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/win32-seh-catchpad-realign.ll

78 lines
2.2 KiB
LLVM
Raw Normal View History

Implemented stack symbol table ordering/packing optimization to improve data locality and code size from SP/FP offset encoding. Differential Revision: http://reviews.llvm.org/D15393 llvm-svn: 260917
2016-02-16 07:44:13 +08:00
; RUN: llc -stack-symbol-ordering=0 < %s | FileCheck %s
[WinEH] Relax assertion in the presence of stack realignment The code is correct as is, but we should test it. llvm-svn: 249715
2015-10-09 02:41:52 +08:00
; The aligned alloca means that we have to realign the stack, which forces the
; use of ESI to address local variables.
target datalayout = "e-m:x-p:32:32-i64:64-f80:32-n8:16:32-a:0:32-S32"
target triple = "i686--windows-msvc"
; Function Attrs: nounwind
define void @realigned_try() personality i8* bitcast (i32 (...)* @_except_handler3 to i8*) {
entry:
%x = alloca [4 x i32], align 16
%arrayidx = getelementptr inbounds [4 x i32], [4 x i32]* %x, i32 0, i32 0
invoke void @useit(i32* %arrayidx)
to label %__try.cont unwind label %catch.dispatch
catch.dispatch: ; preds = %entry
[IR] Reformulate LLVM's EH funclet IR While we have successfully implemented a funclet-oriented EH scheme on top of LLVM IR, our scheme has some notable deficiencies: - catchendpad and cleanupendpad are necessary in the current design but they are difficult to explain to others, even to seasoned LLVM experts. - catchendpad and cleanupendpad are optimization barriers. They cannot be split and force all potentially throwing call-sites to be invokes. This has a noticable effect on the quality of our code generation. - catchpad, while similar in some aspects to invoke, is fairly awkward. It is unsplittable, starts a funclet, and has control flow to other funclets. - The nesting relationship between funclets is currently a property of control flow edges. Because of this, we are forced to carefully analyze the flow graph to see if there might potentially exist illegal nesting among funclets. While we have logic to clone funclets when they are illegally nested, it would be nicer if we had a representation which forbade them upfront. Let's clean this up a bit by doing the following: - Instead, make catchpad more like cleanuppad and landingpad: no control flow, just a bunch of simple operands; catchpad would be splittable. - Introduce catchswitch, a control flow instruction designed to model the constraints of funclet oriented EH. - Make funclet scoping explicit by having funclet instructions consume the token produced by the funclet which contains them. - Remove catchendpad and cleanupendpad. Their presence can be inferred implicitly using coloring information. N.B. The state numbering code for the CLR has been updated but the veracity of it's output cannot be spoken for. An expert should take a look to make sure the results are reasonable. Reviewers: rnk, JosephTremoulet, andrew.w.kaylor Differential Revision: http://reviews.llvm.org/D15139 llvm-svn: 255422
2015-12-12 13:38:55 +08:00
%cs1 = catchswitch within none [label %__except.ret] unwind to caller
[WinEH] Relax assertion in the presence of stack realignment The code is correct as is, but we should test it. llvm-svn: 249715
2015-10-09 02:41:52 +08:00
__except.ret: ; preds = %catch.dispatch
[IR] Reformulate LLVM's EH funclet IR While we have successfully implemented a funclet-oriented EH scheme on top of LLVM IR, our scheme has some notable deficiencies: - catchendpad and cleanupendpad are necessary in the current design but they are difficult to explain to others, even to seasoned LLVM experts. - catchendpad and cleanupendpad are optimization barriers. They cannot be split and force all potentially throwing call-sites to be invokes. This has a noticable effect on the quality of our code generation. - catchpad, while similar in some aspects to invoke, is fairly awkward. It is unsplittable, starts a funclet, and has control flow to other funclets. - The nesting relationship between funclets is currently a property of control flow edges. Because of this, we are forced to carefully analyze the flow graph to see if there might potentially exist illegal nesting among funclets. While we have logic to clone funclets when they are illegally nested, it would be nicer if we had a representation which forbade them upfront. Let's clean this up a bit by doing the following: - Instead, make catchpad more like cleanuppad and landingpad: no control flow, just a bunch of simple operands; catchpad would be splittable. - Introduce catchswitch, a control flow instruction designed to model the constraints of funclet oriented EH. - Make funclet scoping explicit by having funclet instructions consume the token produced by the funclet which contains them. - Remove catchendpad and cleanupendpad. Their presence can be inferred implicitly using coloring information. N.B. The state numbering code for the CLR has been updated but the veracity of it's output cannot be spoken for. An expert should take a look to make sure the results are reasonable. Reviewers: rnk, JosephTremoulet, andrew.w.kaylor Differential Revision: http://reviews.llvm.org/D15139 llvm-svn: 255422
2015-12-12 13:38:55 +08:00
%pad = catchpad within %cs1 [i8* bitcast (i32 ()* @"\01?filt$0@0@realigned_try@@" to i8*)]
catchret from %pad to label %__try.cont
[WinEH] Relax assertion in the presence of stack realignment The code is correct as is, but we should test it. llvm-svn: 249715
2015-10-09 02:41:52 +08:00
__try.cont: ; preds = %entry, %__except.ret
ret void
}
; Function Attrs: nounwind argmemonly
; Function Attrs: nounwind
define internal i32 @"\01?filt$0@0@realigned_try@@"() {
entry:
ret i32 1
}
declare void @useit(i32*)
declare i32 @_except_handler3(...)
