[Polly][PATCH 8/8] [RTC] Annotate the IslAst with runtime alias checks.
Andreas Simbürger
simbuerg at googlemail.com
Wed Aug 13 14:26:08 PDT 2014
One minor comment inline, otherwise LGTM.
On Sun, Aug 10, 2014 at 9:50 AM, Johannes Doerfert
<doerfert at cs.uni-saarland.de> wrote:
> This check will also generate the code for runtime alias checks, thus
> make -polly-use-runtime-alias-checks=true save for the isl code
> generator.
> ---
> lib/CodeGen/IslAst.cpp | 24 ++++++++++
> test/Isl/Ast/alias_simple_1.ll | 58 +++++++++++++++++++++++
> test/Isl/Ast/alias_simple_2.ll | 58 +++++++++++++++++++++++
> test/Isl/Ast/alias_simple_3.ll | 59 ++++++++++++++++++++++++
> test/Isl/Ast/aliasing_multiple_alias_groups.ll | 54 ++++++++++++++++++++++
> test/Isl/Ast/aliasing_parametric_simple_1.ll | 39 ++++++++++++++++
> test/Isl/Ast/aliasing_parametric_simple_2.ll | 43 +++++++++++++++++
> test/Isl/CodeGen/aliasing_parametric_simple_1.ll | 43 +++++++++++++++++
> test/Isl/CodeGen/aliasing_parametric_simple_2.ll | 57 +++++++++++++++++++++++
> 9 files changed, 435 insertions(+)
> create mode 100644 test/Isl/Ast/alias_simple_1.ll
> create mode 100644 test/Isl/Ast/alias_simple_2.ll
> create mode 100644 test/Isl/Ast/alias_simple_3.ll
> create mode 100644 test/Isl/Ast/aliasing_multiple_alias_groups.ll
> create mode 100644 test/Isl/Ast/aliasing_parametric_simple_1.ll
> create mode 100644 test/Isl/Ast/aliasing_parametric_simple_2.ll
> create mode 100644 test/Isl/CodeGen/aliasing_parametric_simple_1.ll
> create mode 100644 test/Isl/CodeGen/aliasing_parametric_simple_2.ll
>
> diff --git a/lib/CodeGen/IslAst.cpp b/lib/CodeGen/IslAst.cpp
> index 500e219..d326c94 100644
> --- a/lib/CodeGen/IslAst.cpp
> +++ b/lib/CodeGen/IslAst.cpp
> @@ -299,6 +299,30 @@ void IslAst::buildRunCondition(__isl_keep isl_ast_build *Build) {
> RunCondition = isl_ast_build_expr_from_pw_aff(Build, Cond);
> RunCondition = isl_ast_expr_eq(RunCondition,
> isl_ast_build_expr_from_pw_aff(Build, PwOne));
> +
> + // Create the alias checks from the minimal/maximal accesses in each alias
> + // groups. This operation is by construction quadratic in the number of
> + // elements in each alias group.
I would add a small comment that explains what condition you check.
Something like:
// Intersect all 2-combinations of MinMaxAccesses of each AliasGroup
of the form:
// &A[i_max] < &B[i_min] || &B[i_max] < &A[i_min]
+- my bad english ;-)
> + isl_ast_expr *NonAliasGroup, *MinExpr, *MaxExpr;
> + for (const Scop::MinMaxVectorTy *MinMaxAccesses : S->getAliasGroups()) {
> + auto AccEnd = MinMaxAccesses->end();
> + for (auto AccIt0 = MinMaxAccesses->begin(); AccIt0 != AccEnd; ++AccIt0) {
> + for (auto AccIt1 = AccIt0 + 1; AccIt1 != AccEnd; ++AccIt1) {
> + MinExpr = isl_ast_expr_addr_of(isl_ast_build_access_from_pw_multi_aff(
> + Build, isl_pw_multi_aff_copy(AccIt0->first)));
> + MaxExpr = isl_ast_expr_addr_of(isl_ast_build_access_from_pw_multi_aff(
> + Build, isl_pw_multi_aff_copy(AccIt1->second)));
> + NonAliasGroup = isl_ast_expr_lt(MaxExpr, MinExpr);
> + MinExpr = isl_ast_expr_addr_of(isl_ast_build_access_from_pw_multi_aff(
> + Build, isl_pw_multi_aff_copy(AccIt1->first)));
> + MaxExpr = isl_ast_expr_addr_of(isl_ast_build_access_from_pw_multi_aff(
