mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-24 06:30:19 +00:00
e7b06c65ba
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@25943 91177308-0d34-0410-b5e6-96231b3b80d8
75 lines
2.2 KiB
Plaintext
75 lines
2.2 KiB
Plaintext
Target Independent Opportunities:
|
|
|
|
===-------------------------------------------------------------------------===
|
|
|
|
FreeBench/mason contains code like this:
|
|
|
|
static p_type m0u(p_type p) {
|
|
int m[]={0, 8, 1, 2, 16, 5, 13, 7, 14, 9, 3, 4, 11, 12, 15, 10, 17, 6};
|
|
p_type pu;
|
|
pu.a = m[p.a];
|
|
pu.b = m[p.b];
|
|
pu.c = m[p.c];
|
|
return pu;
|
|
}
|
|
|
|
We currently compile this into a memcpy from a static array into 'm', then
|
|
a bunch of loads from m. It would be better to avoid the memcpy and just do
|
|
loads from the static array.
|
|
|
|
===-------------------------------------------------------------------------===
|
|
|
|
Get the C front-end to expand hypot(x,y) -> llvm.sqrt(x*x+y*y) when errno and
|
|
precision don't matter (ffastmath). Misc/mandel will like this. :)
|
|
|
|
===-------------------------------------------------------------------------===
|
|
|
|
For all targets, not just X86:
|
|
When llvm.memcpy, llvm.memset, or llvm.memmove are lowered, they should be
|
|
optimized to a few store instructions if the source is constant and the length
|
|
is smallish (< 8). This will greatly help some tests like Shootout/strcat.c
|
|
and fldry.
|
|
|
|
//===---------------------------------------------------------------------===//
|
|
|
|
Solve this DAG isel folding deficiency:
|
|
|
|
int X, Y;
|
|
|
|
void fn1(void)
|
|
{
|
|
X = X | (Y << 3);
|
|
}
|
|
|
|
compiles to
|
|
|
|
fn1:
|
|
movl Y, %eax
|
|
shll $3, %eax
|
|
orl X, %eax
|
|
movl %eax, X
|
|
ret
|
|
|
|
The problem is the store's chain operand is not the load X but rather
|
|
a TokenFactor of the load X and load Y, which prevents the folding.
|
|
|
|
There are two ways to fix this:
|
|
|
|
1. The dag combiner can start using alias analysis to realize that y/x
|
|
don't alias, making the store to X not dependent on the load from Y.
|
|
2. The generated isel could be made smarter in the case it can't
|
|
disambiguate the pointers.
|
|
|
|
Number 1 is the preferred solution.
|
|
|
|
//===---------------------------------------------------------------------===//
|
|
|
|
For dag combiner and instcombine:
|
|
Fold: "A / (B << N)" where B is a power of 2, to "A >> (N + log2(B))".
|
|
Fold: "A % (B << N)" where B is a power of 2, to "A & ((B << N) - 1)".
|
|
|
|
int t(int X, int Y) { return 1 << (X+4); } --> 16 << X
|
|
|
|
|
|
//===---------------------------------------------------------------------===//
|