RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2024-12-02 08:46:37 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update the readme to remove duplicate information and clarify the loop

Browse Source 
problem.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@29468 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Nate Begeman 2006-08-02 05:31:20 +00:00
parent 8f74680c78
commit 83a6d49102
1 changed files with 19 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
lib/Target/X86/README.txt
View File

@ -198,7 +198,7 @@ on some processors (which ones?), it is more efficient to do this:
_test:
movl 8(%esp), %ebx
xor %eax, %eax
xor %eax, %eax
cmpl %ebx, 4(%esp)
setl %al
ret
@ -340,22 +340,6 @@ Enable X86InstrInfo::convertToThreeAddress().
//===---------------------------------------------------------------------===//
Investigate whether it is better to codegen the following
%tmp.1 = mul int %x, 9
to
movl 4(%esp), %eax
leal (%eax,%eax,8), %eax
as opposed to what llc is currently generating:
imull $9, 4(%esp), %eax
Currently the load folding imull has a higher complexity than the LEA32 pattern.
//===---------------------------------------------------------------------===//
We are currently lowering large (1MB+) memmove/memcpy to rep/stosl and rep/movsl
We should leave these as libcalls for everything over a much lower threshold,
since libc is hand tuned for medium and large mem ops (avoiding RFO for large
@ -671,35 +655,26 @@ We should handle __attribute__ ((__visibility__ ("hidden"))).
//===---------------------------------------------------------------------===//
Consider:
int foo(int *a, int t) {
int x;
for (x=0; x<40; ++x)
t = t + a[x] + x;
return t;
int %foo(int* %a, int %t) {
entry:
br label %cond_true
cond_true: ; preds = %cond_true, %entry
%x.0.0 = phi int [ 0, %entry ], [ %tmp9, %cond_true ] ; <int> [#uses=3]
%t_addr.0.0 = phi int [ %t, %entry ], [ %tmp7, %cond_true ] ; <int> [#uses=1]
%tmp2 = getelementptr int* %a, int %x.0.0 ; <int*> [#uses=1]
%tmp3 = load int* %tmp2 ; <int> [#uses=1]
%tmp5 = add int %t_addr.0.0, %x.0.0 ; <int> [#uses=1]
%tmp7 = add int %tmp5, %tmp3 ; <int> [#uses=2]
%tmp9 = add int %x.0.0, 1 ; <int> [#uses=2]
%tmp = setgt int %tmp9, 39 ; <bool> [#uses=1]
br bool %tmp, label %bb12, label %cond_true
bb12: ; preds = %cond_true
ret int %tmp7
}
We generate:
LBB1_1: #cond_true
movl %ecx, %esi
movl (%edx,%eax,4), %edi
movl %esi, %ecx
addl %edi, %ecx
addl %eax, %ecx
incl %eax
cmpl $40, %eax
jne LBB1_1 #cond_true
GCC generates:
L2:
addl (%ecx,%edx,4), %eax
addl %edx, %eax
addl $1, %edx
cmpl $40, %edx
jne L2
Smells like a register coallescing/reassociation issue.
is pessimized by -loop-reduce and -indvars
//===---------------------------------------------------------------------===//