> + Build, isl_pw_multi_aff_copy(AccIt0->second)));
> + NonAliasGroup =
> + isl_ast_expr_or(NonAliasGroup, isl_ast_expr_lt(MaxExpr, MinExpr));
> + RunCondition = isl_ast_expr_and(RunCondition, NonAliasGroup);
> + }
> + }
> + }
> }
>
> IslAst::IslAst(Scop *Scop, Dependences &D) : S(Scop) {
> diff --git a/test/Isl/Ast/alias_simple_1.ll b/test/Isl/Ast/alias_simple_1.ll
> new file mode 100644
> index 0000000..7cbd5e3
> --- /dev/null
> +++ b/test/Isl/Ast/alias_simple_1.ll
> @@ -0,0 +1,58 @@
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze < %s | FileCheck %s --check-prefix=NOAA
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -basicaa < %s | FileCheck %s --check-prefix=BASI
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -tbaa < %s | FileCheck %s --check-prefix=TBAA
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -scev-aa < %s | FileCheck %s --check-prefix=SCEV
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -globalsmodref-aa < %s | FileCheck %s --check-prefix=GLOB
> +;
> +; int A[1024];
> +;
> +;
> +; void jd(float *B, int N) {
> +; for (int i = 0; i < N; i++)
> +; A[i] = B[i];
> +; }
> +;
> +; NOAA: if (1 == 1 && (&MemRef_A[N - 1] < &MemRef_B[0] || &MemRef_B[N - 1] < &MemRef_A[0]))
> +; BASI: if (1 == 1 && (&MemRef_A[N - 1] < &MemRef_B[0] || &MemRef_B[N - 1] < &MemRef_A[0]))
> +; TBAA: if (1 == 1)
> +; SCEV: if (1 == 1 && (&MemRef_A[N - 1] < &MemRef_B[0] || &MemRef_B[N - 1] < &MemRef_A[0]))
> +; GLOB: if (1 == 1 && (&MemRef_A[N - 1] < &MemRef_B[0] || &MemRef_B[N - 1] < &MemRef_A[0]))
> +;
> +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> +
> + at A = common global [1024 x i32] zeroinitializer, align 16
> +
> +define void @jd(float* nocapture readonly %B, i32 %N) {
> +entry:
> + %cmp6 = icmp sgt i32 %N, 0
> + br i1 %cmp6, label %for.body.preheader, label %for.end
> +
> +for.body.preheader: ; preds = %entry
> + br label %for.body
> +
> +for.body: ; preds = %for.body.preheader, %for.body
> + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
> + %arrayidx = getelementptr inbounds float* %B, i64 %indvars.iv
> + %tmp = load float* %arrayidx, align 4, !tbaa !1
> + %conv = fptosi float %tmp to i32
> + %arrayidx2 = getelementptr inbounds [1024 x i32]* @A, i64 0, i64 %indvars.iv
> + store i32 %conv, i32* %arrayidx2, align 4, !tbaa !5
> + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
> + %lftr.wideiv1 = trunc i64 %indvars.iv.next to i32
> + %exitcond2 = icmp eq i32 %lftr.wideiv1, %N
> + br i1 %exitcond2, label %for.end.loopexit, label %for.body
> +
> +for.end.loopexit: ; preds = %for.body
> + br label %for.end
> +
> +for.end: ; preds = %for.end.loopexit, %entry
> + ret void
> +}
> +
> +!0 = metadata !{metadata !""}
> +!1 = metadata !{metadata !2, metadata !2, i64 0}
> +!2 = metadata !{metadata !"float", metadata !3, i64 0}
> +!3 = metadata !{metadata !"omnipotent char", metadata !4, i64 0}
> +!4 = metadata !{metadata !"Simple C/C++ TBAA"}
> +!5 = metadata !{metadata !6, metadata !6, i64 0}
> +!6 = metadata !{metadata !"int", metadata !3, i64 0}
> diff --git a/test/Isl/Ast/alias_simple_2.ll b/test/Isl/Ast/alias_simple_2.ll
> new file mode 100644
> index 0000000..59097b2
> --- /dev/null
> +++ b/test/Isl/Ast/alias_simple_2.ll
> @@ -0,0 +1,58 @@
