static inline __isl_give isl_set *addDomainDimId(__isl_take isl_set *Domain,
unsigned Dim, Loop *L) {
- Domain = isl_set_lower_bound_si(Domain, isl_dim_set, Dim, -1);
isl_id *DimId =
isl_id_alloc(isl_set_get_ctx(Domain), nullptr, static_cast<void *>(L));
return isl_set_set_dim_id(Domain, isl_dim_set, Dim, DimId);
}
Loop *BBLoop = getRegionNodeLoop(RN, LI);
- int BBLoopDepth = getRelativeLoopDepth(BBLoop);
isl_set *PredDom = isl_set_empty(isl_set_get_space(Domain));
for (auto *PredBB : predecessors(BB)) {
if (!PredBBDom) {
// Determine the loop depth of the predecessor and adjust its domain to
- // the domain of the current block. This can mean we have to:
- // o) Drop a dimension if this block is the exit of a loop, not the
- // header of a new loop and the predecessor was part of the loop.
- // o) Add an unconstrainted new dimension if this block is the header
- // of a loop and the predecessor is not part of it.
- // o) Drop the information about the innermost loop dimension when the
- // predecessor and the current block are surrounded by different
- // loops in the same depth.
+ // the domain of the current block. This means we have to:
+ // o) Drop all loop dimension of loops we are leaving.
+ // o) Add a dimension for each loop we are entering.
PredBBDom = getDomainForBlock(PredBB, DomainMap, *R->getRegionInfo());
Loop *PredBBLoop = LI.getLoopFor(PredBB);
while (BoxedLoops.count(PredBBLoop))
PredBBLoop = PredBBLoop->getParentLoop();
- int PredBBLoopDepth = getRelativeLoopDepth(PredBBLoop);
- unsigned LoopDepthDiff = std::abs(BBLoopDepth - PredBBLoopDepth);
- if (BBLoopDepth < PredBBLoopDepth)
- PredBBDom = isl_set_project_out(
- PredBBDom, isl_dim_set, isl_set_n_dim(PredBBDom) - LoopDepthDiff,
- LoopDepthDiff);
- else if (PredBBLoopDepth < BBLoopDepth) {
- assert(LoopDepthDiff == 1);
- PredBBDom = isl_set_add_dims(PredBBDom, isl_dim_set, 1);
- } else if (BBLoop != PredBBLoop && BBLoopDepth >= 0) {
- assert(LoopDepthDiff <= 1);
- PredBBDom = isl_set_drop_constraints_involving_dims(
- PredBBDom, isl_dim_set, BBLoopDepth, 1);
+ Loop *LeaveL = PredBBLoop;
+ while (getRegion().contains(LeaveL) &&
+ (!BBLoop || !LeaveL->contains(BBLoop))) {
+ PredBBDom = isl_set_project_out(PredBBDom, isl_dim_set,
+ isl_set_n_dim(PredBBDom) - 1, 1);
+ LeaveL = LeaveL->getParentLoop();
+ }
+ unsigned CommonDepth = isl_set_n_dim(PredBBDom);
+
+ Loop *EnterL = BBLoop;
+ while (getRegion().contains(EnterL) &&
+ (!PredBBLoop || !EnterL->contains(PredBBLoop))) {
+ PredBBDom =
+ isl_set_insert_dims(PredBBDom, isl_dim_set, CommonDepth, 1);
+ PredBBDom = addDomainDimId(PredBBDom, CommonDepth, EnterL);
+ EnterL = EnterL->getParentLoop();
}
}
; CHECK-LABEL: polly.start:
; CHECK: store i32 %x, i32* %x.addr.0.phiops
-; CHECK-LABEL: polly.merge:
+; CHECK-LABEL: polly.exiting:
; CHECK: %x.addr.0.final_reload = load i32, i32* %x.addr.0.s2a
for.cond: ; preds = %for.inc4, %entry
; CHECK: Invariant Accesses: {
; CHECK-NEXT: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK-NEXT: [N] -> { Stmt_for_j[i0, i1] -> MemRef_init_ptr[0] };
