mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-27 13:30:05 +00:00
db1e51359d
Let's try this again...
This reverts r219432, plus a bug fix.
Description of the bug in r219432 (by Nick):
The bug was using AllPositive to break out of the loop; if the loop break
condition i != e is changed to i != e && AllPositive then the
test_modulo_analysis_with_global test I've added will fail as the Modulo will
be calculated incorrectly (as the last loop iteration is skipped, so Modulo
isn't updated with its Scale).
Nick also adds this comment:
ComputeSignBit is safe to use in loops as it takes into account phi nodes, and
the == EK_ZeroEx check is safe in loops as, no matter how the variable changes
between iterations, zero-extensions will always guarantee a zero sign bit. The
isValueEqualInPotentialCycles check is therefore definitely not needed as all
the variable analysis holds no matter how the variables change between loop
iterations.
And this patch also adds another enhancement to GetLinearExpression - basically
to convert ConstantInts to Offsets (see test_const_eval and
test_const_eval_scaled for the situations this improves).
Original commit message:
This reverts r218944, which reverted r218714, plus a bug fix.
Description of the bug in r218714 (by Nick):
The original patch forgot to check if the Scale in VariableGEPIndex flipped the
sign of the variable. The BasicAA pass iterates over the instructions in the
order they appear in the function, and so BasicAliasAnalysis::aliasGEP is
called with the variable it first comes across as parameter GEP1. Adding a
%reorder label puts the definition of %a after %b so aliasGEP is called with %b
as the first parameter and %a as the second. aliasGEP later calculates that %a
== %b + 1 - %idxprom where %idxprom >= 0 (if %a was passed as the first
parameter it would calculate %b == %a - 1 + %idxprom where %idxprom >= 0) -
ignoring that %idxprom is scaled by -1 here lead the patch to incorrectly
conclude that %a > %b.
Revised patch by Nick White, thanks! Thanks to Lang to isolating the bug.
Slightly modified by me to add an early exit from the loop and avoid
unnecessary, but expensive, function calls.
Original commit message:
Two related things:
1. Fixes a bug when calculating the offset in GetLinearExpression. The code
previously used zext to extend the offset, so negative offsets were converted
to large positive ones.
2. Enhance aliasGEP to deduce that, if the difference between two GEP
allocations is positive and all the variables that govern the offset are also
positive (i.e. the offset is strictly after the higher base pointer), then
locations that fit in the gap between the two base pointers are NoAlias.
Patch by Nick White!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221876 91177308-0d34-0410-b5e6-96231b3b80d8
210 lines
6.2 KiB
LLVM
210 lines
6.2 KiB
LLVM
; RUN: opt < %s -basicaa -aa-eval -print-all-alias-modref-info -disable-output 2>&1 | FileCheck %s
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
; CHECK-LABEL: test_with_zext
|
|
; CHECK: NoAlias: i8* %a, i8* %b
|
|
|
|
define void @test_with_zext() {
|
|
%1 = tail call i8* @malloc(i64 120)
|
|
%a = getelementptr inbounds i8* %1, i64 8