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze < %s | FileCheck %s --check-prefix=NOAA
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -basicaa < %s | FileCheck %s --check-prefix=BASI
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -tbaa < %s | FileCheck %s --check-prefix=TBAA
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -scev-aa < %s | FileCheck %s --check-prefix=SCEV
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -globalsmodref-aa < %s | FileCheck %s --check-prefix=GLOB
> +;
> +; int A[1024], B[1024];
> +;
> +;
> +; void jd(int N) {
> +; for (int i = 0; i < N; i++)
> +; A[i] = B[i];
> +; }
> +;
> +; NOAA: if (1 == 1 && (&MemRef_A[N - 1] < &MemRef_B[0] || &MemRef_B[N - 1] < &MemRef_A[0]))
> +; BASI: if (1 == 1)
> +; TBAA: if (1 == 1 && (&MemRef_A[N - 1] < &MemRef_B[0] || &MemRef_B[N - 1] < &MemRef_A[0]))
> +; SCEV: if (1 == 1 && (&MemRef_A[N - 1] < &MemRef_B[0] || &MemRef_B[N - 1] < &MemRef_A[0]))
> +; GLOB: if (1 == 1 && (&MemRef_A[N - 1] < &MemRef_B[0] || &MemRef_B[N - 1] < &MemRef_A[0]))
> +;
> +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> +
> + at A = common global [1024 x i32] zeroinitializer, align 16
> + at B = common global [1024 x i32] zeroinitializer, align 16
> +
> +define void @jd(i32 %N) {
> +entry:
> + %cmp6 = icmp sgt i32 %N, 0
> + br i1 %cmp6, label %for.body.preheader, label %for.end
> +
> +for.body.preheader: ; preds = %entry
> + br label %for.body
> +
> +for.body: ; preds = %for.body.preheader, %for.body
> + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
> + %arrayidx = getelementptr inbounds [1024 x i32]* @B, i64 0, i64 %indvars.iv
> + %tmp = load i32* %arrayidx, align 4, !tbaa !5
> + %arrayidx2 = getelementptr inbounds [1024 x i32]* @A, i64 0, i64 %indvars.iv
> + store i32 %tmp, i32* %arrayidx2, align 4, !tbaa !5
> + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
> + %lftr.wideiv1 = trunc i64 %indvars.iv.next to i32
> + %exitcond2 = icmp eq i32 %lftr.wideiv1, %N
> + br i1 %exitcond2, label %for.end.loopexit, label %for.body
> +
> +for.end.loopexit: ; preds = %for.body
> + br label %for.end
> +
> +for.end: ; preds = %for.end.loopexit, %entry
> + ret void
> +}
> +
> +!0 = metadata !{metadata !""}
> +!1 = metadata !{metadata !2, metadata !2, i64 0}
> +!2 = metadata !{metadata !"float", metadata !3, i64 0}
> +!3 = metadata !{metadata !"omnipotent char", metadata !4, i64 0}
> +!4 = metadata !{metadata !"Simple C/C++ TBAA"}
> +!5 = metadata !{metadata !6, metadata !6, i64 0}
> +!6 = metadata !{metadata !"int", metadata !3, i64 0}
> diff --git a/test/Isl/Ast/alias_simple_3.ll b/test/Isl/Ast/alias_simple_3.ll
> new file mode 100644
> index 0000000..c34e779
> --- /dev/null
> +++ b/test/Isl/Ast/alias_simple_3.ll
> @@ -0,0 +1,59 @@
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze < %s | FileCheck %s --check-prefix=NOAA
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -basicaa < %s | FileCheck %s --check-prefix=BASI
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -tbaa < %s | FileCheck %s --check-prefix=TBAA
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -scev-aa < %s | FileCheck %s --check-prefix=SCEV
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze -globalsmodref-aa < %s | FileCheck %s --check-prefix=GLOB
