X86InstrInfo: Support immediates that are +1/-1 different in optimizeCompareInstroptimize_compinstr_fix

This is a re-commit of e2c7ee0743592e39274e28dbe0d0c213ba342317 which
was reverted in a2a58d91e82db38fbdf88cc317dcb3753d79d492 and
ea81cea8163a1a0e54df42103ee1c657bbf03791. This includes a fix to
consistently check for EFLAGS being live-out. See phabricator
review.

Original Summary:

This extends `optimizeCompareInstr` to re-use previous comparison
results if the previous comparison was with an immediate that was 1
bigger or smaller. Example:

    CMP x, 13
    ...
    CMP x, 12   ; can be removed if we change the SETg
    SETg ...    ; x > 12  changed to `SETge` (x >= 13) removing CMP

Motivation: This often happens because SelectionDAG canonicalization
tends to add/subtract 1 often when optimizing for fallthrough blocks.
Example for `x > C` the fallthrough optimization switches true/false
blocks with `!(x > C)` --> `x <= C` and canonicalization turns this into
`x < C + 1`.

Differential Revision: https://reviews.llvm.org/D110867

1 files changed, 56 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/peep-test-5.ll b/llvm/test/CodeGen/X86/peep-test-5.ll
new file mode 100644
index 000000000000..2530cf6576b8
--- /dev/null
+++ b/llvm/test/CodeGen/X86/peep-test-5.ll
@@ -0,0 +1,56 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -o - %s -mtriple=x86_64-- | FileCheck %s
+; Example of a decref operation with "immortal" objects.
+; void decref(long* refcount) {
+;  long count = *refcount;
+;  if (count == 1) { free_object() }
+;  else if (count > 1) { *refcount = count - 1; }
+;  else { /* immortal */ }
+; }
+; Resulting assembly should share flags from single CMP instruction for both
+; conditions!
+define void @decref(i32* %p) {
+; CHECK-LABEL: decref:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    movl (%rdi), %eax
+; CHECK-NEXT:    cmpl $1, %eax
+; CHECK-NEXT:    jne .LBB0_2
+; CHECK-NEXT:  # %bb.1: # %bb_free
+; CHECK-NEXT:    callq free_object@PLT
+; CHECK-NEXT:  .LBB0_4: # %end
+; CHECK-NEXT:    popq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
+; CHECK-NEXT:  .LBB0_2: # %bb2
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    jle .LBB0_4
+; CHECK-NEXT:  # %bb.3: # %bb_dec
+; CHECK-NEXT:    decl %eax
+; CHECK-NEXT:    movl %eax, (%rdi)
+; CHECK-NEXT:    popq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
+  %count = load i32, i32* %p, align 4
+  %cmp0 = icmp eq i32 %count, 1
+  br i1 %cmp0, label %bb_free, label %bb2
+
+bb2:
+  %cmp1 = icmp sgt i32 %count, 1
+  br i1 %cmp1, label %bb_dec, label %end
+
+bb_dec:
+  %dec = add nsw i32 %count, -1
+  store i32 %dec, i32* %p, align 4
+  br label %end
+
+bb_free:
+  call void @free_object()
+  br label %end
+
+end:
+  ret void
+}
+
+declare void @free_object()