mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-10-11 23:25:15 +00:00
ad43499fc4
Patch from Preston Briggs <preston.briggs@gmail.com>.
This is an updated version of the dependence-analysis patch, including an MIV
test based on Banerjee's inequalities.
It's a fairly complete implementation of the paper
Practical Dependence Testing
Gina Goff, Ken Kennedy, and Chau-Wen Tseng
PLDI 1991
It cannot yet propagate constraints between coupled RDIV subscripts (discussed
in Section 5.3.2 of the paper).
It's organized as a FunctionPass with a single entry point that supports testing
for dependence between two instructions in a function. If there's no dependence,
it returns null. If there's a dependence, it returns a pointer to a Dependence
which can be queried about details (what kind of dependence, is it loop
independent, direction and distance vector entries, etc). I haven't included
every imaginable feature, but there's a good selection that should be adequate
for supporting many loop transformations. Of course, it can be extended as
necessary.
Included in the patch file are many test cases, commented with C code showing
the loops and array references.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165708 91177308-0d34-0410-b5e6-96231b3b80d8
429 lines
14 KiB
LLVM
429 lines
14 KiB
LLVM
; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
|
|
|
|
; ModuleID = 'ExactSIV.bc'
|
|
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-apple-macosx10.6.0"
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 10; i++) {
|
|
;; A[i + 10] = ...
|
|
;; ... = A[2*i + 1];
|
|
|
|
define void @exact0(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%add = add i64 %i.02, 10
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %add
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%mul = shl i64 %i.02, 1
|
|
%add13 = or i64 %mul, 1
|
|
%arrayidx2 = getelementptr inbounds i32* %A, i64 %add13
|
|
%0 = load i32* %arrayidx2, align 4
|
|
; CHECK: da analyze - flow [<=|<]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 10
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 10; i++) {
|
|
;; A[4*i + 10] = ...
|
|
;; ... = A[2*i + 1];
|
|
|
|
define void @exact1(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = shl i64 %i.02, 2
|
|
%add = add i64 %mul, 10
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %add
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%mul1 = shl i64 %i.02, 1
|
|
%add23 = or i64 %mul1, 1
|
|
%arrayidx3 = getelementptr inbounds i32* %A, i64 %add23
|
|
%0 = load i32* %arrayidx3, align 4
|
|
; CHECK: da analyze - none!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 10
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 10; i++) {
|
|
;; A[6*i] = ...
|
|
;; ... = A[i + 60];
|
|
|
|
define void @exact2(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, 6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%add = add i64 %i.02, 60
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %add
|
|
%0 = load i32* %arrayidx1, align 4
|
|
; CHECK: da analyze - none!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 10
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i <= 10; i++) {
|
|
;; A[6*i] = ...
|
|
;; ... = A[i + 60];
|
|
|
|
define void @exact3(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, 6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%add = add i64 %i.02, 60
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %add
|
|
%0 = load i32* %arrayidx1, align 4
|
|
; CHECK: da analyze - flow [>]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 11
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 12; i++) {
|
|
;; A[6*i] = ...
|
|
;; ... = A[i + 60];
|
|
|
|
define void @exact4(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, 6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%add = add i64 %i.02, 60
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %add
|
|
%0 = load i32* %arrayidx1, align 4
|
|
; CHECK: da analyze - flow [>]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 12
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i <= 12; i++) {
|
|
;; A[6*i] = ...
|
|
;; ... = A[i + 60];
|
|
|
|
define void @exact5(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, 6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%add = add i64 %i.02, 60
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %add
|
|
%0 = load i32* %arrayidx1, align 4
|
|
; CHECK: da analyze - flow [=>|<]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 13
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 18; i++) {
|
|
;; A[6*i] = ...
|
|
;; ... = A[i + 60];
|
|
|
|
define void @exact6(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, 6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%add = add i64 %i.02, 60
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %add
|
|
%0 = load i32* %arrayidx1, align 4
|
|
; CHECK: da analyze - flow [=>|<]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 18
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i <= 18; i++) {
|
|
;; A[6*i] = ...
|
|
;; ... = A[i + 60];
|
|
|
|
define void @exact7(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, 6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%add = add i64 %i.02, 60
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %add
|
|
%0 = load i32* %arrayidx1, align 4
|
|
; CHECK: da analyze - flow [*|<]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 19
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 10; i++) {
|
|
;; A[-6*i] = ...
|
|
;; ... = A[-i - 60];
|
|
|
|
define void @exact8(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, -6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%sub1 = sub i64 -60, %i.02
|
|
%arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
|
|
%0 = load i32* %arrayidx2, align 4
|
|
; CHECK: da analyze - none!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 10
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i <= 10; i++) {
|
|
;; A[-6*i] = ...
|
|
;; ... = A[-i - 60];
|
|
|
|
define void @exact9(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, -6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%sub1 = sub i64 -60, %i.02
|
|
%arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
|
|
%0 = load i32* %arrayidx2, align 4
|
|
; CHECK: da analyze - flow [>]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 11
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 12; i++) {
|
|
;; A[-6*i] = ...
|
|
;; ... = A[-i - 60];
|
|
|
|
define void @exact10(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, -6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%sub1 = sub i64 -60, %i.02
|
|
%arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
|
|
%0 = load i32* %arrayidx2, align 4
|
|
; CHECK: da analyze - flow [>]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 12
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i <= 12; i++) {
|
|
;; A[-6*i] = ...
|
|
;; ... = A[-i - 60];
|
|
|
|
define void @exact11(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, -6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%sub1 = sub i64 -60, %i.02
|
|
%arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
|
|
%0 = load i32* %arrayidx2, align 4
|
|
; CHECK: da analyze - flow [=>|<]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 13
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 18; i++) {
|
|
;; A[-6*i] = ...
|
|
;; ... = A[-i - 60];
|
|
|
|
define void @exact12(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, -6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%sub1 = sub i64 -60, %i.02
|
|
%arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
|
|
%0 = load i32* %arrayidx2, align 4
|
|
; CHECK: da analyze - flow [=>|<]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 18
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i <= 18; i++) {
|
|
;; A[-6*i] = ...
|
|
;; ... = A[-i - 60];
|
|
|
|
define void @exact13(i32* %A, i32* %B) nounwind uwtable ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.02 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%B.addr.01 = phi i32* [ %B, %entry ], [ %incdec.ptr, %for.body ]
|
|
%conv = trunc i64 %i.02 to i32
|
|
%mul = mul i64 %i.02, -6
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 %mul
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%sub1 = sub i64 -60, %i.02
|
|
%arrayidx2 = getelementptr inbounds i32* %A, i64 %sub1
|
|
%0 = load i32* %arrayidx2, align 4
|
|
; CHECK: da analyze - flow [*|<]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.01, i64 1
|
|
store i32 %0, i32* %B.addr.01, align 4
|
|
%inc = add i64 %i.02, 1
|
|
%cmp = icmp ult i64 %inc, 19
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|