reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    1
    2
    3
    4
    5
    6
    7
    8
    9
   10
   11
   12
   13
   14
   15
   16
   17
   18
   19
   20
   21
   22
   23
   24
   25
   26
   27
   28
   29
   30
   31
   32
   33
   34
   35
   36
   37
   38
   39
   40
   41
   42
   43
   44
   45
   46
   47
   48
   49
   50
   51
   52
   53
   54
   55
   56
   57
   58
   59
   60
   61
   62
   63
   64
   65
   66
   67
   68
   69
   70
   71
   72
   73
   74
   75
   76
   77
   78
   79
   80
   81
   82
   83
   84
   85
   86
   87
   88
   89
   90
   91
   92
   93
   94
   95
   96
   97
   98
   99
  100
  101
  102
  103
  104
  105
  106
  107
  108
  109
  110
  111
  112
  113
  114
  115
  116
  117
  118
  119
  120
  121
  122
  123
  124
  125
  126
  127
  128
  129
  130
  131
  132
  133
  134
  135
  136
  137
  138
  139
  140
  141
  142
  143
  144
  145
  146
  147
  148
  149
  150
  151
  152
  153
  154
  155
  156
  157
  158
  159
  160
  161
  162
  163
  164
  165
  166
  167
  168
  169
  170
  171
  172
  173
  174
  175
  176
  177
  178
  179
  180
  181
  182
  183
  184
  185
  186
  187
  188
  189
  190
  191
  192
  193
  194
  195
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s

; The fundamental problem: an add separated from other arithmetic by a sign or
; zero extension can't be combined with the later instructions. However, if the
; first add is 'nsw' or 'nuw' respectively, then we can promote the extension
; ahead of that add to allow optimizations.

define i64 @add_nsw_consts(i32 %i) {
; CHECK-LABEL: add_nsw_consts:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movslq %edi, %rax
; CHECK-NEXT:    addq $12, %rax
; CHECK-NEXT:    retq

  %add = add nsw i32 %i, 5
  %ext = sext i32 %add to i64
  %idx = add i64 %ext, 7
  ret i64 %idx
}

; An x86 bonus: If we promote the sext ahead of the 'add nsw',
; we allow LEA formation and eliminate an add instruction.

define i64 @add_nsw_sext_add(i32 %i, i64 %x) {
; CHECK-LABEL: add_nsw_sext_add:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movslq %edi, %rax
; CHECK-NEXT:    leaq 5(%rax,%rsi), %rax
; CHECK-NEXT:    retq

  %add = add nsw i32 %i, 5
  %ext = sext i32 %add to i64
  %idx = add i64 %x, %ext
  ret i64 %idx
}

; Throw in a scale (left shift) because an LEA can do that too.
; Use a negative constant (LEA displacement) to verify that's handled correctly.

define i64 @add_nsw_sext_lsh_add(i32 %i, i64 %x) {
; CHECK-LABEL: add_nsw_sext_lsh_add:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movslq %edi, %rax
; CHECK-NEXT:    leaq -40(%rsi,%rax,8), %rax
; CHECK-NEXT:    retq

  %add = add nsw i32 %i, -5
  %ext = sext i32 %add to i64
  %shl = shl i64 %ext, 3
  %idx = add i64 %x, %shl
  ret i64 %idx
}

; Don't promote the sext if it has no users. The wider add instruction needs an
; extra byte to encode.

define i64 @add_nsw_sext(i32 %i, i64 %x) {
; CHECK-LABEL: add_nsw_sext:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addl $5, %edi
; CHECK-NEXT:    movslq %edi, %rax
; CHECK-NEXT:    retq

  %add = add nsw i32 %i, 5
  %ext = sext i32 %add to i64
  ret i64 %ext
}

; The typical use case: a 64-bit system where an 'int' is used as an index into an array.

define i8* @gep8(i32 %i, i8* %x) {
; CHECK-LABEL: gep8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movslq %edi, %rax
; CHECK-NEXT:    leaq 5(%rax,%rsi), %rax
; CHECK-NEXT:    retq

  %add = add nsw i32 %i, 5
  %ext = sext i32 %add to i64
  %idx = getelementptr i8, i8* %x, i64 %ext
  ret i8* %idx
}

define i16* @gep16(i32 %i, i16* %x) {
; CHECK-LABEL: gep16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movslq %edi, %rax
; CHECK-NEXT:    leaq -10(%rsi,%rax,2), %rax
; CHECK-NEXT:    retq

