2016-03-29 08:23:41 +08:00
|
|
|
; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-a9 -jump-table-density=40 | FileCheck %s
|
2011-08-26 01:50:53 +08:00
|
|
|
; Test that ldmia_ret preserves implicit operands for return values.
|
|
|
|
|
;
|
|
|
|
|
; This CFG is reduced from a benchmark miscompile. With current
|
|
|
|
|
; if-conversion heuristics, one of the return paths is if-converted
|
|
|
|
|
; into sw.bb18 resulting in an ldmia_ret in the middle of the
|
|
|
|
|
; block. The postra scheduler needs to know that the return implicitly
|
|
|
|
|
; uses the return register, otherwise its antidep breaker scavenges
|
|
|
|
|
; the register in order to hoist the constant load required to test
|
|
|
|
|
; the switch.
|
|
|
|
|
|
|
|
|
|
declare i32 @getint()
|
|
|
|
|
declare i1 @getbool()
|
|
|
|
|
declare void @foo(i32)
|
|
|
|
|
declare i32 @bar(i32)
|
|
|
|
|
|
[ARM] Generate consistent frame records for Thumb2
There is not an official documented ABI for frame pointers in Thumb2,
but we should try to emit something which is useful.
We use r7 as the frame pointer for Thumb code, which currently means
that if a function needs to save a high register (r8-r11), it will get
pushed to the stack between the frame pointer (r7) and link register
(r14). This means that while a stack unwinder can follow the chain of
frame pointers up the stack, it cannot know the offset to lr, so does
not know which functions correspond to the stack frames.
To fix this, we need to push the callee-saved registers in two batches,
with the first push saving the low registers, fp and lr, and the second
push saving the high registers. This is already implemented, but
previously only used for iOS. This patch turns it on for all Thumb2
targets when frame pointers are required by the ABI, and the frame
pointer is r7 (Windows uses r11, so this isn't a problem there). If
frame pointer elimination is enabled we still emit a single push/pop
even if we need a frame pointer for other reasons, to avoid increasing
code size.
We must also ensure that lr is pushed to the stack when using a frame
pointer, so that we end up with a complete frame record. Situations that
could cause this were rare, because we already push lr in most
situations so that we can return using the pop instruction.
Differential Revision: https://reviews.llvm.org/D23516
llvm-svn: 279506
2016-08-23 17:19:22 +08:00
|
|
|
define i32 @test(i32 %in1, i32 %in2) nounwind "no-frame-pointer-elim"="true" {
|
2011-08-26 01:50:53 +08:00
|
|
|
entry:
|
|
|
|
|
%call = tail call zeroext i1 @getbool() nounwind
|
|
|
|
|
br i1 %call, label %sw.bb18, label %sw.bb2
|
|
|
|
|
|
|
|
|
|
sw.bb2: ; preds = %entry
|
|
|
|
|
%cmp = tail call zeroext i1 @getbool() nounwind
|
|
|
|
|
br i1 %cmp, label %sw.epilog58, label %land.lhs.true
|
|
|
|
|
|
|
|
|
|
land.lhs.true: ; preds = %sw.bb2
|
|
|
|
|
%cmp13 = tail call zeroext i1 @getbool() nounwind
|
|
|
|
|
br i1 %cmp13, label %if.then, label %sw.epilog58
|
|
|
|
|
|
|
|
|
|
if.then: ; preds = %land.lhs.true
|
|
|
|
|
tail call void @foo(i32 %in1) nounwind
|
|
|
|
|
br label %sw.epilog58
|
|
|
|
|
|
|
|
|
|
; load the return value
|
|
|
|
|
; CHECK: movs [[RRET:r.]], #2
|
|
|
|
|
; hoist the switch constant without clobbering RRET
|
|
|
|
|
; CHECK: movw
|
|
|
|
|
; CHECK-NOT: [[RRET]]
|
|
|
|
|
; CHECK: , #63707
|
|
|
|
|
; CHECK-NOT: [[RRET]]
|
|
|
|
|
; CHECK: tst
|
|
|
|
|
; If-convert the return
|
|
|
|
|
; CHECK: it ne
|
|
|
|
|
; Fold the CSR+return into a pop
|
MachineSink: Fix and tweak critical-edge breaking heuristic.
Per original comment, the intention of this loop
is to go ahead and break the critical edge
(in order to sink this instruction) if there's
reason to believe doing so might "unblock" the
sinking of additional instructions that define
registers used by this one. The idea is that if
we have a few instructions to sink "together"
breaking the edge might be worthwhile.
This commit makes a few small changes
to help better realize this goal:
First, modify the loop to ignore registers
defined by this instruction. We don't
sink definitions of physical registers,
and sinking an SSA definition isn't
going to unblock an upstream instruction.
