forked from OSchip/llvm-project
5 Commits
| Author | SHA1 | Message | Date |
|---|---|---|---|
Kyle Butt
|
a8c7371d16 |
CodeGen: If Convert blocks that would form a diamond when tail-merged.
The following function currently relies on tail-merging for if
conversion to succeed. The common tail of cond_true and cond_false is
extracted, and this then forms a diamond pattern that can be
successfully if converted.
If this block does not get extracted, either because tail-merging is
disabled or the threshold is higher, we should still recognize this
pattern and if-convert it.
Fixed a regression in the original commit. Need to un-reverse branches after
reversing them, or other conversions go awry.
define i32 @t2(i32 %a, i32 %b) nounwind {
entry:
%tmp1434 = icmp eq i32 %a, %b ; <i1> [#uses=1]
br i1 %tmp1434, label %bb17, label %bb.outer
bb.outer: ; preds = %cond_false, %entry
%b_addr.021.0.ph = phi i32 [ %b, %entry ], [ %tmp10, %cond_false ]
%a_addr.026.0.ph = phi i32 [ %a, %entry ], [ %a_addr.026.0, %cond_false ]
br label %bb
bb: ; preds = %cond_true, %bb.outer
%indvar = phi i32 [ 0, %bb.outer ], [ %indvar.next, %cond_true ]
%tmp. = sub i32 0, %b_addr.021.0.ph
%tmp.40 = mul i32 %indvar, %tmp.
%a_addr.026.0 = add i32 %tmp.40, %a_addr.026.0.ph
%tmp3 = icmp sgt i32 %a_addr.026.0, %b_addr.021.0.ph
br i1 %tmp3, label %cond_true, label %cond_false
cond_true: ; preds = %bb
%tmp7 = sub i32 %a_addr.026.0, %b_addr.021.0.ph
%tmp1437 = icmp eq i32 %tmp7, %b_addr.021.0.ph
%indvar.next = add i32 %indvar, 1
br i1 %tmp1437, label %bb17, label %bb
cond_false: ; preds = %bb
%tmp10 = sub i32 %b_addr.021.0.ph, %a_addr.026.0
%tmp14 = icmp eq i32 %a_addr.026.0, %tmp10
br i1 %tmp14, label %bb17, label %bb.outer
bb17: ; preds = %cond_false, %cond_true, %entry
%a_addr.026.1 = phi i32 [ %a, %entry ], [ %tmp7, %cond_true ], [ %a_addr.026.0, %cond_false ]
ret i32 %a_addr.026.1
}
Without tail-merging or diamond-tail if conversion:
LBB1_1: @ %bb
@ =>This Inner Loop Header: Depth=1
cmp r0, r1
ble LBB1_3
@ BB#2: @ %cond_true
@ in Loop: Header=BB1_1 Depth=1
subs r0, r0, r1
cmp r1, r0
it ne
cmpne r0, r1
bgt LBB1_4
LBB1_3: @ %cond_false
@ in Loop: Header=BB1_1 Depth=1
subs r1, r1, r0
cmp r1, r0
bne LBB1_1
LBB1_4: @ %bb17
bx lr
With diamond-tail if conversion, but without tail-merging:
@ BB#0: @ %entry
cmp r0, r1
it eq
bxeq lr
LBB1_1: @ %bb
@ =>This Inner Loop Header: Depth=1
cmp r0, r1
ite le
suble r1, r1, r0
subgt r0, r0, r1
cmp r1, r0
bne LBB1_1
@ BB#2: @ %bb17
bx lr
llvm-svn: 279671
|
|
|
Kyle Butt
|
ce0196de3f |
Revert "CodeGen: If Convert blocks that would form a diamond when tail-merged."
This reverts commit 0fda93481c4231c06b838ef476c0c404c51ff875. llvm-svn: 279288 |
|
|
Kyle Butt
|
780b517d6b |
CodeGen: If Convert blocks that would form a diamond when tail-merged.
The following function currently relies on tail-merging for if
conversion to succeed. The common tail of cond_true and cond_false is
extracted, and this then forms a diamond pattern that can be
successfully if converted.
If this block does not get extracted, either because tail-merging is
disabled or the threshold is higher, we should still recognize this
pattern and if-convert it.
Fixed a regression in the original commit. Need to un-reverse branches after
reversing them, or other conversions go awry.
Regression on self-hosting bots with no obvious explanation. Tidied up range
handling to be more obviously correct, but there was no smoking gun.
define i32 @t2(i32 %a, i32 %b) nounwind {
entry:
%tmp1434 = icmp eq i32 %a, %b ; <i1> [#uses=1]
br i1 %tmp1434, label %bb17, label %bb.outer
bb.outer: ; preds = %cond_false, %entry
%b_addr.021.0.ph = phi i32 [ %b, %entry ], [ %tmp10, %cond_false ]
%a_addr.026.0.ph = phi i32 [ %a, %entry ], [ %a_addr.026.0, %cond_false ]
br label %bb
bb: ; preds = %cond_true, %bb.outer
%indvar = phi i32 [ 0, %bb.outer ], [ %indvar.next, %cond_true ]
%tmp. = sub i32 0, %b_addr.021.0.ph
%tmp.40 = mul i32 %indvar, %tmp.