-; CHECK-NEXT: Execution Context: [N] -> { : N < 0 or N > 0 }
+; CHECK-NEXT: Execution Context: [N] -> { : N > 0 }
; CHECK-NEXT: }
;
; CHECK: Statements {
; CHECK: Statements {
; CHECK-NEXT: Stmt_for_next
; CHECK-NEXT: Domain :=
-; CHECK-NEXT: [n] -> { Stmt_for_next[i0] : i0 >= 0 and 2i0 <= -3 + n };
+; CHECK-NEXT: [n] -> { Stmt_for_next[i0] : n > 0 and i0 >= 0 and 2i0 <= -3 + n };
; CHECK-NEXT: Schedule :=
; CHECK-NEXT: [n] -> { Stmt_for_next[i0] -> [i0] };
; CHECK-NEXT: ReadAccess := [Reduction Type: +] [Scalar: 0]
--- /dev/null
+; RUN: opt %loadPolly -polly-scops -analyze < %s | FileCheck %s
+; RUN: opt %loadPolly -polly-codegen -S < %s
+
+; Bugpoint-reduced from
+; test-suite/SingleSource/Benchmarks/Adobe-C++/loop_unroll.cpp
+;
+; Check that the loop %loop_start does not narrow the domain (the domain when
+; entering and leaving the loop must be identical)
+;
+; What happened in detail:
+;
+; 1) if.end5 checks %count whether there will be at least one iteration of
+; loop_start. The domain condition added to loop_start therefore is
+; [count] -> { [] : count > 0 }
+; 2) The loop exit condition of loop_start tests whether
+; %indvars.iv.next64 == %0 (which is zext i32 %count to i64, NOT %count
+; itself). %0 and %count have to be treated as independent parameters. The
+; loop exit condition is
+; [p_0] -> { [i0] : i0 = p_0 - 1 }
+; 3) Normalized loop induction variables are always non-negative. The domain
+; condition for this is loop
+; { [i0] : i0 >= 0 }
+; 4) The intersection of all three sets (condition of executing/entering loop,
+; non-negative induction variables, loop exit condition) is
+; [count, p_0] -> { [i0] : count > 0 and i0 >= 0 and i0 = p_0 - 1 }
+; 5) from which ISL can derive
+; [count, p_0] -> { [i0] : p_0 > 0 }
+; 6) if.end5 is either executed when skipping the loop
+; (domain [count] -> { [] : count <= 0 })
+; or though the loop.
+; 7) Assuming the loop is guaranteed to exit, Polly computes the after-the-loop
+; domain by taking the loop exit condition and projecting-out the induction
+; variable. This yields
+; [count, p_0] -> { [] : count > 0 and p_0 > 0 }
+; 8) The disjunction of both cases, 6) and 7)
+; (the two incoming edges of if.end12) is
+; [count, p_0] -> { [] : count <= 0 or (count > 0 and p_0 > 0) }
+; 9) Notice that if.end12 is logically _always_ executed in every scop
+; execution. Both cases of if.end5 will eventually land in if.end12
+
+define void @func(i32 %count, float* %A) {
+entry:
+ %0 = zext i32 %count to i64
+ br i1 undef, label %if.end5.preheader, label %for.end
+
+if.end5.preheader:
+ %cmp6 = icmp sgt i32 %count, 0
+ br label %if.end5
+
+if.end5:
+ br i1 %cmp6, label %loop_start, label %if.end12
+
+loop_start:
+ %indvars.iv63 = phi i64 [ %indvars.iv.next64, %loop_start ], [ 0, %if.end5 ]
+ %add8 = add i32 undef, undef
+ %indvars.iv.next64 = add nuw nsw i64 %indvars.iv63, 1
+ %cmp9 = icmp eq i64 %indvars.iv.next64, %0