> +;
> +; int A[1024];
> +; float B[1024];
> +;
> +; void jd(int N) {
> +; for (int i = 0; i < N; i++)
> +; A[i] = B[i];
> +; }
> +;
> +; NOAA: if (1 == 1 && (&MemRef_A[N - 1] < &MemRef_B[0] || &MemRef_B[N - 1] < &MemRef_A[0]))
> +; BASI: if (1 == 1)
> +; TBAA: if (1 == 1)
> +; SCEV: if (1 == 1 && (&MemRef_A[N - 1] < &MemRef_B[0] || &MemRef_B[N - 1] < &MemRef_A[0]))
> +; GLOB: if (1 == 1 && (&MemRef_A[N - 1] < &MemRef_B[0] || &MemRef_B[N - 1] < &MemRef_A[0]))
> +;
> +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> +
> + at A = common global [1024 x i32] zeroinitializer, align 16
> + at B = common global [1024 x float] zeroinitializer, align 16
> +
> +define void @jd(i32 %N) {
> +entry:
> + %cmp6 = icmp sgt i32 %N, 0
> + br i1 %cmp6, label %for.body.preheader, label %for.end
> +
> +for.body.preheader: ; preds = %entry
> + br label %for.body
> +
> +for.body: ; preds = %for.body.preheader, %for.body
> + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
> + %arrayidx = getelementptr inbounds [1024 x float]* @B, i64 0, i64 %indvars.iv
> + %tmp = load float* %arrayidx, align 4, !tbaa !1
> + %conv = fptosi float %tmp to i32
> + %arrayidx2 = getelementptr inbounds [1024 x i32]* @A, i64 0, i64 %indvars.iv
> + store i32 %conv, i32* %arrayidx2, align 4, !tbaa !5
> + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
> + %lftr.wideiv1 = trunc i64 %indvars.iv.next to i32
> + %exitcond2 = icmp eq i32 %lftr.wideiv1, %N
> + br i1 %exitcond2, label %for.end.loopexit, label %for.body
> +
> +for.end.loopexit: ; preds = %for.body
> + br label %for.end
> +
> +for.end: ; preds = %for.end.loopexit, %entry
> + ret void
> +}
> +
> +!0 = metadata !{metadata !""}
> +!1 = metadata !{metadata !2, metadata !2, i64 0}
> +!2 = metadata !{metadata !"float", metadata !3, i64 0}
> +!3 = metadata !{metadata !"omnipotent char", metadata !4, i64 0}
> +!4 = metadata !{metadata !"Simple C/C++ TBAA"}
> +!5 = metadata !{metadata !6, metadata !6, i64 0}
> +!6 = metadata !{metadata !"int", metadata !3, i64 0}
> diff --git a/test/Isl/Ast/aliasing_multiple_alias_groups.ll b/test/Isl/Ast/aliasing_multiple_alias_groups.ll
> new file mode 100644
> index 0000000..a80ae8f
> --- /dev/null
> +++ b/test/Isl/Ast/aliasing_multiple_alias_groups.ll
> @@ -0,0 +1,54 @@
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks=true -polly-ast -analyze < %s | FileCheck %s --check-prefix=NOAA
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks=true -polly-ast -analyze -tbaa < %s | FileCheck %s --check-prefix=TBAA
> +;
> +; void jd(int *Int0, int *Int1, float *Float0, float *Float1) {
> +; for (int i = 0; i < 1024; i++) {
> +; Int0[i] = Int1[i];
> +; Float0[i] = Float1[i];
> +; }
> +; }
> +;
> +; NOAA: if (1 == 1 && (
> +; NOAA-DAG: &MemRef_Float0[1023] < &MemRef_Int0[0] || &MemRef_Int0[1023] < &MemRef_Float0[0]
> +; NOAA-DAG: &MemRef_Float1[1023] < &MemRef_Int0[0] || &MemRef_Int0[1023] < &MemRef_Float1[0]
> +; NOAA-DAG: &MemRef_Int1[1023] < &MemRef_Int0[0] || &MemRef_Int0[1023] < &MemRef_Int1[0]
> +; NOAA-DAG: &MemRef_Float1[1023] < &MemRef_Float0[0] || &MemRef_Float0[1023] < &MemRef_Float1[0]
> +; NOAA-DAG: &MemRef_Int1[1023] < &MemRef_Float0[0] || &MemRef_Float0[1023] < &MemRef_Int1[0]
