b/lib/Target/README.txt @@ -414,14 +414,6 @@ this construct. //===---------------------------------------------------------------------===// -[LOOP RECOGNITION] - -viterbi speeds up *significantly* if the various "history" related copy loops -are turned into memcpy calls at the source level. We need a "loops to memcpy" -pass. - -//===---------------------------------------------------------------------===// - [LOOP OPTIMIZATION] SingleSource/Benchmarks/Misc/dt.c shows several interesting optimization |