1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 04:32:44 +01:00
llvm-mirror/test/CodeGen/X86/lea-opt-cse3.ll
Petar Jovanovic 9686e666ef Correct dwarf unwind information in function epilogue
This patch aims to provide correct dwarf unwind information in function
epilogue for X86.
It consists of two parts. The first part inserts CFI instructions that set
appropriate cfa offset and cfa register in emitEpilogue() in
X86FrameLowering. This part is X86 specific.

The second part is platform independent and ensures that:

* CFI instructions do not affect code generation (they are not counted as
  instructions when tail duplicating or tail merging)
* Unwind information remains correct when a function is modified by
  different passes. This is done in a late pass by analyzing information
  about cfa offset and cfa register in BBs and inserting additional CFI
  directives where necessary.

Added CFIInstrInserter pass:

* analyzes each basic block to determine cfa offset and register are valid
  at its entry and exit
* verifies that outgoing cfa offset and register of predecessor blocks match
  incoming values of their successors
* inserts additional CFI directives at basic block beginning to correct the
  rule for calculating CFA

Having CFI instructions in function epilogue can cause incorrect CFA
calculation rule for some basic blocks. This can happen if, due to basic
block reordering, or the existence of multiple epilogue blocks, some of the
blocks have wrong cfa offset and register values set by the epilogue block
above them.
CFIInstrInserter is currently run only on X86, but can be used by any target
that implements support for adding CFI instructions in epilogue.

Patch by Violeta Vukobrat.

Differential Revision: https://reviews.llvm.org/D42848

llvm-svn: 330706
2018-04-24 10:32:08 +00:00

165 lines
4.9 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s -check-prefix=X64
; RUN: llc < %s -mtriple=i686-unknown | FileCheck %s -check-prefix=X86
define i32 @foo(i32 %a, i32 %b) local_unnamed_addr #0 {
; X64-LABEL: foo:
; X64: # %bb.0: # %entry
; X64-NEXT: # kill: def $esi killed $esi def $rsi
; X64-NEXT: # kill: def $edi killed $edi def $rdi
; X64-NEXT: leal 4(%rdi,%rsi,2), %ecx
; X64-NEXT: leal 4(%rdi,%rsi,4), %eax
; X64-NEXT: imull %ecx, %eax
; X64-NEXT: retq
;
; X86-LABEL: foo:
; X86: # %bb.0: # %entry
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: leal 4(%ecx,%eax,2), %edx
; X86-NEXT: leal 4(%ecx,%eax,4), %eax
; X86-NEXT: imull %edx, %eax
; X86-NEXT: retl
entry:
%mul = shl i32 %b, 1
%add = add i32 %a, 4
%add1 = add i32 %add, %mul
%mul2 = shl i32 %b, 2
%add4 = add i32 %add, %mul2
%mul5 = mul nsw i32 %add1, %add4
ret i32 %mul5
}
define i32 @foo1(i32 %a, i32 %b) local_unnamed_addr #0 {
; X64-LABEL: foo1:
; X64: # %bb.0: # %entry
; X64-NEXT: # kill: def $esi killed $esi def $rsi
; X64-NEXT: # kill: def $edi killed $edi def $rdi
; X64-NEXT: leal 4(%rdi,%rsi,4), %ecx
; X64-NEXT: leal 4(%rdi,%rsi,8), %eax
; X64-NEXT: imull %ecx, %eax
; X64-NEXT: retq
;
; X86-LABEL: foo1:
; X86: # %bb.0: # %entry
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: leal 4(%ecx,%eax,4), %edx
; X86-NEXT: leal 4(%ecx,%eax,8), %eax
; X86-NEXT: imull %edx, %eax
; X86-NEXT: retl
entry:
%mul = shl i32 %b, 2
%add = add i32 %a, 4
%add1 = add i32 %add, %mul
%mul2 = shl i32 %b, 3
%add4 = add i32 %add, %mul2
%mul5 = mul nsw i32 %add1, %add4
ret i32 %mul5
}
define i32 @foo1_mult_basic_blocks(i32 %a, i32 %b) local_unnamed_addr #0 {
; X64-LABEL: foo1_mult_basic_blocks:
; X64: # %bb.0: # %entry
; X64-NEXT: # kill: def $esi killed $esi def $rsi
; X64-NEXT: # kill: def $edi killed $edi def $rdi
; X64-NEXT: leal 4(%rdi,%rsi,4), %ecx
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpl $10, %ecx
; X64-NEXT: je .LBB2_2
; X64-NEXT: # %bb.1: # %mid
; X64-NEXT: leal 4(%rdi,%rsi,8), %eax
; X64-NEXT: imull %eax, %ecx
; X64-NEXT: movl %ecx, %eax
; X64-NEXT: .LBB2_2: # %exit
; X64-NEXT: retq
;
; X86-LABEL: foo1_mult_basic_blocks:
; X86: # %bb.0: # %entry
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: leal 4(%esi,%edx,4), %ecx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl $10, %ecx
; X86-NEXT: je .LBB2_2
; X86-NEXT: # %bb.1: # %mid
; X86-NEXT: leal 4(%esi,%edx,8), %eax
; X86-NEXT: imull %eax, %ecx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: .LBB2_2: # %exit
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl
entry:
%mul = shl i32 %b, 2
%add = add i32 %a, 4
%add1 = add i32 %add, %mul
%cmp = icmp ne i32 %add1 , 10
br i1 %cmp , label %mid , label %exit
mid:
%addn = add i32 %a , 4
%mul2 = shl i32 %b, 3
%add4 = add i32 %addn, %mul2
%mul5 = mul nsw i32 %add1, %add4
br label %exit
exit:
%retmul = phi i32 [%mul5 , %mid] , [0 , %entry]
ret i32 %retmul
}
define i32 @foo1_mult_basic_blocks_illegal_scale(i32 %a, i32 %b) local_unnamed_addr #0 {
; X64-LABEL: foo1_mult_basic_blocks_illegal_scale:
; X64: # %bb.0: # %entry
; X64-NEXT: # kill: def $esi killed $esi def $rsi
; X64-NEXT: # kill: def $edi killed $edi def $rdi
; X64-NEXT: leal 4(%rdi,%rsi,2), %ecx
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: cmpl $10, %ecx
; X64-NEXT: je .LBB3_2
; X64-NEXT: # %bb.1: # %mid
; X64-NEXT: leal 4(%rdi,%rsi,8), %eax
; X64-NEXT: imull %eax, %ecx
; X64-NEXT: movl %ecx, %eax
; X64-NEXT: .LBB3_2: # %exit
; X64-NEXT: retq
;
; X86-LABEL: foo1_mult_basic_blocks_illegal_scale:
; X86: # %bb.0: # %entry
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: leal 4(%esi,%edx,2), %ecx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: cmpl $10, %ecx
; X86-NEXT: je .LBB3_2
; X86-NEXT: # %bb.1: # %mid
; X86-NEXT: leal 4(%esi,%edx,8), %eax
; X86-NEXT: imull %eax, %ecx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: .LBB3_2: # %exit
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl
entry:
%mul = shl i32 %b, 1
%add = add i32 %a, 4
%add1 = add i32 %add, %mul
%cmp = icmp ne i32 %add1 , 10
br i1 %cmp, label %mid , label %exit
mid:
%addn = add i32 %a , 4
%mul2 = shl i32 %b, 3
%add4 = add i32 %addn, %mul2
%mul5 = mul nsw i32 %add1, %add4
br label %exit
exit:
%retmul = phi i32 [%mul5 , %mid] , [0 , %entry]
ret i32 %retmul
}