+ br i1 %cmp9, label %if.end12, label %loop_start
+
+if.end12:
+ store float 0.0, float* %A
+ br label %for.end
+
+for.end:
+ ret void
+}
+
+
+; CHECK: Statements {
+; CHECK-NEXT: Stmt_if_end12
+; CHECK-NEXT: Domain :=
+; CHECK-NEXT: [count, p_1] -> { Stmt_if_end12[] };
+; CHECK-NEXT: Schedule :=
+; CHECK-NEXT: [count, p_1] -> { Stmt_if_end12[] -> [] };
+; CHECK-NEXT: MustWriteAccess := [Reduction Type: NONE] [Scalar: 0]
+; CHECK-NEXT: [count, p_1] -> { Stmt_if_end12[] -> MemRef_A[0] };
+; CHECK-NEXT: }
; CHECK: Statements {
; CHECK-NEXT: Stmt_for_cond
; CHECK-NEXT: Domain :=
-; CHECK-NEXT: [N] -> { Stmt_for_cond[i0] : N >= 2 and 0 <= i0 < N; Stmt_for_cond[0] : N <= 1 };
+; CHECK-NEXT: [N] -> { Stmt_for_cond[i0] : 0 <= i0 < N; Stmt_for_cond[0] : N <= 0 };
; CHECK-NEXT: Schedule :=
-; CHECK-NEXT: [N] -> { Stmt_for_cond[i0] -> [i0, 0, 0, 0] : N >= 2 and i0 < N; Stmt_for_cond[0] -> [0, 0, 0, 0] : N <= 1 };
+; CHECK-NEXT: [N] -> { Stmt_for_cond[i0] -> [i0, 0, 0, 0] : i0 < N; Stmt_for_cond[0] -> [0, 0, 0, 0] : N <= 0 };
; CHECK-NEXT: ReadAccess := [Reduction Type: NONE] [Scalar: 1]
; CHECK-NEXT: [N] -> { Stmt_for_cond[i0] -> MemRef_x_addr_0__phi[] };
; CHECK-NEXT: MustWriteAccess := [Reduction Type: NONE] [Scalar: 1]
; CHECK-NEXT: [N] -> { Stmt_for_cond[i0] -> MemRef_x_addr_0[] };
; CHECK-NEXT: Stmt_for_body
; CHECK-NEXT: Domain :=
-; CHECK-NEXT: [N] -> { Stmt_for_body[i0] : N >= 2 and 0 <= i0 <= -2 + N };
+; CHECK-NEXT: [N] -> { Stmt_for_body[i0] : 0 <= i0 <= -2 + N };
; CHECK-NEXT: Schedule :=
; CHECK-NEXT: [N] -> { Stmt_for_body[i0] -> [i0, 1, 0, 0] };
; CHECK-NEXT: ReadAccess := [Reduction Type: NONE] [Scalar: 1]
; RUN: opt %loadPolly -pass-remarks-analysis="polly-scops" -polly-scops -disable-output < %s 2>&1 | FileCheck %s
;
; CHECK: remark: test/ScopInfo/remarks.c:4:7: SCoP begins here.
-; CHECK: remark: test/ScopInfo/remarks.c:8:5: Finite loop restriction: [M, N, Debug] -> { : N > 0 and (M <= -2 or M = -1) }
-; CHECK: remark: test/ScopInfo/remarks.c:13:7: No-error restriction: [M, N, Debug] -> { : M >= 0 and N > 0 and (Debug < 0 or Debug > 0) }
-; CHECK: remark: test/ScopInfo/remarks.c:9:7: Inbounds assumption: [M, N, Debug] -> { : M <= 100 or (M > 0 and N <= 0) }
-; CHECK: remark: <unknown>:0:0: No-overflows restriction: [N, M, Debug] -> { : M <= -2147483649 - N or M >= 2147483648 - N }
+; CHECK: remark: test/ScopInfo/remarks.c:8:5: Finite loop restriction: [M, N, Debug] -> { : M < 0 and N > 0 }
+; CHECK: remark: test/ScopInfo/remarks.c:13:7: No-error restriction: [M, N, Debug] -> { : M >= 0 and N > 0 and (Debug < 0 or Debug > 0) }
+; CHECK: remark: test/ScopInfo/remarks.c:9:7: Inbounds assumption: [M, N, Debug] -> { : M <= 100 or (M > 0 and N <= 0) }
+; CHECK: remark: <unknown>:0:0: No-overflows restriction: [N, M, Debug] -> { : M <= -2147483649 - N or M >= 2147483648 - N }
; CHECK: remark: test/ScopInfo/remarks.c:9:18: Possibly aliasing pointer, use restrict keyword.
; CHECK: remark: test/ScopInfo/remarks.c:9:33: Possibly aliasing pointer, use restrict keyword.