> +; NOAA-DAG: &MemRef_Int1[1023] < &MemRef_Float1[0] || &MemRef_Float1[1023] < &MemRef_Int1[0]
> +; NOAA: ))
> +;
> +; TBAA: if (1 == 1 && (
> +; TBAA-DAG: &MemRef_Int0[1023] < &MemRef_Int1[0] || &MemRef_Int1[1023] < &MemRef_Int0[0]
> +; TBAA-DAG: &MemRef_Float1[1023] < &MemRef_Float0[0] || &MemRef_Float0[1023] < &MemRef_Float1[0]
> +; TBAA: ))
> +;
> +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> +
> +define void @jd(i32* nocapture %Int0, i32* nocapture readonly %Int1, float* nocapture %Float0, float* nocapture readonly %Float1) {
> +entry:
> + br label %for.body
> +
> +for.body: ; preds = %for.body, %entry
> + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
> + %arrayidx = getelementptr inbounds i32* %Int1, i64 %indvars.iv
> + %tmp = load i32* %arrayidx, align 4, !tbaa !0
> + %arrayidx2 = getelementptr inbounds i32* %Int0, i64 %indvars.iv
> + store i32 %tmp, i32* %arrayidx2, align 4, !tbaa !0
> + %arrayidx4 = getelementptr inbounds float* %Float1, i64 %indvars.iv
> + %tmp1 = load float* %arrayidx4, align 4, !tbaa !4
> + %arrayidx6 = getelementptr inbounds float* %Float0, i64 %indvars.iv
> + store float %tmp1, float* %arrayidx6, align 4, !tbaa !4
> + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
> + %exitcond = icmp eq i64 %indvars.iv.next, 1024
> + br i1 %exitcond, label %for.end, label %for.body
> +
> +for.end: ; preds = %for.body
> + ret void
> +}
> +
> +!0 = metadata !{metadata !1, metadata !1, i64 0}
> +!1 = metadata !{metadata !"int", metadata !2, i64 0}
> +!2 = metadata !{metadata !"omnipotent char", metadata !3, i64 0}
> +!3 = metadata !{metadata !"Simple C/C++ TBAA"}
> +!4 = metadata !{metadata !5, metadata !5, i64 0}
> +!5 = metadata !{metadata !"float", metadata !2, i64 0}
> diff --git a/test/Isl/Ast/aliasing_parametric_simple_1.ll b/test/Isl/Ast/aliasing_parametric_simple_1.ll
> new file mode 100644
> index 0000000..09413af
> --- /dev/null
> +++ b/test/Isl/Ast/aliasing_parametric_simple_1.ll
> @@ -0,0 +1,39 @@
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze %s | FileCheck %s
> +;
> +; void jd(int *A, int *B, int c) {
> +; for (int i = 0; i < 1024; i++)
> +; A[i] = B[c];
> +; }
> +;
> +; CHECK: if (1 == 1 && (&MemRef_A[1023] < &MemRef_B[c] || &MemRef_B[c] < &MemRef_A[0]))
> +; CHECK: for (int c1 = 0; c1 <= 1023; c1 += 1)
> +; CHECK: Stmt_for_body(c1);
> +; CHECK: else
> +; CHECK: /* original code */
> +;
> +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> +
> +define void @jd(i32* %A, i32* %B, i32 %c) {
> +entry:
> + br label %for.cond
> +
> +for.cond: ; preds = %for.inc, %entry
> + %indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
> + %exitcond = icmp ne i64 %indvars.iv, 1024
> + br i1 %exitcond, label %for.body, label %for.end
> +
> +for.body: ; preds = %for.cond
> + %idxprom = sext i32 %c to i64
> + %arrayidx = getelementptr inbounds i32* %B, i64 %idxprom
> + %tmp = load i32* %arrayidx, align 4
> + %arrayidx2 = getelementptr inbounds i32* %A, i64 %indvars.iv
> + store i32 %tmp, i32* %arrayidx2, align 4
> + br label %for.inc
> +
> +for.inc: ; preds = %for.body
> + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
> + br label %for.cond
> +
> +for.end: ; preds = %for.cond
> + ret void
> +}
