6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-09-07 01:54:50 +00:00
Code Issues Projects Releases Wiki Activity
5d37370a6f
llvm-6502/lib/Transforms
History
Chris Lattner 5d37370a6f When loop rotation happens, it is *very* common for the duplicated condbr 
to be foldable into an uncond branch.  When this happens, we can make a
much simpler CFG for the loop, which is important for nested loop cases
where we want the outer loop to be aggressively optimized.

Handle this case more aggressively.  For example, previously on
phi-duplicate.ll we would get this:


define void @test(i32 %N, double* %G) nounwind ssp {
entry:
  %cmp1 = icmp slt i64 1, 1000
  br i1 %cmp1, label %bb.nph, label %for.end

bb.nph:                                           ; preds = %entry
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.cond
  %j.02 = phi i64 [ 1, %bb.nph ], [ %inc, %for.cond ]
  %arrayidx = getelementptr inbounds double* %G, i64 %j.02
  %tmp3 = load double* %arrayidx
  %sub = sub i64 %j.02, 1
  %arrayidx6 = getelementptr inbounds double* %G, i64 %sub
  %tmp7 = load double* %arrayidx6
  %add = fadd double %tmp3, %tmp7
  %arrayidx10 = getelementptr inbounds double* %G, i64 %j.02
  store double %add, double* %arrayidx10
  %inc = add nsw i64 %j.02, 1
  br label %for.cond

for.cond:                                         ; preds = %for.body
  %cmp = icmp slt i64 %inc, 1000
  br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge

for.cond.for.end_crit_edge:                       ; preds = %for.cond
  br label %for.end

for.end:                                          ; preds = %for.cond.for.end_crit_edge, %entry
  ret void
}

Now we get the much nicer:

define void @test(i32 %N, double* %G) nounwind ssp {
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %j.01 = phi i64 [ 1, %entry ], [ %inc, %for.body ]
  %arrayidx = getelementptr inbounds double* %G, i64 %j.01
  %tmp3 = load double* %arrayidx
  %sub = sub i64 %j.01, 1
  %arrayidx6 = getelementptr inbounds double* %G, i64 %sub
  %tmp7 = load double* %arrayidx6
  %add = fadd double %tmp3, %tmp7
  %arrayidx10 = getelementptr inbounds double* %G, i64 %j.01
  store double %add, double* %arrayidx10
  %inc = add nsw i64 %j.01, 1
  %cmp = icmp slt i64 %inc, 1000
  br i1 %cmp, label %for.body, label %for.end

for.end:                                          ; preds = %for.body
  ret void
}

With all of these recent changes, we are now able to compile:

void foo(char *X) {
 for (int i = 0; i != 100; ++i) 
   for (int j = 0; j != 100; ++j)
     X[j+i*100] = 0;
}

into a single memset of 10000 bytes.  This series of changes
should also be helpful for other nested loop scenarios as well.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123079 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-08 19:59:06 +00:00
..
Hello Since the Hello pass is built as a loadable dynamic library, don't try to convert it to new-style registration yet. 2010-10-07 00:31:16 +00:00
InstCombine Fix a bug in r123034 (trying to sext/zext non-integers) and clean up a little. 2011-01-08 10:51:36 +00:00
Instrumentation Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
IPO Improve the accuracy of the inlining heuristic looking for the 2011-01-04 19:01:54 +00:00
Scalar When loop rotation happens, it is *very* common for the duplicated condbr 2011-01-08 19:59:06 +00:00
Utils various code cleanups, enhance MergeBlockIntoPredecessor to preserve 2011-01-08 19:08:40 +00:00
Makefile Revert r100896 and around - this breaks the only mingw32 buildbot we have. 2010-04-15 19:51:42 +00:00