; CHECK: remark: test/ScopInfo/remarks.c:9:15: Possibly aliasing pointer, use restrict keyword.
; CHECK: Statements {
; CHECK-NEXT: Stmt_sw_bb_1
; CHECK-NEXT: Domain :=
-; CHECK-NEXT: [N] -> { Stmt_sw_bb_1[i0] : 4*floor((-1 + i0)/4) = -1 + i0 and 0 < i0 < N };
+; CHECK-NEXT: [N] -> { Stmt_sw_bb_1[i0] : 4*floor((-1 + i0)/4) = -1 + i0 and 0 <= i0 < N };
; CHECK-NEXT: Schedule :=
; CHECK-NEXT: [N] -> { Stmt_sw_bb_1[i0] -> [i0, 2] };
; CHECK-NEXT: ReadAccess := [Reduction Type: +] [Scalar: 0]
; CHECK-NEXT: [N] -> { Stmt_sw_bb_1[i0] -> MemRef_A[i0] };
; CHECK-NEXT: Stmt_sw_bb_2
; CHECK-NEXT: Domain :=
-; CHECK-NEXT: [N] -> { Stmt_sw_bb_2[i0] : 4*floor((-2 + i0)/4) = -2 + i0 and 2 <= i0 < N };
+; CHECK-NEXT: [N] -> { Stmt_sw_bb_2[i0] : 4*floor((-2 + i0)/4) = -2 + i0 and 0 <= i0 < N };
; CHECK-NEXT: Schedule :=
; CHECK-NEXT: [N] -> { Stmt_sw_bb_2[i0] -> [i0, 1] };
; CHECK-NEXT: ReadAccess := [Reduction Type: +] [Scalar: 0]
; AST: if (1)
;
-; AST: {
-; AST-NEXT: for (int c0 = 1; c0 < N - 2; c0 += 4) {
-; AST-NEXT: Stmt_sw_bb_1(c0);
+; AST: for (int c0 = 1; c0 < N; c0 += 4) {
+; AST-NEXT: Stmt_sw_bb_1(c0);
+; AST-NEXT: if (N >= c0 + 2) {
; AST-NEXT: Stmt_sw_bb_2(c0 + 1);
-; AST-NEXT: Stmt_sw_bb_6(c0 + 2);
+; AST-NEXT: if (N >= c0 + 3)
+; AST-NEXT: Stmt_sw_bb_6(c0 + 2);
; AST-NEXT: }
-; AST-NEXT: if (N >= 2)
-; AST-NEXT: if (N % 4 >= 2) {
-; AST-NEXT: Stmt_sw_bb_1(-(N % 4) + N + 1);
-; AST-NEXT: if ((N - 3) % 4 == 0)
-; AST-NEXT: Stmt_sw_bb_2(N - 1);
-; AST-NEXT: }
; AST-NEXT: }
;
; AST: else
; CHECK-NEXT: [N] -> { Stmt_sw_bb[i0] -> MemRef_A[i0] };
; CHECK-NEXT: Stmt_sw_bb_2
; CHECK-NEXT: Domain :=
-; CHECK-NEXT: [N] -> { Stmt_sw_bb_2[i0] : 4*floor((-2 + i0)/4) = -2 + i0 and 2 <= i0 < N };
+; CHECK-NEXT: [N] -> { Stmt_sw_bb_2[i0] : 4*floor((-2 + i0)/4) = -2 + i0 and 0 <= i0 < N };
; CHECK-NEXT: Schedule :=
; CHECK-NEXT: [N] -> { Stmt_sw_bb_2[i0] -> [i0, 0] };
; CHECK-NEXT: ReadAccess := [Reduction Type: +] [Scalar: 0]
; AST: if (1)
;
-; AST: for (int c0 = 0; c0 < N; c0 += 4) {
-; AST-NEXT: Stmt_sw_bb(c0);
-; AST-NEXT: if (N >= c0 + 3)
+; AST: {
+; AST-NEXT: for (int c0 = 0; c0 < N - 2; c0 += 4) {
+; AST-NEXT: Stmt_sw_bb(c0);
; AST-NEXT: Stmt_sw_bb_2(c0 + 2);
+; AST-NEXT: }