> diff --git a/test/Isl/Ast/aliasing_parametric_simple_2.ll b/test/Isl/Ast/aliasing_parametric_simple_2.ll
> new file mode 100644
> index 0000000..4b9c889
> --- /dev/null
> +++ b/test/Isl/Ast/aliasing_parametric_simple_2.ll
> @@ -0,0 +1,43 @@
> +; RUN: opt %loadPolly -polly-use-runtime-alias-checks -polly-ast -analyze < %s | FileCheck %s
> +;
> +; void jd(int *A, int *B, int c) {
> +; for (int i = 0; i < 1024; i++)
> +; A[i] = B[c - 10] + B[5];
> +; }
> +;
> +; CHECK: if (1 == 1 && (&MemRef_A[1023] < &MemRef_B[c >= 15 ? 5 : c - 10] || &MemRef_B[c <= 15 ? 5 : c - 10] < &MemRef_A[0]))
> +; CHECK: for (int c1 = 0; c1 <= 1023; c1 += 1)
> +; CHECK: Stmt_for_body(c1);
> +; CHECK: else
> +; CHECK: /* original code */
> +;
> +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> +
> +define void @jd(i32* %A, i32* %B, i32 %c) {
> +entry:
> + br label %for.cond
> +
> +for.cond: ; preds = %for.inc, %entry
> + %indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
> + %exitcond = icmp ne i64 %indvars.iv, 1024
> + br i1 %exitcond, label %for.body, label %for.end
> +
> +for.body: ; preds = %for.cond
> + %sub = add nsw i32 %c, -10
> + %idxprom = sext i32 %sub to i64
> + %arrayidx = getelementptr inbounds i32* %B, i64 %idxprom
> + %tmp = load i32* %arrayidx, align 4
> + %arrayidx1 = getelementptr inbounds i32* %B, i64 5
> + %tmp1 = load i32* %arrayidx1, align 4
> + %add = add nsw i32 %tmp, %tmp1
> + %arrayidx3 = getelementptr inbounds i32* %A, i64 %indvars.iv
> + store i32 %add, i32* %arrayidx3, align 4
> + br label %for.inc
> +
> +for.inc: ; preds = %for.body
> + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
> + br label %for.cond
> +
> +for.end: ; preds = %for.cond
> + ret void
> +}
> diff --git a/test/Isl/CodeGen/aliasing_parametric_simple_1.ll b/test/Isl/CodeGen/aliasing_parametric_simple_1.ll
> new file mode 100644
> index 0000000..cdb38be
> --- /dev/null
> +++ b/test/Isl/CodeGen/aliasing_parametric_simple_1.ll
> @@ -0,0 +1,43 @@
> +; RUN: opt %loadPolly -polly-codegen-isl -polly-use-runtime-alias-checks -S < %s | FileCheck %s
> +;
> +; void jd(int *A, int *B, int c) {
> +; for (int i = 0; i < 1024; i++)
> +; A[i] = B[c];
> +; }
> +;
> +; CHECK: %[[AMax:[._a-zA-Z0-9]*]] = getelementptr i32* %A, i64 1023
> +; CHECK: %[[BMin:[._a-zA-Z0-9]*]] = getelementptr i32* %B, i32 %c
> +; CHECK: %[[AltB:[._a-zA-Z0-9]*]] = icmp ult i32* %[[AMax]], %[[BMin]]
> +; CHECK: %[[BMax:[._a-zA-Z0-9]*]] = getelementptr i32* %B, i32 %c
> +; CHECK: %[[AMin:[._a-zA-Z0-9]*]] = getelementptr i32* %A, i64 0
> +; CHECK: %[[BltA:[._a-zA-Z0-9]*]] = icmp ult i32* %[[BMax]], %[[AMin]]
> +; CHECK: %[[NoAlias:[._a-zA-Z0-9]*]] = or i1 %[[AltB]], %[[BltA]]
> +; CHECK: %[[RTC:[._a-zA-Z0-9]*]] = and i1 true, %[[NoAlias]]
> +; CHECK: br i1 %[[RTC]], label %polly.start, label %for.cond
> +;
> +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> +
> +define void @jd(i32* %A, i32* %B, i32 %c) {
> +entry:
> + br label %for.cond
> +
> +for.cond: ; preds = %for.inc, %entry
> + %indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
> + %exitcond = icmp ne i64 %indvars.iv, 1024
> + br i1 %exitcond, label %for.body, label %for.end
> +
> +for.body: ; preds = %for.cond
> + %idxprom = sext i32 %c to i64