|
|
%2 = getelementptr inbounds i8* %1, i64 16
|
|
%3 = zext i32 3 to i64
|
|
%b = getelementptr inbounds i8* %2, i64 %3
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_with_lshr
|
|
; CHECK: NoAlias: i8* %a, i8* %b
|
|
|
|
define void @test_with_lshr(i64 %i) {
|
|
%1 = tail call i8* @malloc(i64 120)
|
|
%a = getelementptr inbounds i8* %1, i64 8
|
|
%2 = getelementptr inbounds i8* %1, i64 16
|
|
%3 = lshr i64 %i, 2
|
|
%b = getelementptr inbounds i8* %2, i64 %3
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_with_a_loop
|
|
; CHECK: NoAlias: i8* %a, i8* %b
|
|
|
|
define void @test_with_a_loop(i8* %mem) {
|
|
br label %for.loop
|
|
|
|
for.loop:
|
|
%i = phi i32 [ 0, %0 ], [ %i.plus1, %for.loop ]
|
|
%a = getelementptr inbounds i8* %mem, i64 8
|
|
%a.plus1 = getelementptr inbounds i8* %mem, i64 16
|
|
%i.64 = zext i32 %i to i64
|
|
%b = getelementptr inbounds i8* %a.plus1, i64 %i.64
|
|
%i.plus1 = add nuw nsw i32 %i, 1
|
|
%cmp = icmp eq i32 %i.plus1, 10
|
|
br i1 %cmp, label %for.loop.exit, label %for.loop
|
|
|
|
for.loop.exit:
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_with_varying_base_pointer_in_loop
|
|
; CHECK: NoAlias: i8* %a, i8* %b
|
|
|
|
define void @test_with_varying_base_pointer_in_loop(i8* %mem.orig) {
|
|
br label %for.loop
|
|
|
|
for.loop:
|
|
%mem = phi i8* [ %mem.orig, %0 ], [ %mem.plus1, %for.loop ]
|
|
%i = phi i32 [ 0, %0 ], [ %i.plus1, %for.loop ]
|
|
%a = getelementptr inbounds i8* %mem, i64 8
|
|
%a.plus1 = getelementptr inbounds i8* %mem, i64 16
|
|
%i.64 = zext i32 %i to i64
|
|
%b = getelementptr inbounds i8* %a.plus1, i64 %i.64
|
|
%i.plus1 = add nuw nsw i32 %i, 1
|
|
%mem.plus1 = getelementptr inbounds i8* %mem, i64 8
|
|
%cmp = icmp eq i32 %i.plus1, 10
|
|
br i1 %cmp, label %for.loop.exit, label %for.loop
|
|
|
|
for.loop.exit:
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_sign_extension
|
|
; CHECK: PartialAlias: i64* %b.i64, i8* %a
|
|
|
|
define void @test_sign_extension(i32 %p) {
|
|
%1 = tail call i8* @malloc(i64 120)
|
|
%p.64 = zext i32 %p to i64
|
|
%a = getelementptr inbounds i8* %1, i64 %p.64
|
|
%p.minus1 = add i32 %p, -1
|
|
%p.minus1.64 = zext i32 %p.minus1 to i64
|
|
%b.i8 = getelementptr inbounds i8* %1, i64 %p.minus1.64
|
|
%b.i64 = bitcast i8* %b.i8 to i64*
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_fe_tools
|
|
; CHECK: PartialAlias: i32* %a, i32* %b
|
|
|
|
define void @test_fe_tools([8 x i32]* %values) {
|
|
br label %reorder
|
|
|
|
for.loop:
|
|
%i = phi i32 [ 0, %reorder ], [ %i.next, %for.loop ]
|
|
%idxprom = zext i32 %i to i64
|
|
%b = getelementptr inbounds [8 x i32]* %values, i64 0, i64 %idxprom
|
|
%i.next = add nuw nsw i32 %i, 1
|
|
%1 = icmp eq i32 %i.next, 10
|
|
br i1 %1, label %for.loop.exit, label %for.loop
|
|
|
|
reorder:
|
|
%a = getelementptr inbounds [8 x i32]* %values, i64 0, i64 1
|
|
br label %for.loop
|
|
|
|
for.loop.exit:
|
|
ret void
|
|
}
|
|
|
|
@b = global i32 0, align 4
|
|
@d = global i32 0, align 4
|
|
|
|
; CHECK-LABEL: test_spec2006
|
|
; CHECK: PartialAlias: i32** %x, i32** %y
|
|
|
|
define void @test_spec2006() {
|
|
%h = alloca [1 x [2 x i32*]], align 16
|
|