Second, ignore uses of physical registers.
Instructions that define physical registers are
rejected for sinking, and so moving this one
won't enable moving any defining instructions.
As an added bonus, while virtual register
use-def chains are generally small due
to SSA goodness, iteration over the uses
and definitions (used by hasOneNonDBGUse)
for physical registers like EFLAGS
can be rather expensive in practice.
(This is the original reason for looking at this)
Finally, to keep things simple continue
to only consider this trick for registers that
have a single use (via hasOneNonDBGUse),
but to avoid spuriously breaking critical edges
only do so if the definition resides
in the same MBB and therefore this one directly
blocks it from being sunk as well.
If sinking them together is meant to be,
let the iterative nature of this pass
sink the definition into this block first.
Update tests to accomodate this change,
add new testcase where sinking avoids pipeline stalls.
llvm-svn: 192608
2013-10-15 00:57:17 +08:00
|
|
|
; CHECK: pop {r4, r5, r7, pc}
|
2011-08-26 01:50:53 +08:00
|
|
|
sw.bb18:
|
|
|
|
|
%call20 = tail call i32 @bar(i32 %in2) nounwind
|
|
|
|
|
switch i32 %call20, label %sw.default56 [
|
|
|
|
|
i32 168, label %sw.bb21
|
|
|
|
|
i32 165, label %sw.bb21
|
|
|
|
|
i32 261, label %sw.epilog58
|
|
|
|
|
i32 188, label %sw.epilog58
|
|
|
|
|
i32 187, label %sw.epilog58
|
|
|
|
|
i32 186, label %sw.epilog58
|
|
|
|
|
i32 185, label %sw.epilog58
|
|
|
|
|
i32 184, label %sw.epilog58
|
|
|
|
|
i32 175, label %sw.epilog58
|
|
|
|
|
i32 174, label %sw.epilog58
|
|
|
|
|
i32 173, label %sw.epilog58
|
|
|
|
|
i32 172, label %sw.epilog58
|
|
|
|
|
i32 171, label %sw.epilog58
|
|
|
|
|
i32 167, label %sw.epilog58
|
|
|
|
|
i32 166, label %sw.epilog58
|
|
|
|
|
i32 164, label %sw.epilog58
|
|
|
|
|
i32 163, label %sw.epilog58
|
|
|
|
|
i32 161, label %sw.epilog58
|
|
|
|
|
i32 160, label %sw.epilog58
|
|
|
|
|
i32 -1, label %sw.bb33
|
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
sw.bb21: ; preds = %sw.bb18, %sw.bb18
|
|
|
|
|
tail call void @foo(i32 %in2) nounwind
|
|
|
|
|
%call28 = tail call i32 @getint() nounwind
|
|
|
|
|
%tobool = icmp eq i32 %call28, 0
|
|
|
|
|
br i1 %tobool, label %if.then29, label %sw.epilog58
|
|
|
|
|
|
|
|
|
|
if.then29: ; preds = %sw.bb21
|
|
|
|
|
tail call void @foo(i32 %in2) nounwind
|
|
|
|
|
br label %sw.epilog58
|
|
|
|
|
|
|
|
|
|
sw.bb33: ; preds = %sw.bb18
|
|
|
|
|
%cmp42 = tail call zeroext i1 @getbool() nounwind
|
|
|
|
|
br i1 %cmp42, label %sw.default56, label %land.lhs.true44
|
|
|
|
|
|
|
|
|
|
land.lhs.true44: ; preds = %sw.bb33
|
|
|
|
|
%call50 = tail call i32 @getint() nounwind
|
|
|
|
|
%cmp51 = icmp slt i32 %call50, 0
|
|
|
|
|
br i1 %cmp51, label %if.then53, label %sw.default56
|
|
|
|
|
|
|
|
|
|
if.then53: ; preds = %land.lhs.true44
|
|
|
|
|
tail call void @foo(i32 %in2) nounwind
|
|
|
|
|
br label %sw.default56
|
|
|
|
|
|
|
|
|
|
sw.default56: ; preds = %sw.bb33, %land.lhs.true44, %if.then53, %sw.bb18
|
|
|
|
|
br label %sw.epilog58
|
|
|
|
|
|
|
|
|
|
sw.epilog58:
|
|
|
|
|
%retval.0 = phi i32 [ 4, %sw.default56 ], [ 2, %sw.bb21 ], [ 2, %if.then29 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb18 ], [ 2, %sw.bb2 ], [ 2, %land.lhs.true ], [ 2, %if.then ]
|
|
|
|
|
ret i32 %retval.0
|
|
|
|
|
}
|