summaryrefslogtreecommitdiffstats
path: root/llvm/lib/CodeGen/RegAllocLinearScan.cpp
diff options
context:
space:
mode:
authorChris Lattner <sabre@nondot.org>2004-03-16 23:29:09 +0000
committerChris Lattner <sabre@nondot.org>2004-03-16 23:29:09 +0000
commit95057f6ad1d8af0464c30d1187b40def57d2f591 (patch)
treea3c17fa19067c1a3c5f4eab205407a670ca43245 /llvm/lib/CodeGen/RegAllocLinearScan.cpp
parentbb1a2cc7abc796eb0d2f0b7ae61786a707bd71a8 (diff)
downloadbcm5719-llvm-95057f6ad1d8af0464c30d1187b40def57d2f591.tar.gz
bcm5719-llvm-95057f6ad1d8af0464c30d1187b40def57d2f591.zip
Okay, so there is no reasonable way for tail duplication to update SSA form,
as it is making effectively arbitrary modifications to the CFG and we don't have a domset/domfrontier implementations that can handle the dynamic updates. Instead of having a bunch of code that doesn't actually work in practice, just demote any potentially tricky values to the stack (causing the problem to go away entirely). Later invocations of mem2reg will rebuild SSA for us. This fixes all of the major performance regressions with tail duplication from LLVM 1.1. For example, this loop: --- int popcount(int x) { int result = 0; while (x != 0) { result = result + (x & 0x1); x = x >> 1; } return result; } --- Used to be compiled into: int %popcount(int %X) { entry: br label %loopentry loopentry: ; preds = %entry, %no_exit %x.0 = phi int [ %X, %entry ], [ %tmp.9, %no_exit ] ; <int> [#uses=3] %result.1.0 = phi int [ 0, %entry ], [ %tmp.6, %no_exit ] ; <int> [#uses=2] %tmp.1 = seteq int %x.0, 0 ; <bool> [#uses=1] br bool %tmp.1, label %loopexit, label %no_exit no_exit: ; preds = %loopentry %tmp.4 = and int %x.0, 1 ; <int> [#uses=1] %tmp.6 = add int %tmp.4, %result.1.0 ; <int> [#uses=1] %tmp.9 = shr int %x.0, ubyte 1 ; <int> [#uses=1] br label %loopentry loopexit: ; preds = %loopentry ret int %result.1.0 } And is now compiled into: int %popcount(int %X) { entry: br label %no_exit no_exit: ; preds = %entry, %no_exit %x.0.0 = phi int [ %X, %entry ], [ %tmp.9, %no_exit ] ; <int> [#uses=2] %result.1.0.0 = phi int [ 0, %entry ], [ %tmp.6, %no_exit ] ; <int> [#uses=1] %tmp.4 = and int %x.0.0, 1 ; <int> [#uses=1] %tmp.6 = add int %tmp.4, %result.1.0.0 ; <int> [#uses=2] %tmp.9 = shr int %x.0.0, ubyte 1 ; <int> [#uses=2] %tmp.1 = seteq int %tmp.9, 0 ; <bool> [#uses=1] br bool %tmp.1, label %loopexit, label %no_exit loopexit: ; preds = %no_exit ret int %tmp.6 } llvm-svn: 12457
Diffstat (limited to 'llvm/lib/CodeGen/RegAllocLinearScan.cpp')
0 files changed, 0 insertions, 0 deletions
OpenPOWER on IntegriCloud