%d.val = load i32* @d, align 4
|
|
%d.promoted = sext i32 %d.val to i64
|
|
%1 = icmp slt i32 %d.val, 2
|
|
br i1 %1, label %.lr.ph, label %3
|
|
|
|
.lr.ph: ; preds = %0
|
|
br label %2
|
|
|
|
; <label>:2 ; preds = %.lr.ph, %2
|
|
%i = phi i32 [ %d.val, %.lr.ph ], [ %i.plus1, %2 ]
|
|
%i.promoted = sext i32 %i to i64
|
|
%x = getelementptr inbounds [1 x [2 x i32*]]* %h, i64 0, i64 %d.promoted, i64 %i.promoted
|
|
%i.plus1 = add nsw i32 %i, 1
|
|
%cmp = icmp slt i32 %i.plus1, 2
|
|
br i1 %cmp, label %2, label %3
|
|
|
|
; <label>:3 ; preds = %._crit_edge, %0
|
|
%y = getelementptr inbounds [1 x [2 x i32*]]* %h, i64 0, i64 0, i64 1
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_modulo_analysis_easy_case
|
|
; CHECK: NoAlias: i32** %x, i32** %y
|
|
|
|
define void @test_modulo_analysis_easy_case(i64 %i) {
|
|
%h = alloca [1 x [2 x i32*]], align 16
|
|
%x = getelementptr inbounds [1 x [2 x i32*]]* %h, i64 0, i64 %i, i64 0
|
|
%y = getelementptr inbounds [1 x [2 x i32*]]* %h, i64 0, i64 0, i64 1
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_modulo_analysis_in_loop
|
|
; CHECK: NoAlias: i32** %x, i32** %y
|
|
|
|
define void @test_modulo_analysis_in_loop() {
|
|
%h = alloca [1 x [2 x i32*]], align 16
|
|
br label %for.loop
|
|
|
|
for.loop:
|
|
%i = phi i32 [ 0, %0 ], [ %i.plus1, %for.loop ]
|
|
%i.promoted = sext i32 %i to i64
|
|
%x = getelementptr inbounds [1 x [2 x i32*]]* %h, i64 0, i64 %i.promoted, i64 0
|
|
%y = getelementptr inbounds [1 x [2 x i32*]]* %h, i64 0, i64 0, i64 1
|
|
%i.plus1 = add nsw i32 %i, 1
|
|
%cmp = icmp slt i32 %i.plus1, 2
|
|
br i1 %cmp, label %for.loop, label %for.loop.exit
|
|
|
|
for.loop.exit:
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_modulo_analysis_with_global
|
|
; CHECK: PartialAlias: i32** %x, i32** %y
|
|
|
|
define void @test_modulo_analysis_with_global() {
|
|
%h = alloca [1 x [2 x i32*]], align 16
|
|
%b = load i32* @b, align 4
|
|
%b.promoted = sext i32 %b to i64
|
|
br label %for.loop
|
|
|
|
for.loop:
|
|
%i = phi i32 [ 0, %0 ], [ %i.plus1, %for.loop ]
|
|
%i.promoted = sext i32 %i to i64
|
|
%x = getelementptr inbounds [1 x [2 x i32*]]* %h, i64 0, i64 %i.promoted, i64 %b.promoted
|
|
%y = getelementptr inbounds [1 x [2 x i32*]]* %h, i64 0, i64 0, i64 1
|
|
%i.plus1 = add nsw i32 %i, 1
|
|
%cmp = icmp slt i32 %i.plus1, 2
|
|
br i1 %cmp, label %for.loop, label %for.loop.exit
|
|
|
|
for.loop.exit:
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_const_eval
|
|
; CHECK: NoAlias: i8* %a, i8* %b
|
|
define void @test_const_eval(i8* %ptr, i64 %offset) {
|
|
%a = getelementptr inbounds i8* %ptr, i64 %offset
|
|
%a.dup = getelementptr inbounds i8* %ptr, i64 %offset
|
|
%three = zext i32 3 to i64
|
|
%b = getelementptr inbounds i8* %a.dup, i64 %three
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: test_const_eval_scaled
|
|
; CHECK: MustAlias: i8* %a, i8* %b
|
|
define void @test_const_eval_scaled(i8* %ptr) {
|
|
%three = zext i32 3 to i64
|
|
%six = mul i64 %three, 2
|
|
%a = getelementptr inbounds i8* %ptr, i64 %six
|
|
%b = getelementptr inbounds i8* %ptr, i64 6
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: nounwind
|
|
declare noalias i8* @malloc(i64)
|