typically cost 1 cycle) instead of shld/shrd instruction (which are typically
6 or more cycles). This also saves code space.
For example, instead of emitting:
rotr:
mov %EAX, DWORD PTR [%ESP + 4]
mov %CL, BYTE PTR [%ESP + 8]
shrd %EAX, %EAX, %CL
ret
rotli:
mov %EAX, DWORD PTR [%ESP + 4]
shrd %EAX, %EAX, 27
ret
Emit:
rotr32:
mov %CL, BYTE PTR [%ESP + 8]
mov %EAX, DWORD PTR [%ESP + 4]
ror %EAX, %CL
ret
rotli32:
mov %EAX, DWORD PTR [%ESP + 4]
ror %EAX, 27
ret
We also emit byte rotate instructions which do not have a sh[lr]d counterpart
at all.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19692 91177308-0d34-0410-b5e6-96231b3b80d8
select operations or to shifts that are by a constant. This automatically
implements (with no special code) all of the special cases for shift by 32,
shift by < 32 and shift by > 32.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19679 91177308-0d34-0410-b5e6-96231b3b80d8
range. Either they are undefined (the default), they mask the shift amount
to the size of the register (X86, Alpha, etc), or they extend the shift (PPC).
This defaults to undefined, which is conservatively correct.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19677 91177308-0d34-0410-b5e6-96231b3b80d8
Add a hook to find out how the target handles shift amounts that are out of
range. Either they are undefined (the default), they mask the shift amount
to the size of the register (X86, Alpha, etc), or they extend the shift (PPC).
This defaults to undefined, which is conservatively correct.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19676 91177308-0d34-0410-b5e6-96231b3b80d8
do it. This results in better code on X86 for floats (because if strict
precision is not required, we can elide some more expensive double -> float
conversions like the old isel did), and allows other targets to emit
CopyFromRegs that are not legal for arguments.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19668 91177308-0d34-0410-b5e6-96231b3b80d8
* Insert some really pedantic assertions that will notice when we emit the
same loads more than one time, exposing bugs. This turns a miscompilation in
bzip2 into a compile-fail. yaay.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19658 91177308-0d34-0410-b5e6-96231b3b80d8
match (X+Y)+(Z << 1), because we match the X+Y first, consuming the index
register, then there is no place to put the Z.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19652 91177308-0d34-0410-b5e6-96231b3b80d8
X86/reg-pressure.ll again, and allows us to do nice things in other cases.
For example, we now codegen this sort of thing:
int %loadload(int *%X, int* %Y) {
%Z = load int* %Y
%Y = load int* %X ;; load between %Z and store
%Q = add int %Z, 1
store int %Q, int* %Y
ret int %Y
}
Into this:
loadload:
mov %EAX, DWORD PTR [%ESP + 4]
mov %EAX, DWORD PTR [%EAX]
mov %ECX, DWORD PTR [%ESP + 8]
inc DWORD PTR [%ECX]
ret
where we weren't able to form the 'inc [mem]' before. This also lets the
instruction selector emit loads in any order it wants to, which can be good
for register pressure as well.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19644 91177308-0d34-0410-b5e6-96231b3b80d8
1. Fold [mem] += (1|-1) into inc [mem]/dec [mem] to save some icache space.
2. Do not let token factor nodes prevent forming '[mem] op= val' folds.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19643 91177308-0d34-0410-b5e6-96231b3b80d8
the basic block that uses them if possible. This is a big win on X86, as it
lets us fold the argument loads into instructions and reduce register pressure
(by not loading all of the arguments in the entry block).
For this (contrived to show the optimization) testcase:
int %argtest(int %A, int %B) {
%X = sub int 12345, %A
br label %L
L:
%Y = add int %X, %B
ret int %Y
}
we used to produce:
argtest:
mov %ECX, DWORD PTR [%ESP + 4]
mov %EAX, 12345
sub %EAX, %ECX
mov %EDX, DWORD PTR [%ESP + 8]
.LBBargtest_1: # L
add %EAX, %EDX
ret
now we produce:
argtest:
mov %EAX, 12345
sub %EAX, DWORD PTR [%ESP + 4]
.LBBargtest_1: # L
add %EAX, DWORD PTR [%ESP + 8]
ret
This also fixes the FIXME in the code.
BTW, this occurs in real code. 164.gzip shrinks from 8623 to 8608 lines of
.s file. The stack frame in huft_build shrinks from 1644->1628 bytes,
inflate_codes shrinks from 116->108 bytes, and inflate_block from 2620->2612,
due to fewer spills.
Take that alkis. :-)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19639 91177308-0d34-0410-b5e6-96231b3b80d8
