[CGP] Split some critical edges coming out of indirect branches

Splitting critical edges when one of the source edges is an indirectbr
is hard in general (because it requires changing the memory the indirectbr
reads). But if a block only has a single indirectbr predecessor (which is
the common case), we can simulate splitting that edge by splitting
the destination block, and retargeting the *direct* branches.

This is motivated by the use of computed gotos in python 2.7: PyEval_EvalFrame()
ends up using an indirect branch with ~100 successors, and passing a constant to
each of those. Since MachineSink can't break indirect critical edges on demand
(and doing this in MIR doesn't look feasible), this causes us to emit about ~100
defs of registers containing constants, which we in the predecessor block, where
only one of those constants is used in each successor. So, at each computed goto,
we needlessly spill about a 100 constants to stack. The end result is that a
clang-compiled python interpreter can be about ~2.5x slower on a simple python
reduction loop than a gcc-compiled interpreter.

Differential Revision: https://reviews.llvm.org/D29916

llvm-svn: 296149

3 files changed, 26 insertions, 13 deletions

diff --git a/llvm/test/CodeGen/ARM/indirectbr.ll b/llvm/test/CodeGen/ARM/indirectbr.ll
index d15ef14b449..90defad43a7 100644
--- a/llvm/test/CodeGen/ARM/indirectbr.ll
+++ b/llvm/test/CodeGen/ARM/indirectbr.ll
@@ -47,6 +47,7 @@ L3:                                               ; preds = %L4, %bb2
   br label %L2
 
 L2:                                               ; preds = %L3, %bb2
+; THUMB-LABEL: %L1.clone
 ; THUMB: muls
   %res.2 = phi i32 [ %res.1, %L3 ], [ 1, %bb2 ]   ; <i32> [#uses=1]
   %phitmp = mul i32 %res.2, 6                     ; <i32> [#uses=1]
diff --git a/llvm/test/CodeGen/MSP430/indirectbr2.ll b/llvm/test/CodeGen/MSP430/indirectbr2.ll
index b0b4f1cbfd2..55598b97d91 100644
--- a/llvm/test/CodeGen/MSP430/indirectbr2.ll
+++ b/llvm/test/CodeGen/MSP430/indirectbr2.ll
@@ -5,7 +5,7 @@ define internal i16 @foo(i16 %i) nounwind {
 entry:
   %tmp1 = getelementptr inbounds [5 x i8*], [5 x i8*]* @C.0.2070, i16 0, i16 %i ; <i8**> [#uses=1]
   %gotovar.4.0 = load i8*, i8** %tmp1, align 4        ; <i8*> [#uses=1]
-; CHECK: br .LC.0.2070(r12)
+; CHECK: br .LC.0.2070(r15)
   indirectbr i8* %gotovar.4.0, [label %L5, label %L4, label %L3, label %L2, label %L1]
 
 L5:                                               ; preds = %bb2
diff --git a/llvm/test/CodeGen/PowerPC/indirectbr.ll b/llvm/test/CodeGen/PowerPC/indirectbr.ll
index d1e03ca7773..c040d7859a8 100644
--- a/llvm/test/CodeGen/PowerPC/indirectbr.ll
+++ b/llvm/test/CodeGen/PowerPC/indirectbr.ll
@@ -17,23 +17,35 @@ entry:
 bb2:                                              ; preds = %entry, %bb3
   %gotovar.4.0 = phi i8* [ %gotovar.4.0.pre, %bb3 ], [ %0, %entry ] ; <i8*> [#uses=1]
 ; PIC: mtctr
-; PIC-NEXT: li
-; PIC-NEXT: li
-; PIC-NEXT: li
-; PIC-NEXT: li
 ; PIC-NEXT: bctr
+; PIC: li
+; PIC: b LBB
+; PIC: li
+; PIC: b LBB
+; PIC: li
+; PIC: b LBB
+; PIC: li
+; PIC: b LBB
 ; STATIC: mtctr
-; STATIC-NEXT: li
-; STATIC-NEXT: li
-; STATIC-NEXT: li
-; STATIC-NEXT: li
 ; STATIC-NEXT: bctr
+; STATIC: li
+; STATIC: b LBB
+; STATIC: li
+; STATIC: b LBB
+; STATIC: li
+; STATIC: b LBB
+; STATIC: li
+; STATIC: b LBB
 ; PPC64: mtctr
-; PPC64-NEXT: li
-; PPC64-NEXT: li
-; PPC64-NEXT: li
-; PPC64-NEXT: li
 ; PPC64-NEXT: bctr
+; PPC64: li
+; PPC64: b LBB
+; PPC64: li
+; PPC64: b LBB
+; PPC64: li
+; PPC64: b LBB
+; PPC64: li
+; PPC64: b LBB
   indirectbr i8* %gotovar.4.0, [label %L5, label %L4, label %L3, label %L2, label %L1]
 
 bb3:                                              ; preds = %entry