mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 13:02:52 +02:00
952bb51433
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.
llvm-svn: 165708
213 lines
7.0 KiB
LLVM
213 lines
7.0 KiB
LLVM
; RUN: opt < %s -analyze -basicaa -da | FileCheck %s
|
|
|
|
; ModuleID = 'WeakZeroSrcSIV.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 < 30; i++)
|
|
;; A[10] = ...
|
|
;; ... = A[2*i + 10];
|
|
|
|
define void @weakzerosrc0(i32* %A, i32* %B, i64 %n) 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
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 10
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%mul = shl i64 %i.02, 1
|
|
%add = add i64 %mul, 10
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %add
|
|
%0 = load i32* %arrayidx1, align 4
|
|
; CHECK: da analyze - flow [p<=|<]!
|
|
%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, 30
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < n; i++)
|
|
;; A[10] = ...
|
|
;; ... = A[n*i + 10];
|
|
|
|
define void @weakzerosrc1(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
|
|
entry:
|
|
%cmp1 = icmp eq i64 %n, 0
|
|
br i1 %cmp1, label %for.end, label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
|
|
%B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
|
|
%conv = trunc i64 %i.03 to i32
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 10
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%mul = mul i64 %i.03, %n
|
|
%add = add i64 %mul, 10
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %add
|
|
%0 = load i32* %arrayidx1, align 4
|
|
; CHECK: da analyze - flow [p<=|<]!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
|
|
store i32 %0, i32* %B.addr.02, align 4
|
|
%inc = add i64 %i.03, 1
|
|
%cmp = icmp ult i64 %inc, %n
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body, %entry
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 5; i++)
|
|
;; A[10] = ...
|
|
;; ... = A[2*i];
|
|
|
|
define void @weakzerosrc2(i32* %A, i32* %B, i64 %n) 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
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 10
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%mul = shl i64 %i.02, 1
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %mul
|
|
%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, 5
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 6; i++)
|
|
;; A[10] = ...
|
|
;; ... = A[2*i];
|
|
|
|
define void @weakzerosrc3(i32* %A, i32* %B, i64 %n) 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
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 10
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%mul = shl i64 %i.02, 1
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %mul
|
|
%0 = load i32* %arrayidx1, align 4
|
|
; CHECK: da analyze - flow [=>p|<]!
|
|
%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, 6
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 7; i++)
|
|
;; A[10] = ...
|
|
;; ... = A[2*i];
|
|
|
|
define void @weakzerosrc4(i32* %A, i32* %B, i64 %n) 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
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 10
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%mul = shl i64 %i.02, 1
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %mul
|
|
%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, 7
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < 7; i++)
|
|
;; A[-10] = ...
|
|
;; ... = A[2*i];
|
|
|
|
define void @weakzerosrc5(i32* %A, i32* %B, i64 %n) 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
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 -10
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%mul = shl i64 %i.02, 1
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %mul
|
|
%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, 7
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
|
|
;; for (long unsigned i = 0; i < n; i++)
|
|
;; A[10] = ...
|
|
;; ... = A[3*i];
|
|
|
|
define void @weakzerosrc6(i32* %A, i32* %B, i64 %n) nounwind uwtable ssp {
|
|
entry:
|
|
%cmp1 = icmp eq i64 %n, 0
|
|
br i1 %cmp1, label %for.end, label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.03 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
|
|
%B.addr.02 = phi i32* [ %incdec.ptr, %for.body ], [ %B, %entry ]
|
|
%conv = trunc i64 %i.03 to i32
|
|
%arrayidx = getelementptr inbounds i32* %A, i64 10
|
|
store i32 %conv, i32* %arrayidx, align 4
|
|
%mul = mul i64 %i.03, 3
|
|
%arrayidx1 = getelementptr inbounds i32* %A, i64 %mul
|
|
%0 = load i32* %arrayidx1, align 4
|
|
; CHECK: da analyze - none!
|
|
%incdec.ptr = getelementptr inbounds i32* %B.addr.02, i64 1
|
|
store i32 %0, i32* %B.addr.02, align 4
|
|
%inc = add i64 %i.03, 1
|
|
%cmp = icmp ult i64 %inc, %n
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body, %entry
|
|
ret void
|
|
}
|