This eliminates an N*N*logN algorithm from the loop simplify pass, replacing
it with a much simpler and faster alternative. In a debug build, this reduces
gccas time on eon from 85s to 42s.
llvm-svn: 14851
"load (cast foo)". This allows us to compile C++ code like this:
class Bclass {
public: virtual int operator()() { return 666; }
};
class Dclass: public Bclass {
public: virtual int operator()() { return 667; }
} ;
int main(int argc, char** argv) {
Dclass x;
return x();
}
Into this:
int %main(int %argc, sbyte** %argv) {
entry:
call void %__main( )
ret int 667
}
Instead of this:
int %main(int %argc, sbyte** %argv) {
entry:
%x = alloca "struct.std::bad_typeid" ; <"struct.std::bad_typeid"*> [#uses=3]
call void %__main( )
%tmp.1.i.i = getelementptr "struct.std::bad_typeid"* %x, uint 0, uint 0, uint 0 ; <int (...)***> [#uses=1]
store int (...)** getelementptr ([3 x int (...)*]* %vtable for Bclass, int 0, long 2), int (...)*** %tmp.1.i.i
%tmp.3.i = getelementptr "struct.std::bad_typeid"* %x, int 0, uint 0, uint 0 ; <int (...)***> [#uses=1]
store int (...)** getelementptr ([3 x int (...)*]* %vtable for Dclass, int 0, long 2), int (...)*** %tmp.3.i
%tmp.5 = load int ("struct.std::bad_typeid"*)** cast (int (...)** getelementptr ([3 x int (...)*]* %vtable for Dclass, int 0, long 2) to int
("struct.std::bad_typeid"*)**) ; <int ("struct.std::bad_typeid"*)*> [#uses=1]
%tmp.6 = call int %tmp.5( "struct.std::bad_typeid"* %x ) ; <int> [#uses=1]
ret int %tmp.6
ret int 0
}
In order words, we now resolve the virtual function call.
llvm-svn: 14783
Don't touch GEPs for which DecomposeArrayRef is not going to do anything
special (e.g., < 2 indices, or 2 indices and the last one is a constant.)
llvm-svn: 14647
186.crafty, fhourstones and 132.ijpeg.
Bugpoint makes really nasty miscompilations embarassingly easy to find. It
narrowed it down to the instcombiner and this testcase (from fhourstones):
bool %l7153_l4706_htstat_loopentry_2E_4_no_exit_2E_4(int* %i, [32 x int]* %works, int* %tmp.98.out) {
newFuncRoot:
%tmp.96 = load int* %i ; <int> [#uses=1]
%tmp.97 = getelementptr [32 x int]* %works, long 0, int %tmp.96 ; <int*> [#uses=1]
%tmp.98 = load int* %tmp.97 ; <int> [#uses=2]
%tmp.99 = load int* %i ; <int> [#uses=1]
%tmp.100 = and int %tmp.99, 7 ; <int> [#uses=1]
%tmp.101 = seteq int %tmp.100, 7 ; <bool> [#uses=2]
%tmp.102 = cast bool %tmp.101 to int ; <int> [#uses=0]
br bool %tmp.101, label %codeRepl4.exitStub, label %codeRepl3.exitStub
codeRepl4.exitStub: ; preds = %newFuncRoot
store int %tmp.98, int* %tmp.98.out
ret bool true
codeRepl3.exitStub: ; preds = %newFuncRoot
store int %tmp.98, int* %tmp.98.out
ret bool false
}
... which only has one combination performed on it:
$ llvm-as < t.ll | opt -instcombine -debug | llvm-dis
IC: Old = %tmp.101 = seteq int %tmp.100, 7 ; <bool> [#uses=1]
New = setne int %tmp.100, 0 ; <bool>:<badref> [#uses=0]
IC: MOD = br bool %tmp.101, label %codeRepl3.exitStub, label %codeRepl4.exitStub
IC: MOD = %tmp.97 = getelementptr [32 x int]* %works, uint 0, int %tmp.96 ; <int*> [#uses=1]
It doesn't get much better than this. :)
llvm-svn: 14109
collapse this:
bool %le(int %A, int %B) {
%c1 = setgt int %A, %B
%tmp = select bool %c1, int 1, int 0
%c2 = setlt int %A, %B
%result = select bool %c2, int -1, int %tmp
%c3 = setle int %result, 0
ret bool %c3
}
into:
bool %le(int %A, int %B) {
%c3 = setle int %A, %B ; <bool> [#uses=1]
ret bool %c3
}
which is handy, because the Java FE makes these sequences all over the place.
This is tested as: test/Regression/Transforms/InstCombine/JavaCompare.ll
llvm-svn: 14086
This code hadn't been updated after the "structs with more than 256 elements"
related changes to the GEP instruction. Also it was not handling the
ConstantAggregateZero class.
Now it does!
llvm-svn: 13834
into (X & (C2 << C1)) != (C3 << C1), where the shift may be either left or
right and the compare may be any one.
This triggers 1546 times in 176.gcc alone, as it is a common pattern that
occurs for bitfield accesses.
llvm-svn: 13740
in the size calculation.
This is not something you want to see:
Loop Unroll: F[main] Loop %no_exit Loop Size = 2 Trip Count = 2147483648 - UNROLLING!
The problem was that 2*2147483648 == 0.
Now we get:
Loop Unroll: F[main] Loop %no_exit Loop Size = 2 Trip Count = 2147483648 - TOO LARGE: 4294967296>100
Thanks to some anonymous person playing with the demo page that repeatedly
caused zion to go into swapping land. That's one way to ensure you'll get
a quick bugfix. :)
Testcase here: Transforms/LoopUnroll/2004-05-13-DontUnrollTooMuch.ll
llvm-svn: 13564
%tmp.0 = getelementptr [50 x sbyte]* %ar, uint 0, int 5 ; <sbyte*> [#uses=2]
%tmp.7 = getelementptr sbyte* %tmp.0, int 8 ; <sbyte*> [#uses=1]
together. This patch actually allows us to simplify and generalize the code.
llvm-svn: 13415