Chris Lattner 020f714a93 If an indvar with a variable stride is used by the exit condition, go ahead ... and handle it like constant stride vars. This fixes some bad codegen in variable stride cases. For example, it compiles this: void foo(int k, int i) { for (k=i+i; k <= 8192; k+=i) flags2[k] = 0; } to: LBB1_1: #bb.preheader movl %eax, %ecx addl %ecx, %ecx movl L_flags2$non_lazy_ptr, %edx LBB1_2: #bb movb $0, (%edx,%ecx) addl %eax, %ecx cmpl $8192, %ecx jle LBB1_2 #bb LBB1_5: #return ret or (if the array is local and we are in dynamic-nonpic or static mode): LBB3_2: #bb movb $0, _flags2(%ecx) addl %eax, %ecx cmpl $8192, %ecx jle LBB3_2 #bb and: lis r2, ha16(L_flags2$non_lazy_ptr) lwz r2, lo16(L_flags2$non_lazy_ptr)(r2) slwi r3, r4, 1 LBB1_2: ;bb li r5, 0 add r6, r4, r3 stbx r5, r2, r3 cmpwi cr0, r6, 8192 bgt cr0, LBB1_5 ;return instead of: leal (%eax,%eax,2), %ecx movl %eax, %edx addl %edx, %edx addl L_flags2$non_lazy_ptr, %edx xorl %esi, %esi LBB1_2: #bb movb $0, (%edx,%esi) movl %eax, %edi addl %esi, %edi addl %ecx, %esi cmpl $8192, %esi jg LBB1_5 #return and: lis r2, ha16(L_flags2$non_lazy_ptr) lwz r2, lo16(L_flags2$non_lazy_ptr)(r2) mulli r3, r4, 3 slwi r5, r4, 1 li r6, 0 add r2, r2, r5 LBB1_2: ;bb li r5, 0 add r7, r3, r6 stbx r5, r2, r6 add r6, r4, r6 cmpwi cr0, r7, 8192 ble cr0, LBB1_2 ;bb This speeds up Benchmarks/Shootout/sieve from 8.533s to 6.464s and implements LoopStrengthReduce/var_stride_used_by_compare.ll git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@31809 91177308-0d34-0410-b5e6-96231b3b80d8		2006-11-17 06:17:33 +00:00
..
ADCE.cpp	eliminate RegisterOpt. It does the same thing as RegisterPass.	2006-08-27 22:42:52 +00:00
BasicBlockPlacement.cpp	eliminate RegisterOpt. It does the same thing as RegisterPass.	2006-08-27 22:42:52 +00:00
CondPropagate.cpp	There can be more than one PHINode at the start of the block.	2006-11-01 23:04:45 +00:00
ConstantProp.cpp	eliminate RegisterOpt. It does the same thing as RegisterPass.	2006-08-27 22:42:52 +00:00
CorrelatedExprs.cpp	remove dead code	2006-11-03 01:34:58 +00:00
DCE.cpp	eliminate RegisterOpt. It does the same thing as RegisterPass.	2006-08-27 22:42:52 +00:00
DeadStoreElimination.cpp	eliminate RegisterOpt. It does the same thing as RegisterPass.	2006-08-27 22:42:52 +00:00
GCSE.cpp	eliminate RegisterOpt. It does the same thing as RegisterPass.	2006-08-27 22:42:52 +00:00
IndVarSimplify.cpp	Fix Transforms/IndVarsSimplify/2006-09-20-LFTR-Crash.ll	2006-09-21 05:12:20 +00:00
InstructionCombining.cpp	Fix a gcc 4.2 warning.	2006-11-15 04:53:24 +00:00
LICM.cpp	An sinkable instruction may exist with uses, if those uses are in dead blocks.	2006-09-12 19:17:09 +00:00
LoopStrengthReduce.cpp	If an indvar with a variable stride is used by the exit condition, go ahead	2006-11-17 06:17:33 +00:00
LoopUnroll.cpp	For PR786:	2006-11-02 20:25:50 +00:00
LoopUnswitch.cpp	For PR786:	2006-11-02 20:25:50 +00:00
LowerGC.cpp	For PR950:	2006-10-20 07:07:24 +00:00
LowerPacked.cpp	For PR950:	2006-10-20 07:07:24 +00:00
Makefile	DONT_BUILD_RELINKED is gone and implied by BUILD_ARCHIVE now	2005-10-24 02:26:13 +00:00
PredicateSimplifier.cpp	Unbreak VC++ build.	2006-11-05 19:31:28 +00:00
Reassociate.cpp	For PR950:	2006-11-02 01:53:59 +00:00
Reg2Mem.cpp	eliminate RegisterOpt. It does the same thing as RegisterPass.	2006-08-27 22:42:52 +00:00
ScalarReplAggregates.cpp	For PR950:	2006-11-08 06:47:33 +00:00
SCCP.cpp	For PR786:	2006-11-02 20:25:50 +00:00
SimplifyCFG.cpp	eliminate RegisterOpt. It does the same thing as RegisterPass.	2006-08-27 22:42:52 +00:00
TailDuplication.cpp	set DEBUG_TYPE right	2006-09-27 04:58:23 +00:00
TailRecursionElimination.cpp	For PR786:	2006-11-02 20:25:50 +00:00