+; AST-NEXT: if (N >= 1 && (N + 1) % 4 >= 2)
+; AST-NEXT: Stmt_sw_bb(-((N + 1) % 4) + N + 1);
; AST-NEXT: }
;
; AST: else
; CHECK-NEXT: [N] -> { Stmt_sw_bb_1[i0] -> MemRef_A[i0] };
; CHECK-NEXT: Stmt_sw_bb_5
; CHECK-NEXT: Domain :=
-; CHECK-NEXT: [N] -> { Stmt_sw_bb_5[i0] : 4*floor((-2 + i0)/4) = -2 + i0 and 2 <= i0 < N };
+; CHECK-NEXT: [N] -> { Stmt_sw_bb_5[i0] : 4*floor((-2 + i0)/4) = -2 + i0 and 0 <= i0 < N };
; CHECK-NEXT: Schedule :=
; CHECK-NEXT: [N] -> { Stmt_sw_bb_5[i0] -> [i0, 0] };
; CHECK-NEXT: ReadAccess := [Reduction Type: +] [Scalar: 0]
; CHECK-NEXT: [N] -> { Stmt_sw_bb[i0] -> MemRef_A[i0] };
; CHECK-NEXT: Stmt_sw_bb_1
; CHECK-NEXT: Domain :=
-; CHECK-NEXT: [N] -> { Stmt_sw_bb_1[i0] : 4*floor((-1 + i0)/4) = -1 + i0 and 0 < i0 < N };
+; CHECK-NEXT: [N] -> { Stmt_sw_bb_1[i0] : 4*floor((-1 + i0)/4) = -1 + i0 and 0 <= i0 < N };
; CHECK-NEXT: Schedule :=
; CHECK-NEXT: [N] -> { Stmt_sw_bb_1[i0] -> [i0, 2] };
; CHECK-NEXT: ReadAccess := [Reduction Type: +] [Scalar: 0]
; CHECK-NEXT: [N] -> { Stmt_sw_bb_1[i0] -> MemRef_A[i0] };
; CHECK-NEXT: Stmt_sw_bb_5
; CHECK-NEXT: Domain :=
-; CHECK-NEXT: [N] -> { Stmt_sw_bb_5[i0] : 4*floor((-2 + i0)/4) = -2 + i0 and 2 <= i0 < N };
+; CHECK-NEXT: [N] -> { Stmt_sw_bb_5[i0] : 4*floor((-2 + i0)/4) = -2 + i0 and 0 <= i0 < N };
; CHECK-NEXT: Schedule :=
; CHECK-NEXT: [N] -> { Stmt_sw_bb_5[i0] -> [i0, 1] };
; CHECK-NEXT: ReadAccess := [Reduction Type: +] [Scalar: 0]
; AST: if (1)
;
-; AST: {
-; AST-NEXT: for (int c0 = 0; c0 < N - 3; c0 += 4) {
-; AST-NEXT: Stmt_sw_bb(c0);
+; AST: for (int c0 = 0; c0 < N; c0 += 4) {
+; AST-NEXT: Stmt_sw_bb(c0);
+; AST-NEXT: if (N >= c0 + 2) {
; AST-NEXT: Stmt_sw_bb_1(c0 + 1);
-; AST-NEXT: Stmt_sw_bb_5(c0 + 2);
-; AST-NEXT: Stmt_sw_bb_9(c0 + 3);
-; AST-NEXT: }
-; AST-NEXT: if (N >= 1)
-; AST-NEXT: if (N % 4 >= 1) {
-; AST-NEXT: Stmt_sw_bb(-(N % 4) + N);
-; AST-NEXT: if (N % 4 >= 2) {
-; AST-NEXT: Stmt_sw_bb_1(-(N % 4) + N + 1);
-; AST-NEXT: if ((N - 3) % 4 == 0)
-; AST-NEXT: Stmt_sw_bb_5(N - 1);
-; AST-NEXT: }
+; AST-NEXT: if (N >= c0 + 3) {
+; AST-NEXT: Stmt_sw_bb_5(c0 + 2);
+; AST-NEXT: if (N >= c0 + 4)
+; AST-NEXT: Stmt_sw_bb_9(c0 + 3);
; AST-NEXT: }
+; AST-NEXT: }
; AST-NEXT: }
;
; AST: else