maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/shrink-wrap-chkstk.ll

73 lines
2.1 KiB
LLVM
Raw Normal View History

[X86] Put no-op ADJCALLSTACK markers around all dynamic lowerings Summary: These ADJCALLSTACK markers don't generate code, but they keep dynamic alloca code that calls chkstk out of the prologue. This slightly pessimizes inalloca calls by preventing some register copy coalescing, but I can live with that. Reviewers: qcolombet Subscribers: hans, llvm-commits Differential Revision: http://reviews.llvm.org/D15200 llvm-svn: 254645
2015-12-04 04:46:59 +08:00
; RUN: llc < %s -enable-shrink-wrap=true | FileCheck %s
; chkstk cannot come before the usual prologue, since it adjusts ESP.
[X86] Fix a shrink-wrapping miscompile around __chkstk __chkstk clobbers EAX. If EAX is live across the prologue, then we have to take extra steps to save it. We already had code to do this if EAX was a register parameter. This change adapts it to work when shrink wrapping is used. llvm-svn: 261039
2016-02-17 08:17:33 +08:00
; If chkstk is used in the prologue, we also have to be careful about preserving
; EAX if it is used.
[X86] Put no-op ADJCALLSTACK markers around all dynamic lowerings Summary: These ADJCALLSTACK markers don't generate code, but they keep dynamic alloca code that calls chkstk out of the prologue. This slightly pessimizes inalloca calls by preventing some register copy coalescing, but I can live with that. Reviewers: qcolombet Subscribers: hans, llvm-commits Differential Revision: http://reviews.llvm.org/D15200 llvm-svn: 254645
2015-12-04 04:46:59 +08:00
target datalayout = "e-m:x-p:32:32-i64:64-f80:32-n8:16:32-a:0:32-S32"
target triple = "i686-pc-windows-msvc18.0.0"
Re-commit r269828 "X86: Avoid using _chkstk when lowering WIN_ALLOCA instructions" with an additional fix to make RegAllocFast ignore undef physreg uses. It would previously get confused about the "push %eax" instruction's use of eax. That method for adjusting the stack pointer is used in X86FrameLowering::emitSPUpdate as well, but since that runs after register-allocation, we didn't run into the RegAllocFast issue before. llvm-svn: 269949
2016-05-19 00:10:17 +08:00
%struct.S = type { [8192 x i8] }
[X86] Put no-op ADJCALLSTACK markers around all dynamic lowerings Summary: These ADJCALLSTACK markers don't generate code, but they keep dynamic alloca code that calls chkstk out of the prologue. This slightly pessimizes inalloca calls by preventing some register copy coalescing, but I can live with that. Reviewers: qcolombet Subscribers: hans, llvm-commits Differential Revision: http://reviews.llvm.org/D15200 llvm-svn: 254645
2015-12-04 04:46:59 +08:00
Revert "[X86] Elide references to _chkstk for dynamic allocas" This reverts commit r262370. It turns out there is code out there that does sequences of allocas greater than 4K: http://crbug.com/591404 The goal of this change was to improve the code size of inalloca call sequences, but we got tangled up in the mess of dynamic allocas. Instead, we should come back later with a separate MI pass that uses dominance to optimize the full sequence. This should also be able to remove the often unneeded stacksave/stackrestore pairs around the call. llvm-svn: 262505
2016-03-03 03:20:59 +08:00
define x86_thiscallcc void @call_inalloca(i1 %x) {
[X86] Put no-op ADJCALLSTACK markers around all dynamic lowerings Summary: These ADJCALLSTACK markers don't generate code, but they keep dynamic alloca code that calls chkstk out of the prologue. This slightly pessimizes inalloca calls by preventing some register copy coalescing, but I can live with that. Reviewers: qcolombet Subscribers: hans, llvm-commits Differential Revision: http://reviews.llvm.org/D15200 llvm-svn: 254645
2015-12-04 04:46:59 +08:00
entry:
%argmem = alloca inalloca <{ %struct.S }>, align 4
%argidx1 = getelementptr inbounds <{ %struct.S }>, <{ %struct.S }>* %argmem, i32 0, i32 0, i32 0, i32 0
%argidx2 = getelementptr inbounds <{ %struct.S }>, <{ %struct.S }>* %argmem, i32 0, i32 0, i32 0, i32 1
store i8 42, i8* %argidx2, align 4
br i1 %x, label %bb1, label %bb2
bb1:
store i8 42, i8* %argidx1, align 4
br label %bb2
bb2:
call void @inalloca_params(<{ %struct.S }>* inalloca nonnull %argmem)