> + %arrayidx = getelementptr inbounds i32* %B, i64 %idxprom
> + %tmp = load i32* %arrayidx, align 4
> + %arrayidx2 = getelementptr inbounds i32* %A, i64 %indvars.iv
> + store i32 %tmp, i32* %arrayidx2, align 4
> + br label %for.inc
> +
> +for.inc: ; preds = %for.body
> + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
> + br label %for.cond
> +
> +for.end: ; preds = %for.cond
> + ret void
> +}
> diff --git a/test/Isl/CodeGen/aliasing_parametric_simple_2.ll b/test/Isl/CodeGen/aliasing_parametric_simple_2.ll
> new file mode 100644
> index 0000000..2062985
> --- /dev/null
> +++ b/test/Isl/CodeGen/aliasing_parametric_simple_2.ll
> @@ -0,0 +1,57 @@
> +; RUN: opt %loadPolly -polly-codegen-isl -polly-use-runtime-alias-checks -S < %s | FileCheck %s
> +;
> +; void jd(int *A, int *B, int c) {
> +; for (int i = 0; i < 1024; i++)
> +; A[i] = B[c - 10] + B[5];
> +; }
> +;
> +; CHECK: %[[AMax:[._a-zA-Z0-9]*]] = getelementptr i32* %A, i64 1023
> +; CHECK: %[[m0:[._a-zA-Z0-9]*]] = sext i32 %c to i64
> +; CHECK: %[[m1:[._a-zA-Z0-9]*]] = icmp sge i64 %[[m0]], 15
> +; CHECK: %[[m2:[._a-zA-Z0-9]*]] = sext i32 %c to i64
> +; CHECK: %[[m3:[._a-zA-Z0-9]*]] = sub nsw i64 %[[m2]], 10
> +; CHECK: %[[m4:[._a-zA-Z0-9]*]] = select i1 %[[m1]], i64 5, i64 %[[m3]]
> +; CHECK: %[[BMin:[._a-zA-Z0-9]*]] = getelementptr i32* %B, i64 %[[m4]]
> +; CHECK: %[[AltB:[._a-zA-Z0-9]*]] = icmp ult i32* %[[AMax]], %[[BMin]]
> +; CHECK: %[[M0:[._a-zA-Z0-9]*]] = sext i32 %c to i64
> +; CHECK: %[[M1:[._a-zA-Z0-9]*]] = icmp sle i64 %[[M0]], 15
> +; CHECK: %[[M2:[._a-zA-Z0-9]*]] = sext i32 %c to i64
> +; CHECK: %[[M3:[._a-zA-Z0-9]*]] = sub nsw i64 %[[M2]], 10
> +; CHECK: %[[M4:[._a-zA-Z0-9]*]] = select i1 %[[M1]], i64 5, i64 %[[M3]]
> +; CHECK: %[[BMax:[._a-zA-Z0-9]*]] = getelementptr i32* %B, i64 %[[M4]]
> +; CHECK: %[[AMin:[._a-zA-Z0-9]*]] = getelementptr i32* %A, i64 0
> +; CHECK: %[[BltA:[._a-zA-Z0-9]*]] = icmp ult i32* %[[BMax]], %[[AMin]]
> +; CHECK: %[[NoAlias:[._a-zA-Z0-9]*]] = or i1 %[[AltB]], %[[BltA]]
> +; CHECK: %[[RTC:[._a-zA-Z0-9]*]] = and i1 true, %[[NoAlias]]
> +; CHECK: br i1 %[[RTC]], label %polly.start, label %for.cond
> +;
> +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> +
> +define void @jd(i32* %A, i32* %B, i32 %c) {
> +entry:
> + br label %for.cond
> +
> +for.cond: ; preds = %for.inc, %entry
> + %indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
> + %exitcond = icmp ne i64 %indvars.iv, 1024
> + br i1 %exitcond, label %for.body, label %for.end
> +
> +for.body: ; preds = %for.cond
> + %sub = add nsw i32 %c, -10
> + %idxprom = sext i32 %sub to i64
> + %arrayidx = getelementptr inbounds i32* %B, i64 %idxprom
> + %tmp = load i32* %arrayidx, align 4
> + %arrayidx1 = getelementptr inbounds i32* %B, i64 5
> + %tmp1 = load i32* %arrayidx1, align 4
> + %add = add nsw i32 %tmp, %tmp1
> + %arrayidx3 = getelementptr inbounds i32* %A, i64 %indvars.iv
> + store i32 %add, i32* %arrayidx3, align 4
> + br label %for.inc
> +
> +for.inc: ; preds = %for.body
> + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
> + br label %for.cond
> +
> +for.end: ; preds = %for.cond
> + ret void
> +}
> --
> 2.0.4
>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
More information about the llvm-commits
mailing list