; CHECK-LABEL: _realigned_try:
; Prologue
; CHECK: pushl %ebp
; CHECK: movl %esp, %ebp
; CHECK: pushl %ebx
; CHECK: pushl %edi
; CHECK: pushl %esi
; CHECK: andl $-16, %esp
; CHECK: subl $64, %esp
; CHECK: movl %esp, %esi
; Spill EBP
; CHECK: movl %ebp, 12(%esi)
; Spill ESP
; CHECK: movl %esp, 36(%esi)
; The state is stored at ESI+56, the end of the node is ESI+60.
; CHECK: movl $-1, 56(%esi)
;
; __try
; CHECK: calll _useit
;
; Epilogue
[WinEH] Don't emit CATCHRET from visitCatchPad Instead, emit a CATCHPAD node which will get selected to a target specific sequence. llvm-svn: 252528
2015-11-10 07:07:48 +08:00
; CHECK: LBB0_2: # %__try.cont
[WinEH] Relax assertion in the presence of stack realignment The code is correct as is, but we should test it. llvm-svn: 249715
2015-10-09 02:41:52 +08:00
; CHECK: leal -12(%ebp), %esp
; CHECK: popl %esi
; CHECK: popl %edi
; CHECK: popl %ebx
; CHECK: popl %ebp
; CHECK: retl
;
[IR] Reformulate LLVM's EH funclet IR While we have successfully implemented a funclet-oriented EH scheme on top of LLVM IR, our scheme has some notable deficiencies: - catchendpad and cleanupendpad are necessary in the current design but they are difficult to explain to others, even to seasoned LLVM experts. - catchendpad and cleanupendpad are optimization barriers. They cannot be split and force all potentially throwing call-sites to be invokes. This has a noticable effect on the quality of our code generation. - catchpad, while similar in some aspects to invoke, is fairly awkward. It is unsplittable, starts a funclet, and has control flow to other funclets. - The nesting relationship between funclets is currently a property of control flow edges. Because of this, we are forced to carefully analyze the flow graph to see if there might potentially exist illegal nesting among funclets. While we have logic to clone funclets when they are illegally nested, it would be nicer if we had a representation which forbade them upfront. Let's clean this up a bit by doing the following: - Instead, make catchpad more like cleanuppad and landingpad: no control flow, just a bunch of simple operands; catchpad would be splittable. - Introduce catchswitch, a control flow instruction designed to model the constraints of funclet oriented EH. - Make funclet scoping explicit by having funclet instructions consume the token produced by the funclet which contains them. - Remove catchendpad and cleanupendpad. Their presence can be inferred implicitly using coloring information. N.B. The state numbering code for the CLR has been updated but the veracity of it's output cannot be spoken for. An expert should take a look to make sure the results are reasonable. Reviewers: rnk, JosephTremoulet, andrew.w.kaylor Differential Revision: http://reviews.llvm.org/D15139 llvm-svn: 255422
2015-12-12 13:38:55 +08:00
; CHECK: LBB0_1: # %__except.ret
[WinEH] Relax assertion in the presence of stack realignment The code is correct as is, but we should test it. llvm-svn: 249715
2015-10-09 02:41:52 +08:00
; Restore ESP
; CHECK: movl -24(%ebp), %esp
; Recompute ESI by subtracting 60 from the end of the registration node.
; CHECK: leal -60(%ebp), %esi
; Restore EBP
; CHECK: movl 12(%esi), %ebp
; Rejoin normal control flow
[WinEH] Don't emit CATCHRET from visitCatchPad Instead, emit a CATCHPAD node which will get selected to a target specific sequence. llvm-svn: 252528
2015-11-10 07:07:48 +08:00
; CHECK: jmp LBB0_2