%a_addr.026.0 = add i32 %tmp.40, %a_addr.026.0.ph
%tmp3 = icmp sgt i32 %a_addr.026.0, %b_addr.021.0.ph
br i1 %tmp3, label %cond_true, label %cond_false
cond_true: ; preds = %bb
%tmp7 = sub i32 %a_addr.026.0, %b_addr.021.0.ph
%tmp1437 = icmp eq i32 %tmp7, %b_addr.021.0.ph
%indvar.next = add i32 %indvar, 1
br i1 %tmp1437, label %bb17, label %bb
cond_false: ; preds = %bb
%tmp10 = sub i32 %b_addr.021.0.ph, %a_addr.026.0
%tmp14 = icmp eq i32 %a_addr.026.0, %tmp10
br i1 %tmp14, label %bb17, label %bb.outer
bb17: ; preds = %cond_false, %cond_true, %entry
%a_addr.026.1 = phi i32 [ %a, %entry ], [ %tmp7, %cond_true ], [ %a_addr.026.0, %cond_false ]
ret i32 %a_addr.026.1
}
Without tail-merging or diamond-tail if conversion:
LBB1_1: @ %bb
@ =>This Inner Loop Header: Depth=1
cmp r0, r1
ble LBB1_3
@ BB#2: @ %cond_true
@ in Loop: Header=BB1_1 Depth=1
subs r0, r0, r1
cmp r1, r0
it ne
cmpne r0, r1
bgt LBB1_4
LBB1_3: @ %cond_false
@ in Loop: Header=BB1_1 Depth=1
subs r1, r1, r0
cmp r1, r0
bne LBB1_1
LBB1_4: @ %bb17
bx lr
With diamond-tail if conversion, but without tail-merging:
@ BB#0: @ %entry
cmp r0, r1
it eq
bxeq lr
LBB1_1: @ %bb
@ =>This Inner Loop Header: Depth=1
cmp r0, r1
ite le
suble r1, r1, r0
subgt r0, r0, r1
cmp r1, r0
bne LBB1_1
@ BB#2: @ %bb17
bx lr
llvm-svn: 279168
|
|
|
Diana Picus
|
68be1eb885 |
Revert "CodeGen: If Convert blocks that would form a diamond when tail-merged."
This reverts commit r278287. This commit broke the clang-cmake-thumbv7-a15-full-sh bot. See https://llvm.org/bugs/show_bug.cgi?id=28949 llvm-svn: 278621 |
|
|
Kyle Butt
|
e1c931b171 |
CodeGen: If Convert blocks that would form a diamond when tail-merged.
The following function currently relies on tail-merging for if
conversion to succeed. The common tail of cond_true and cond_false is
extracted, and this then forms a diamond pattern that can be
successfully if converted.
If this block does not get extracted, either because tail-merging is
disabled or the threshold is higher, we should still recognize this
pattern and if-convert it.
Fixed a regression in the original commit. Need to un-reverse branches after
reversing them, or other conversions go awry.
define i32 @t2(i32 %a, i32 %b) nounwind {
entry:
%tmp1434 = icmp eq i32 %a, %b ; <i1> [#uses=1]
br i1 %tmp1434, label %bb17, label %bb.outer
bb.outer: ; preds = %cond_false, %entry
%b_addr.021.0.ph = phi i32 [ %b, %entry ], [ %tmp10, %cond_false ]
%a_addr.026.0.ph = phi i32 [ %a, %entry ], [ %a_addr.026.0, %cond_false ]
br label %bb
bb: ; preds = %cond_true, %bb.outer
%indvar = phi i32 [ 0, %bb.outer ], [ %indvar.next, %cond_true ]
%tmp. = sub i32 0, %b_addr.021.0.ph
%tmp.40 = mul i32 %indvar, %tmp.
%a_addr.026.0 = add i32 %tmp.40, %a_addr.026.0.ph
%tmp3 = icmp sgt i32 %a_addr.026.0, %b_addr.021.0.ph
br i1 %tmp3, label %cond_true, label %cond_false
cond_true: ; preds = %bb
%tmp7 = sub i32 %a_addr.026.0, %b_addr.021.0.ph
%tmp1437 = icmp eq i32 %tmp7, %b_addr.021.0.ph
%indvar.next = add i32 %indvar, 1
br i1 %tmp1437, label %bb17, label %bb
cond_false: ; preds = %bb
%tmp10 = sub i32 %b_addr.021.0.ph, %a_addr.026.0
%tmp14 = icmp eq i32 %a_addr.026.0, %tmp10
br i1 %tmp14, label %bb17, label %bb.outer
bb17: ; preds = %cond_false, %cond_true, %entry
%a_addr.026.1 = phi i32 [ %a, %entry ], [ %tmp7, %cond_true ], [ %a_addr.026.0, %cond_false ]
ret i32 %a_addr.026.1
}
Without tail-merging or diamond-tail if conversion:
LBB1_1: @ %bb
@ =>This Inner Loop Header: Depth=1
cmp r0, r1
ble LBB1_3
@ BB#2: @ %cond_true
@ in Loop: Header=BB1_1 Depth=1
subs r0, r0, r1
cmp r1, r0
it ne
cmpne r0, r1
bgt LBB1_4
LBB1_3: @ %cond_false
@ in Loop: Header=BB1_1 Depth=1
subs r1, r1, r0
cmp r1, r0
bne LBB1_1
LBB1_4: @ %bb17
bx lr
With diamond-tail if conversion, but without tail-merging:
@ BB#0: @ %entry
cmp r0, r1
it eq
bxeq lr
LBB1_1: @ %bb
@ =>This Inner Loop Header: Depth=1
cmp r0, r1
ite le
suble r1, r1, r0
subgt r0, r0, r1
cmp r1, r0
bne LBB1_1
@ BB#2: @ %bb17
bx lr
llvm-svn: 278287
|