ret void
}
; CHECK-LABEL: _call_inalloca: # @call_inalloca
; CHECK: pushl %ebp
; CHECK: movl %esp, %ebp
Re-commit r269828 "X86: Avoid using _chkstk when lowering WIN_ALLOCA instructions" with an additional fix to make RegAllocFast ignore undef physreg uses. It would previously get confused about the "push %eax" instruction's use of eax. That method for adjusting the stack pointer is used in X86FrameLowering::emitSPUpdate as well, but since that runs after register-allocation, we didn't run into the RegAllocFast issue before. llvm-svn: 269949
2016-05-19 00:10:17 +08:00
; CHECK: movl $8192, %eax
[X86] Put no-op ADJCALLSTACK markers around all dynamic lowerings Summary: These ADJCALLSTACK markers don't generate code, but they keep dynamic alloca code that calls chkstk out of the prologue. This slightly pessimizes inalloca calls by preventing some register copy coalescing, but I can live with that. Reviewers: qcolombet Subscribers: hans, llvm-commits Differential Revision: http://reviews.llvm.org/D15200 llvm-svn: 254645
2015-12-04 04:46:59 +08:00
; CHECK: calll __chkstk
; CHECK: calll _inalloca_params
; CHECK: movl %ebp, %esp
; CHECK: popl %ebp
; CHECK: retl
declare void @inalloca_params(<{ %struct.S }>* inalloca)
[X86] Fix a shrink-wrapping miscompile around __chkstk __chkstk clobbers EAX. If EAX is live across the prologue, then we have to take extra steps to save it. We already had code to do this if EAX was a register parameter. This change adapts it to work when shrink wrapping is used. llvm-svn: 261039
2016-02-17 08:17:33 +08:00
declare i32 @doSomething(i32, i32*)
; In this test case, we force usage of EAX before the prologue, and have to
; compensate before calling __chkstk. It would also be valid for us to avoid
; shrink wrapping in this case.
define x86_fastcallcc i32 @use_eax_before_prologue(i32 inreg %a, i32 inreg %b) {
%tmp = alloca i32, i32 1024, align 4
%tmp2 = icmp slt i32 %a, %b
br i1 %tmp2, label %true, label %false
true:
store i32 %a, i32* %tmp, align 4
%tmp4 = call i32 @doSomething(i32 0, i32* %tmp)
br label %false
false:
%tmp.0 = phi i32 [ %tmp4, %true ], [ %a, %0 ]
ret i32 %tmp.0
}
; CHECK-LABEL: @use_eax_before_prologue@8: # @use_eax_before_prologue
; CHECK: movl %ecx, %eax
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding" Re-enable commit r323991 now that r325931 has been committed to make MachineOperand::isRenamable() check more conservative w.r.t. code changes and opt-in on a per-target basis. llvm-svn: 326208
2018-02-28 00:59:10 +08:00
; CHECK: cmpl %edx, %ecx
[X86] Fix a shrink-wrapping miscompile around __chkstk __chkstk clobbers EAX. If EAX is live across the prologue, then we have to take extra steps to save it. We already had code to do this if EAX was a register parameter. This change adapts it to work when shrink wrapping is used. llvm-svn: 261039
2016-02-17 08:17:33 +08:00
; CHECK: jge LBB1_2
; CHECK: pushl %eax
[X86] Enable call frame optimization ("mov to push") not only for optsize (PR26325) The size savings are significant, and from what I can tell, both ICC and GCC do this. Differential Revision: http://reviews.llvm.org/D18573 llvm-svn: 264966
2016-03-31 07:38:01 +08:00
; CHECK: movl $4092, %eax
[X86] Fix a shrink-wrapping miscompile around __chkstk __chkstk clobbers EAX. If EAX is live across the prologue, then we have to take extra steps to save it. We already had code to do this if EAX was a register parameter. This change adapts it to work when shrink wrapping is used. llvm-svn: 261039
2016-02-17 08:17:33 +08:00
; CHECK: calll __chkstk
[X86] Enable call frame optimization ("mov to push") not only for optsize (PR26325) The size savings are significant, and from what I can tell, both ICC and GCC do this. Differential Revision: http://reviews.llvm.org/D18573 llvm-svn: 264966
2016-03-31 07:38:01 +08:00
; CHECK: movl 4092(%esp), %eax
[X86] Fix a shrink-wrapping miscompile around __chkstk __chkstk clobbers EAX. If EAX is live across the prologue, then we have to take extra steps to save it. We already had code to do this if EAX was a register parameter. This change adapts it to work when shrink wrapping is used. llvm-svn: 261039
2016-02-17 08:17:33 +08:00
; CHECK: calll _doSomething
; CHECK: LBB1_2:
; CHECK: retl