  %add = add nsw i32 %i, -5
  %ext = sext i32 %add to i64
  %idx = getelementptr i16, i16* %x, i64 %ext
  ret i16* %idx
}

define i32* @gep32(i32 %i, i32* %x) {
; CHECK-LABEL: gep32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movslq %edi, %rax
; CHECK-NEXT:    leaq 20(%rsi,%rax,4), %rax
; CHECK-NEXT:    retq

  %add = add nsw i32 %i, 5
  %ext = sext i32 %add to i64
  %idx = getelementptr i32, i32* %x, i64 %ext
  ret i32* %idx
}

define i64* @gep64(i32 %i, i64* %x) {
; CHECK-LABEL: gep64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movslq %edi, %rax
; CHECK-NEXT:    leaq -40(%rsi,%rax,8), %rax
; CHECK-NEXT:    retq

  %add = add nsw i32 %i, -5
  %ext = sext i32 %add to i64
  %idx = getelementptr i64, i64* %x, i64 %ext
  ret i64* %idx
}

; LEA can't scale by 16, but the adds can still be combined into an LEA.

define i128* @gep128(i32 %i, i128* %x) {
; CHECK-LABEL: gep128:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movslq %edi, %rax
; CHECK-NEXT:    shlq $4, %rax
; CHECK-NEXT:    leaq 80(%rax,%rsi), %rax
; CHECK-NEXT:    retq

  %add = add nsw i32 %i, 5
  %ext = sext i32 %add to i64
  %idx = getelementptr i128, i128* %x, i64 %ext
  ret i128* %idx
}

; A bigger win can be achieved when there is more than one use of the
; sign extended value. In this case, we can eliminate sign extension
; instructions plus use more efficient addressing modes for memory ops.

define void @PR20134(i32* %a, i32 %i) {
; CHECK-LABEL: PR20134:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movslq %esi, %rax
; CHECK-NEXT:    movl 4(%rdi,%rax,4), %ecx
; CHECK-NEXT:    addl 8(%rdi,%rax,4), %ecx
; CHECK-NEXT:    movl %ecx, (%rdi,%rax,4)
; CHECK-NEXT:    retq

  %add1 = add nsw i32 %i, 1
  %idx1 = sext i32 %add1 to i64
  %gep1 = getelementptr i32, i32* %a, i64 %idx1
  %load1 = load i32, i32* %gep1, align 4

  %add2 = add nsw i32 %i, 2
  %idx2 = sext i32 %add2 to i64
  %gep2 = getelementptr i32, i32* %a, i64 %idx2
  %load2 = load i32, i32* %gep2, align 4

  %add3 = add i32 %load1, %load2
  %idx3 = sext i32 %i to i64
  %gep3 = getelementptr i32, i32* %a, i64 %idx3
  store i32 %add3, i32* %gep3, align 4
  ret void
}

; The same as @PR20134 but sign extension is replaced with zero extension
define void @PR20134_zext(i32* %a, i32 %i) {
; CHECK-LABEL: PR20134_zext:
; CHECK:       # %bb.0:
; CHECK-NEXT:    movl %esi, %eax
; CHECK-NEXT:    movl 4(%rdi,%rax,4), %ecx
; CHECK-NEXT:    addl 8(%rdi,%rax,4), %ecx
; CHECK-NEXT:    movl %ecx, (%rdi,%rax,4)
; CHECK-NEXT:    retq

  %add1 = add nuw i32 %i, 1
  %idx1 = zext i32 %add1 to i64
  %gep1 = getelementptr i32, i32* %a, i64 %idx1
  %load1 = load i32, i32* %gep1, align 4

  %add2 = add nuw i32 %i, 2
  %idx2 = zext i32 %add2 to i64
  %gep2 = getelementptr i32, i32* %a, i64 %idx2
  %load2 = load i32, i32* %gep2, align 4

  %add3 = add i32 %load1, %load2
  %idx3 = zext i32 %i to i64
  %gep3 = getelementptr i32, i32* %a, i64 %idx3
  store i32 %add3, i32* %gep3, align 4
  ret void
}