Skip to content
Commit f07a587c authored by Chris Lattner's avatar Chris Lattner
Browse files

Make IVUseShouldUsePostIncValue more aggressive when the use is a PHI. In

particular, it should realize that phi's use their values in the pred block
not the phi block itself.  This change turns our em3d loop from this:

_test:
        cmpwi cr0, r4, 0
        bgt cr0, LBB_test_2     ; entry.no_exit_crit_edge
LBB_test_1:     ; entry.loopexit_crit_edge
        li r2, 0
        b LBB_test_6    ; loopexit
LBB_test_2:     ; entry.no_exit_crit_edge
        li r6, 0
LBB_test_3:     ; no_exit
        or r2, r6, r6
        lwz r6, 0(r3)
        cmpw cr0, r6, r5
        beq cr0, LBB_test_6     ; loopexit
LBB_test_4:     ; endif
        addi r3, r3, 4
        addi r6, r2, 1
        cmpw cr0, r6, r4
        blt cr0, LBB_test_3     ; no_exit
LBB_test_5:     ; endif.loopexit.loopexit_crit_edge
        addi r3, r2, 1
        blr
LBB_test_6:     ; loopexit
        or r3, r2, r2
        blr

into:

_test:
        cmpwi cr0, r4, 0
        bgt cr0, LBB_test_2     ; entry.no_exit_crit_edge
LBB_test_1:     ; entry.loopexit_crit_edge
        li r2, 0
        b LBB_test_5    ; loopexit
LBB_test_2:     ; entry.no_exit_crit_edge
        li r6, 0
LBB_test_3:     ; no_exit
        lwz r2, 0(r3)
        cmpw cr0, r2, r5
        or r2, r6, r6
        beq cr0, LBB_test_5     ; loopexit
LBB_test_4:     ; endif
        addi r3, r3, 4
        addi r6, r6, 1
        cmpw cr0, r6, r4
        or r2, r6, r6
        blt cr0, LBB_test_3     ; no_exit
LBB_test_5:     ; loopexit
        or r3, r2, r2
        blr


Unfortunately, this is actually worse code, because the register coallescer
is getting confused somehow.  If it were doing its job right, it could turn the
code into this:

_test:
        cmpwi cr0, r4, 0
        bgt cr0, LBB_test_2     ; entry.no_exit_crit_edge
LBB_test_1:     ; entry.loopexit_crit_edge
        li r6, 0
        b LBB_test_5    ; loopexit
LBB_test_2:     ; entry.no_exit_crit_edge
        li r6, 0
LBB_test_3:     ; no_exit
        lwz r2, 0(r3)
        cmpw cr0, r2, r5
        beq cr0, LBB_test_5     ; loopexit
LBB_test_4:     ; endif
        addi r3, r3, 4
        addi r6, r6, 1
        cmpw cr0, r6, r4
        blt cr0, LBB_test_3     ; no_exit
LBB_test_5:     ; loopexit
        or r3, r6, r6
        blr

... which I'll work on next. :)

llvm-svn: 23604
parent e4ed42a4
Loading
Loading
Loading
Loading
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment