mono/linux-packaging-mono
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Imported Upstream version 6.10.0.49

Browse Source 
Former-commit-id: 1d6753294b2993e1fbf92de9366bb9544db4189b
This commit is contained in:
Xamarin Public Jenkins (auto-signing)
2020-01-16 16:38:04 +00:00
parent d94e79959b
commit 468663ddbb
48518 changed files with 2789335 additions and 61176 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
external/llvm-project/polly/test/ScheduleOptimizer/2012-03-16-Empty-Domain.ll vendored Normal file
View File

@@ -0,0 +1,16 @@
; RUN: opt %loadPolly -polly-opt-isl -S < %s
target datalayout = "e-p:32:32:32-i64:64:64-i32:32:32-i16:16:16-i1:32:32-f64:64:64-f32:32:32-a0:0-n32"
define void @sdbout_label() nounwind {
entry:
br label %for.cond
for.cond: ; preds = %for.cond, %entry
%0 = phi i32 [ 0, %entry ], [ %1, %for.cond ]
%1 = add nsw i32 %0, 1
%exitcond72 = icmp eq i32 %1, 7
br i1 %exitcond72, label %sw.epilog66, label %for.cond
sw.epilog66: ; preds = %for.cond
ret void
}

204
external/llvm-project/polly/test/ScheduleOptimizer/2012-04-16-Trivially-vectorizable-loops.ll vendored Normal file
View File

@@ -0,0 +1,204 @@
; RUN: opt %loadPolly -basicaa -polly-opt-isl -polly-vectorizer=polly < %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"
%struct._IO_FILE = type { i32, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, %struct._IO_marker*, %struct._IO_FILE*, i32, i32, i64, i16, i8, [1 x i8], i8*, i64, i8*, i8*, i8*, i8*, i64, i32, [20 x i8] }
%struct._IO_marker = type { %struct._IO_marker*, %struct._IO_FILE*, i32 }
@A = common global [1536 x [1536 x float]] zeroinitializer, align 16
@B = common global [1536 x [1536 x float]] zeroinitializer, align 16
@stdout = external global %struct._IO_FILE*
@.str = private unnamed_addr constant [5 x i8] c"%lf \00", align 1
@C = common global [1536 x [1536 x float]] zeroinitializer, align 16
@.str1 = private unnamed_addr constant [2 x i8] c"\0A\00", align 1
define void @init_array() nounwind uwtable {
entry:
br label %for.cond
for.cond: ; preds = %for.inc17, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc18, %for.inc17 ]
%cmp = icmp slt i32 %i.0, 1536
br i1 %cmp, label %for.body, label %for.end19
for.body: ; preds = %for.cond
br label %for.cond1
for.cond1: ; preds = %for.inc, %for.body
%j.0 = phi i32 [ 0, %for.body ], [ %inc, %for.inc ]
%cmp2 = icmp slt i32 %j.0, 1536
br i1 %cmp2, label %for.body3, label %for.end
for.body3: ; preds = %for.cond1
%mul = mul nsw i32 %i.0, %j.0
%rem = srem i32 %mul, 1024
%add = add nsw i32 1, %rem
%conv = sitofp i32 %add to double
%div = fdiv double %conv, 2.000000e+00
%conv4 = fptrunc double %div to float
%idxprom = sext i32 %j.0 to i64
%idxprom5 = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @A, i32 0, i64 %idxprom5
%arrayidx6 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx, i32 0, i64 %idxprom
store float %conv4, float* %arrayidx6, align 4
%mul7 = mul nsw i32 %i.0, %j.0
%rem8 = srem i32 %mul7, 1024
%add9 = add nsw i32 1, %rem8
%conv10 = sitofp i32 %add9 to double
%div11 = fdiv double %conv10, 2.000000e+00
%conv12 = fptrunc double %div11 to float
%idxprom13 = sext i32 %j.0 to i64
%idxprom14 = sext i32 %i.0 to i64
%arrayidx15 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @B, i32 0, i64 %idxprom14
%arrayidx16 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx15, i32 0, i64 %idxprom13
store float %conv12, float* %arrayidx16, align 4
br label %for.inc
for.inc: ; preds = %for.body3
%inc = add nsw i32 %j.0, 1
br label %for.cond1
for.end: ; preds = %for.cond1
br label %for.inc17
for.inc17: ; preds = %for.end
%inc18 = add nsw i32 %i.0, 1
br label %for.cond
for.end19: ; preds = %for.cond
ret void
}
define void @print_array() nounwind uwtable {
entry:
br label %for.cond
for.cond: ; preds = %for.inc10, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc11, %for.inc10 ]
%cmp = icmp slt i32 %i.0, 1536
br i1 %cmp, label %for.body, label %for.end12
for.body: ; preds = %for.cond
br label %for.cond1
for.cond1: ; preds = %for.inc, %for.body
%j.0 = phi i32 [ 0, %for.body ], [ %inc, %for.inc ]
%cmp2 = icmp slt i32 %j.0, 1536
br i1 %cmp2, label %for.body3, label %for.end
for.body3: ; preds = %for.cond1
%0 = load %struct._IO_FILE*, %struct._IO_FILE** @stdout, align 8
%idxprom = sext i32 %j.0 to i64
%idxprom4 = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom4
%arrayidx5 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx, i32 0, i64 %idxprom
%1 = load float, float* %arrayidx5, align 4
%conv = fpext float %1 to double
%call = call i32 (%struct._IO_FILE*, i8*, ...) @fprintf(%struct._IO_FILE* %0, i8* getelementptr inbounds ([5 x i8], [5 x i8]* @.str, i32 0, i32 0), double %conv)
%rem = srem i32 %j.0, 80
%cmp6 = icmp eq i32 %rem, 79
br i1 %cmp6, label %if.then, label %if.end
if.then: ; preds = %for.body3
%2 = load %struct._IO_FILE*, %struct._IO_FILE** @stdout, align 8
%call8 = call i32 (%struct._IO_FILE*, i8*, ...) @fprintf(%struct._IO_FILE* %2, i8* getelementptr inbounds ([2 x i8], [2 x i8]* @.str1, i32 0, i32 0))
br label %if.end
if.end: ; preds = %if.then, %for.body3
br label %for.inc
for.inc: ; preds = %if.end
%inc = add nsw i32 %j.0, 1
br label %for.cond1
for.end: ; preds = %for.cond1
%3 = load %struct._IO_FILE*, %struct._IO_FILE** @stdout, align 8
%call9 = call i32 (%struct._IO_FILE*, i8*, ...) @fprintf(%struct._IO_FILE* %3, i8* getelementptr inbounds ([2 x i8], [2 x i8]* @.str1, i32 0, i32 0))
br label %for.inc10
for.inc10: ; preds = %for.end
%inc11 = add nsw i32 %i.0, 1
br label %for.cond
for.end12: ; preds = %for.cond
ret void
}
declare i32 @fprintf(%struct._IO_FILE*, i8*, ...)
define i32 @main() nounwind uwtable {
entry:
call void @init_array()
br label %for.cond
for.cond: ; preds = %for.inc28, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc29, %for.inc28 ]
%cmp = icmp slt i32 %i.0, 1536
br i1 %cmp, label %for.body, label %for.end30
for.body: ; preds = %for.cond
br label %for.cond1
for.cond1: ; preds = %for.inc25, %for.body
%j.0 = phi i32 [ 0, %for.body ], [ %inc26, %for.inc25 ]
%cmp2 = icmp slt i32 %j.0, 1536
br i1 %cmp2, label %for.body3, label %for.end27
for.body3: ; preds = %for.cond1
%idxprom = sext i32 %j.0 to i64
%idxprom4 = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom4
%arrayidx5 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx, i32 0, i64 %idxprom
store float 0.000000e+00, float* %arrayidx5, align 4
br label %for.cond6
for.cond6: ; preds = %for.inc, %for.body3
%k.0 = phi i32 [ 0, %for.body3 ], [ %inc, %for.inc ]
%cmp7 = icmp slt i32 %k.0, 1536
br i1 %cmp7, label %for.body8, label %for.end
for.body8: ; preds = %for.cond6
%idxprom9 = sext i32 %j.0 to i64
%idxprom10 = sext i32 %i.0 to i64
%arrayidx11 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom10
%arrayidx12 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx11, i32 0, i64 %idxprom9
%0 = load float, float* %arrayidx12, align 4
%idxprom13 = sext i32 %k.0 to i64
%idxprom14 = sext i32 %i.0 to i64
%arrayidx15 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @A, i32 0, i64 %idxprom14
%arrayidx16 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx15, i32 0, i64 %idxprom13
%1 = load float, float* %arrayidx16, align 4
%idxprom17 = sext i32 %j.0 to i64
%idxprom18 = sext i32 %k.0 to i64
%arrayidx19 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @B, i32 0, i64 %idxprom18
%arrayidx20 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx19, i32 0, i64 %idxprom17
%2 = load float, float* %arrayidx20, align 4
%mul = fmul float %1, %2
%add = fadd float %0, %mul
%idxprom21 = sext i32 %j.0 to i64
%idxprom22 = sext i32 %i.0 to i64
%arrayidx23 = getelementptr inbounds [1536 x [1536 x float]], [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom22
%arrayidx24 = getelementptr inbounds [1536 x float], [1536 x float]* %arrayidx23, i32 0, i64 %idxprom21
store float %add, float* %arrayidx24, align 4
br label %for.inc
for.inc: ; preds = %for.body8
%inc = add nsw i32 %k.0, 1
br label %for.cond6
for.end: ; preds = %for.cond6
br label %for.inc25
for.inc25: ; preds = %for.end
%inc26 = add nsw i32 %j.0, 1
br label %for.cond1
for.end27: ; preds = %for.cond1
br label %for.inc28
for.inc28: ; preds = %for.end27
%inc29 = add nsw i32 %i.0, 1
br label %for.cond
for.end30: ; preds = %for.cond
ret i32 0
}

23
external/llvm-project/polly/test/ScheduleOptimizer/2013-04-11-Empty-Domain-two.ll vendored Normal file
View File

@@ -0,0 +1,23 @@
; RUN: opt %loadPolly -polly-opt-isl -S < %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"
; Check that we handle statements with an empty iteration domain correctly.
define void @f() {
entry:
%A = alloca double
br label %for
for:
%indvar = phi i32 [ %indvar.next, %for.inc ], [ 0, %entry ]
%exitcond = icmp ne i32 %indvar, -1
br i1 %exitcond, label %for.inc, label %return
for.inc:
%indvar.next = add i32 %indvar, 1
store double 1.0, double* %A
br label %for
return:
ret void
}

69
external/llvm-project/polly/test/ScheduleOptimizer/computeout.ll vendored Normal file
View File

@@ -0,0 +1,69 @@
; RUN: opt -S %loadPolly -basicaa -polly-opt-isl -polly-opt-fusion=max -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basicaa -polly-opt-isl -polly-opt-fusion=max -polly-ast -analyze -polly-dependences-computeout=1 < %s | FileCheck %s -check-prefix=TIMEOUT
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"
; for(i = 0; i < 100; i++ )
; S1: A[i] = 2;
;
; for (i = 0; i < 10; i++ )
; S2: A[i] = 5;
;
; for (i = 0; i < 200; i++ )
; S3: A[i] = 5;
define void @sequential_writes() {
entry:
%A = alloca [200 x i32]
br label %S1
S1:
%indvar.1 = phi i64 [ 0, %entry ], [ %indvar.next.1, %S1 ]
%arrayidx.1 = getelementptr [200 x i32], [200 x i32]* %A, i64 0, i64 %indvar.1
store i32 2, i32* %arrayidx.1
%indvar.next.1 = add i64 %indvar.1, 1
%exitcond.1 = icmp ne i64 %indvar.next.1, 100
br i1 %exitcond.1, label %S1, label %exit.1
exit.1:
br label %S2
S2:
%indvar.2 = phi i64 [ 0, %exit.1 ], [ %indvar.next.2, %S2 ]
%arrayidx.2 = getelementptr [200 x i32], [200 x i32]* %A, i64 0, i64 %indvar.2
store i32 5, i32* %arrayidx.2
%indvar.next.2 = add i64 %indvar.2, 1
%exitcond.2 = icmp ne i64 %indvar.next.2, 10
br i1 %exitcond.2, label %S2, label %exit.2
exit.2:
br label %S3
S3:
%indvar.3 = phi i64 [ 0, %exit.2 ], [ %indvar.next.3, %S3 ]
%arrayidx.3 = getelementptr [200 x i32], [200 x i32]* %A, i64 0, i64 %indvar.3
store i32 7, i32* %arrayidx.3
%indvar.next.3 = add i64 %indvar.3, 1
%exitcond.3 = icmp ne i64 %indvar.next.3, 200
br i1 %exitcond.3, label %S3 , label %exit.3
exit.3:
ret void
}
; CHECK: for (int c0 = 0; c0 <= 199; c0 += 1) {
; CHECK: if (c0 <= 99) {
; CHECK: Stmt_S1(c0);
; CHECK: if (c0 <= 9)
; CHECK: Stmt_S2(c0);
; CHECK: }
; CHECK: Stmt_S3(c0);
; CHECK: }
; TIMEOUT: for (int c0 = 0; c0 <= 99; c0 += 1)
; TIMEOUT: Stmt_S1(c0);
; TIMEOUT: for (int c0 = 0; c0 <= 9; c0 += 1)
; TIMEOUT: Stmt_S2(c0);
; TIMEOUT: for (int c0 = 0; c0 <= 199; c0 += 1)
; TIMEOUT: Stmt_S3(c0);

234
external/llvm-project/polly/test/ScheduleOptimizer/ensure-correct-tile-sizes.ll vendored Normal file
View File

@@ -0,0 +1,234 @@
; RUN: opt %loadPolly -analyze -polly-process-unprofitable -polly-remarks-minimal \
; RUN: -polly-opt-isl -polly-pattern-matching-based-opts=true \
; RUN: -polly-target-throughput-vector-fma=1 \
; RUN: -polly-target-latency-vector-fma=1 \
; RUN: -polly-ast -polly-target-vector-register-bitwidth=4096 \
; RUN: -polly-target-1st-cache-level-associativity=3 < %s | FileCheck %s
;
; /* Test that Polly does not crash due to configurations that can lead to
; incorrect tile size computations.
; The parameters are setup such that Car in `getMacroKernelParams`
; is evaluated to 0. */
;
; static const int N = 3000;
;
; void f(int A[N][N], int B[N][N], int C[N][N]) {
; for (int i = 0; i < N; i++) {
; for (int j = 0; j < N; j++) {
; A[i][j] = 0;
; for (int k = 0; k < N; k++) {
; A[i][j] += B[i][k] * C[k][j];
; }
; }
; }
; }
;
; CHECK: // 1st level tiling - Tiles
; CHECK-NEXT: for (int c0 = 0; c0 <= 93; c0 += 1)
; CHECK-NEXT: for (int c1 = 0; c1 <= 93; c1 += 1) {
; CHECK-NEXT: // 1st level tiling - Points
; CHECK-NEXT: for (int c2 = 0; c2 <= min(31, -32 * c0 + 2999); c2 += 1)
; CHECK-NEXT: for (int c3 = 0; c3 <= min(31, -32 * c1 + 2999); c3 += 1)
; CHECK-NEXT: Stmt_for_body3(32 * c0 + c2, 32 * c1 + c3);
; CHECK-NEXT: }
; CHECK-NEXT: // Inter iteration alias-free
; CHECK-NEXT: // Register tiling - Tiles
; CHECK-NEXT: for (int c0 = 0; c0 <= 23; c0 += 1)
; CHECK-NEXT: for (int c1 = 0; c1 <= 2999; c1 += 1)
; CHECK-NEXT: for (int c2 = 0; c2 <= 2999; c2 += 1) {
; CHECK-NEXT: // Register tiling - Points
; CHECK-NEXT: {
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 1, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 2, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 3, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 4, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 5, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 6, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 7, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 8, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 9, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 10, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 11, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 12, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 13, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 14, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 15, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 16, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 17, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 18, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 19, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 20, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 21, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 22, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 23, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 24, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 25, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 26, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 27, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 28, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 29, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 30, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 31, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 32, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 33, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 34, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 35, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 36, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 37, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 38, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 39, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 40, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 41, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 42, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 43, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 44, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 45, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 46, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 47, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 48, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 49, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 50, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 51, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 52, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 53, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 54, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 55, c2);
; CHECK-NEXT: if (c0 <= 22) {
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 56, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 57, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 58, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 59, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 60, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 61, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 62, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 63, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 64, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 65, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 66, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 67, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 68, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 69, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 70, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 71, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 72, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 73, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 74, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 75, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 76, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 77, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 78, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 79, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 80, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 81, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 82, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 83, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 84, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 85, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 86, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 87, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 88, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 89, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 90, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 91, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 92, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 93, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 94, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 95, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 96, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 97, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 98, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 99, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 100, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 101, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 102, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 103, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 104, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 105, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 106, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 107, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 108, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 109, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 110, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 111, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 112, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 113, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 114, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 115, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 116, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 117, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 118, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 119, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 120, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 121, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 122, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 123, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 124, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 125, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 126, c2);
; CHECK-NEXT: Stmt_for_body8(c1, 128 * c0 + 127, c2);
; CHECK-NEXT: }
; CHECK-NEXT: }
; CHECK-NEXT: }
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
define void @f([3000 x i32]* %A, [3000 x i32]* %B, [3000 x i32]* %C) {
entry:
br label %for.cond
for.cond: ; preds = %for.inc24, %entry
%indvars.iv4 = phi i64 [ %indvars.iv.next5, %for.inc24 ], [ 0, %entry ]
%exitcond6 = icmp ne i64 %indvars.iv4, 3000
br i1 %exitcond6, label %for.body, label %for.end26
for.body: ; preds = %for.cond
br label %for.cond1
for.cond1: ; preds = %for.inc21, %for.body
%indvars.iv1 = phi i64 [ %indvars.iv.next2, %for.inc21 ], [ 0, %for.body ]
%exitcond3 = icmp ne i64 %indvars.iv1, 3000
br i1 %exitcond3, label %for.body3, label %for.end23
for.body3: ; preds = %for.cond1
%arrayidx5 = getelementptr inbounds [3000 x i32], [3000 x i32]* %A, i64 %indvars.iv4, i64 %indvars.iv1
store i32 0, i32* %arrayidx5, align 4
br label %for.cond6
for.cond6: ; preds = %for.inc, %for.body3
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %for.body3 ]
%exitcond = icmp ne i64 %indvars.iv, 3000
br i1 %exitcond, label %for.body8, label %for.end
for.body8: ; preds = %for.cond6
%arrayidx12 = getelementptr inbounds [3000 x i32], [3000 x i32]* %B, i64 %indvars.iv4, i64 %indvars.iv
%tmp = load i32, i32* %arrayidx12, align 4
%arrayidx16 = getelementptr inbounds [3000 x i32], [3000 x i32]* %C, i64 %indvars.iv, i64 %indvars.iv1
%tmp7 = load i32, i32* %arrayidx16, align 4
%mul = mul nsw i32 %tmp, %tmp7
%arrayidx20 = getelementptr inbounds [3000 x i32], [3000 x i32]* %A, i64 %indvars.iv4, i64 %indvars.iv1
%tmp8 = load i32, i32* %arrayidx20, align 4
%add = add nsw i32 %tmp8, %mul
store i32 %add, i32* %arrayidx20, align 4
br label %for.inc
for.inc: ; preds = %for.body8
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
br label %for.cond6
for.end: ; preds = %for.cond6
br label %for.inc21
for.inc21: ; preds = %for.end
%indvars.iv.next2 = add nuw nsw i64 %indvars.iv1, 1
br label %for.cond1
for.end23: ; preds = %for.cond1
br label %for.inc24
for.inc24: ; preds = %for.end23
%indvars.iv.next5 = add nuw nsw i64 %indvars.iv4, 1
br label %for.cond
for.end26: ; preds = %for.cond
ret void
}

91
external/llvm-project/polly/test/ScheduleOptimizer/full_partial_tile_separation.ll vendored Normal file
View File

@@ -0,0 +1,91 @@
; RUN: opt -S %loadPolly -polly-pattern-matching-based-opts=false \
; RUN: -polly-vectorizer=stripmine -polly-opt-isl -polly-ast -analyze \
; RUN: < %s | FileCheck %s
; CHECK: // 1st level tiling - Tiles
; CHECK-NEXT: #pragma known-parallel
; CHECK-NEXT: for (int c0 = 0; c0 <= floord(ni - 1, 32); c0 += 1)
; CHECK-NEXT: for (int c1 = 0; c1 <= floord(nj - 1, 32); c1 += 1)
; CHECK-NEXT: for (int c2 = 0; c2 <= floord(nk - 1, 32); c2 += 1) {
; CHECK-NEXT: // 1st level tiling - Points
; CHECK-NEXT: for (int c3 = 0; c3 <= min(31, ni - 32 * c0 - 1); c3 += 1) {
; CHECK-NEXT: for (int c4 = 0; c4 <= min(7, -8 * c1 + nj / 4 - 1); c4 += 1)
; CHECK-NEXT: for (int c5 = 0; c5 <= min(31, nk - 32 * c2 - 1); c5 += 1) {
; CHECK-NEXT: // SIMD
; CHECK-NEXT: for (int c6 = 0; c6 <= 3; c6 += 1)
; CHECK-NEXT: Stmt_for_body_6(32 * c0 + c3, 32 * c1 + 4 * c4 + c6, 32 * c2 + c5);
; CHECK-NEXT: }
; CHECK-NEXT: if (32 * c1 + 31 >= nj)
; CHECK-NEXT: #pragma minimal dependence distance: 1
; CHECK-NEXT: for (int c5 = 0; c5 <= min(31, nk - 32 * c2 - 1); c5 += 1) {
; CHECK-NEXT: // SIMD
; CHECK-NEXT: for (int c6 = 0; c6 < nj % 4; c6 += 1)
; CHECK-NEXT: Stmt_for_body_6(32 * c0 + c3, -(nj % 4) + nj + c6, 32 * c2 + c5);
; CHECK-NEXT: }
; CHECK-NEXT: }
; CHECK-NEXT: }
; Function Attrs: nounwind uwtable
define void @kernel_gemm(i32 %ni, i32 %nj, i32 %nk, double %alpha, double %beta, [1024 x double]* %C, [1024 x double]* %A, [1024 x double]* %B) #0 {
entry:
%cmp.27 = icmp sgt i32 %ni, 0
br i1 %cmp.27, label %for.cond.1.preheader.lr.ph, label %for.end.22
for.cond.1.preheader.lr.ph: ; preds = %entry
br label %for.cond.1.preheader
for.cond.1.preheader: ; preds = %for.cond.1.preheader.lr.ph, %for.inc.20
%indvars.iv33 = phi i64 [ 0, %for.cond.1.preheader.lr.ph ], [ %indvars.iv.next34, %for.inc.20 ]
%cmp2.25 = icmp sgt i32 %nj, 0
br i1 %cmp2.25, label %for.cond.4.preheader.lr.ph, label %for.inc.20
for.cond.4.preheader.lr.ph: ; preds = %for.cond.1.preheader
br label %for.cond.4.preheader
for.cond.4.preheader: ; preds = %for.cond.4.preheader.lr.ph, %for.inc.17
%indvars.iv29 = phi i64 [ 0, %for.cond.4.preheader.lr.ph ], [ %indvars.iv.next30, %for.inc.17 ]
%cmp5.23 = icmp sgt i32 %nk, 0
br i1 %cmp5.23, label %for.body.6.lr.ph, label %for.inc.17
for.body.6.lr.ph: ; preds = %for.cond.4.preheader
br label %for.body.6
for.body.6: ; preds = %for.body.6.lr.ph, %for.body.6
%indvars.iv = phi i64 [ 0, %for.body.6.lr.ph ], [ %indvars.iv.next, %for.body.6 ]
%arrayidx8 = getelementptr inbounds [1024 x double], [1024 x double]* %A, i64 %indvars.iv33, i64 %indvars.iv
%0 = load double, double* %arrayidx8, align 8
%arrayidx12 = getelementptr inbounds [1024 x double], [1024 x double]* %B, i64 %indvars.iv, i64 %indvars.iv29
%1 = load double, double* %arrayidx12, align 8
%mul = fmul double %0, %1
%arrayidx16 = getelementptr inbounds [1024 x double], [1024 x double]* %C, i64 %indvars.iv33, i64 %indvars.iv29
%2 = load double, double* %arrayidx16, align 8
%add = fadd double %2, %mul
store double %add, double* %arrayidx16, align 8
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp ne i32 %lftr.wideiv, %nk
br i1 %exitcond, label %for.body.6, label %for.cond.4.for.inc.17_crit_edge
for.cond.4.for.inc.17_crit_edge: ; preds = %for.body.6
br label %for.inc.17
for.inc.17: ; preds = %for.cond.4.for.inc.17_crit_edge, %for.cond.4.preheader
%indvars.iv.next30 = add nuw nsw i64 %indvars.iv29, 1
%lftr.wideiv31 = trunc i64 %indvars.iv.next30 to i32
%exitcond32 = icmp ne i32 %lftr.wideiv31, %nj
br i1 %exitcond32, label %for.cond.4.preheader, label %for.cond.1.for.inc.20_crit_edge
for.cond.1.for.inc.20_crit_edge: ; preds = %for.inc.17
br label %for.inc.20
for.inc.20: ; preds = %for.cond.1.for.inc.20_crit_edge, %for.cond.1.preheader
%indvars.iv.next34 = add nuw nsw i64 %indvars.iv33, 1
%lftr.wideiv35 = trunc i64 %indvars.iv.next34 to i32
%exitcond36 = icmp ne i32 %lftr.wideiv35, %ni
br i1 %exitcond36, label %for.cond.1.preheader, label %for.cond.for.end.22_crit_edge
for.cond.for.end.22_crit_edge: ; preds = %for.inc.20
br label %for.end.22
for.end.22: ; preds = %for.cond.for.end.22_crit_edge, %entry
ret void
}

55
external/llvm-project/polly/test/ScheduleOptimizer/kernel_gemm___%for.body---%for.end24.jscop vendored Normal file
View File

@@ -0,0 +1,55 @@
{
"arrays" : [
{
"name" : "MemRef_C1",
"sizes" : [ "*" ],
"type" : "double"
},
{
"name" : "MemRef_A",
"sizes" : [ "*", "1024" ],
"type" : "double"
},
{
"name" : "MemRef_B",
"sizes" : [ "*", "1024" ],
"type" : "double"
},
{
"name" : "MemRef_C",
"sizes" : [ "*", "1024" ],
"type" : "double"
}
],
"context" : "{ : }",
"name" : "%for.body---%for.end24",
"statements" : [
{
"accesses" : [
{
"kind" : "read",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C1[0] }"
},
{
"kind" : "read",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_A[i0, i2] }"
},
{
"kind" : "read",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_B[i2, i1] }"
},
{
"kind" : "read",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C[i0, i1] }"
},
{
"kind" : "write",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C[i0, i1] }"
}
],
"domain" : "{ Stmt_for_body6[i0, i1, i2] : 0 <= i0 <= 1023 and 0 <= i1 <= 1023 and 0 <= i2 <= 1023 }",
"name" : "Stmt_for_body6",
"schedule" : "{ Stmt_for_body6[i0, i1, i2] -> [i0, i1, i2] }"
}
]
}

55
external/llvm-project/polly/test/ScheduleOptimizer/kernel_gemm___%for.body---%for.end24.jscop.transformed vendored Normal file
View File

@@ -0,0 +1,55 @@
{
"arrays" : [
{
"name" : "MemRef_C1",
"sizes" : [ "*" ],
"type" : "double"
},
{
"name" : "MemRef_A",
"sizes" : [ "*", "1024" ],
"type" : "double"
},
{
"name" : "MemRef_B",
"sizes" : [ "*", "1024" ],
"type" : "double"
},
{
"name" : "MemRef_C",
"sizes" : [ "*", "1024" ],
"type" : "double"
}
],
"context" : "{ : }",
"name" : "%for.body---%for.end24",
"statements" : [
{
"accesses" : [
{
"kind" : "read",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C[i0, i1] }"
},
{
"kind" : "read",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_A[i0, i2] }"
},
{
"kind" : "read",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_B[i2, i1] }"
},
{
"kind" : "read",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C1[0] }"
},
{
"kind" : "write",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C[i0, i1] }"
}
],
"domain" : "{ Stmt_for_body6[i0, i1, i2] : 0 <= i0 <= 1023 and 0 <= i1 <= 1023 and 0 <= i2 <= 1023 }",
"name" : "Stmt_for_body6",
"schedule" : "{ Stmt_for_body6[i0, i1, i2] -> [i0, i1, i2] }"
}
]
}

46
external/llvm-project/polly/test/ScheduleOptimizer/kernel_gemm___%for.cond1.preheader---%for.end18.jscop.transformed vendored Normal file
View File

@@ -0,0 +1,46 @@
{
"arrays" : [
{
"name" : "MemRef_B",
"sizes" : [ "*", "1024" ],
"type" : "double"
},
{
"name" : "MemRef_C",
"sizes" : [ "*", "1024" ],
"type" : "double"
},
{
"name" : "New_MemRef_A",
"sizes" : [ "1024", "1024" ],
"type" : "double"
}
],
"context" : "{ : }",
"name" : "%for.cond1.preheader---%for.end18",
"statements" : [
{
"accesses" : [
{
"kind" : "read",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_B[i2, i1] }"
},
{
"kind" : "read",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> New_MemRef_A[i0, i2] }"
},
{
"kind" : "read",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C[i0, i1] }"
},
{
"kind" : "write",
"relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C[i0, i1] }"
}
],
"domain" : "{ Stmt_for_body6[i0, i1, i2] : 0 <= i0 <= 1023 and 0 <= i1 <= 1023 and 0 <= i2 <= 1023 }",
"name" : "Stmt_for_body6",
"schedule" : "{ Stmt_for_body6[i0, i1, i2] -> [i0, i1, i2] }"
}
]
}

40
external/llvm-project/polly/test/ScheduleOptimizer/line-tiling-2.ll vendored Normal file
View File

@@ -0,0 +1,40 @@
; RUN: opt %loadPolly -polly-opt-isl -analyze \
; RUN: -polly-ast -polly-tile-sizes=1,64 < %s | FileCheck %s
; CHECK: for (int c0 = 0; c0 <= 1023; c0 += 1)
; CHECK: for (int c1 = 0; c1 <= 7; c1 += 1)
; CHECK: for (int c3 = 0; c3 <= 63; c3 += 1)
; CHECK: Stmt_for_body3(c0, 64 * c1 + c3);
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-n32-S64"
; Function Attrs: nounwind
define void @line([512 x i32]* %A) {
entry:
br label %entry.split
entry.split: ; preds = %entry
br label %for.body3.lr.ph
for.body3.lr.ph: ; preds = %for.inc5, %entry.split
%i.0 = phi i32 [ 0, %entry.split ], [ %inc6, %for.inc5 ]
br label %for.body3
for.body3: ; preds = %for.body3.lr.ph, %for.body3
%j.0 = phi i32 [ 0, %for.body3.lr.ph ], [ %inc, %for.body3 ]
%mul = mul nsw i32 %j.0, %i.0
%rem = srem i32 %mul, 42
%arrayidx4 = getelementptr inbounds [512 x i32], [512 x i32]* %A, i32 %i.0, i32 %j.0
store i32 %rem, i32* %arrayidx4, align 4
%inc = add nsw i32 %j.0, 1
%cmp2 = icmp slt i32 %inc, 512
br i1 %cmp2, label %for.body3, label %for.inc5
for.inc5: ; preds = %for.body3
%inc6 = add nsw i32 %i.0, 1
%cmp = icmp slt i32 %inc6, 1024
br i1 %cmp, label %for.body3.lr.ph, label %for.end7
for.end7: ; preds = %for.inc5
ret void
}

39
external/llvm-project/polly/test/ScheduleOptimizer/line-tiling.ll vendored Normal file
View File

@@ -0,0 +1,39 @@
; RUN: opt %loadPolly -polly-opt-isl -analyze -polly-ast -polly-tile-sizes=64,1 < %s | FileCheck %s
; CHECK: for (int c0 = 0; c0 <= 15; c0 += 1)
; CHECK: for (int c1 = 0; c1 <= 511; c1 += 1)
; CHECK: for (int c2 = 0; c2 <= 63; c2 += 1)
; CHECK: Stmt_for_body3(64 * c0 + c2, c1);
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-n32-S64"
; Function Attrs: nounwind
define void @line([512 x i32]* %A) {
entry:
br label %entry.split
entry.split: ; preds = %entry
br label %for.body3.lr.ph
for.body3.lr.ph: ; preds = %for.inc5, %entry.split
%i.0 = phi i32 [ 0, %entry.split ], [ %inc6, %for.inc5 ]
br label %for.body3
for.body3: ; preds = %for.body3.lr.ph, %for.body3
%j.0 = phi i32 [ 0, %for.body3.lr.ph ], [ %inc, %for.body3 ]
%mul = mul nsw i32 %j.0, %i.0
%rem = srem i32 %mul, 42
%arrayidx4 = getelementptr inbounds [512 x i32], [512 x i32]* %A, i32 %i.0, i32 %j.0
store i32 %rem, i32* %arrayidx4, align 4
%inc = add nsw i32 %j.0, 1
%cmp2 = icmp slt i32 %inc, 512
br i1 %cmp2, label %for.body3, label %for.inc5
for.inc5: ; preds = %for.body3
%inc6 = add nsw i32 %i.0, 1
%cmp = icmp slt i32 %inc6, 1024
br i1 %cmp, label %for.body3.lr.ph, label %for.end7
for.end7: ; preds = %for.inc5
ret void
}

101
external/llvm-project/polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout.ll vendored Normal file
View File

@@ -0,0 +1,101 @@
; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true \
; RUN: -polly-target-throughput-vector-fma=1 \
; RUN: -polly-target-latency-vector-fma=8 \
; RUN: -polly-target-1st-cache-level-associativity=8 \
; RUN: -polly-target-2nd-cache-level-associativity=8 \
; RUN: -polly-target-1st-cache-level-size=32768 \
; RUN: -polly-target-2nd-cache-level-size=262144 \
; RUN: -polly-optimized-scops \
; RUN: -polly-target-vector-register-bitwidth=256 \
; RUN: -disable-output < %s 2>&1 | FileCheck %s
;
; /* C := alpha*A*B + beta*C */
; for (i = 0; i < _PB_NI; i++)
; for (j = 0; j < _PB_NJ; j++)
; {
; C[i][j] *= beta;
; for (k = 0; k < _PB_NK; ++k)
; C[i][j] += alpha * A[i][k] * B[k][j];
; }
;
; CHECK: double Packed_B[ { [] -> [(256)] } ][ { [] -> [(256)] } ][ { [] -> [(8)] } ];
; CHECK-NEXT: double Packed_A[ { [] -> [(24)] } ][ { [] -> [(256)] } ][ { [] -> [(4)] } ]; // Element size 8
;
; CHECK: { Stmt_Copy_0[i0, i1, i2] -> MemRef_arg6[i0, i2] };
; CHECK-NEXT: new: { Stmt_Copy_0[i0, i1, i2] -> Packed_A[o0, o1, o2] : 256*floor((-i2 + o1)/256) = -i2 + o1 and 96*floor((-i0 + 4o0 + o2)/96) = -i0 + 4o0 + o2 and 0 <= o1 <= 255 and o2 >= 0 and -4o0 <= o2 <= 95 - 4o0 and o2 <= 3 };
;
; CHECK: { Stmt_Copy_0[i0, i1, i2] -> MemRef_arg7[i2, i1] };
; CHECK-NEXT: new: { Stmt_Copy_0[i0, i1, i2] -> Packed_B[o0, o1, i1 - 8o0] : 256*floor((-i2 + o1)/256) = -i2 + o1 and -7 + i1 <= 8o0 <= i1 and 0 <= o1 <= 255 };
;
; CHECK: CopyStmt_0
; CHECK-NEXT: Domain :=
; CHECK-NEXT: { CopyStmt_0[i0, i1, i2] : 0 <= i0 <= 1055 and 0 <= i1 <= 1055 and 0 <= i2 <= 1023 };
; CHECK-NEXT: Schedule :=
; CHECK-NEXT: ;
; CHECK-NEXT: MustWriteAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK-NEXT: ;
; CHECK-NEXT: new: { CopyStmt_0[i0, i1, i2] -> Packed_B[o0, o1, i1 - 8o0] : 256*floor((-i2 + o1)/256) = -i2 + o1 and -7 + i1 <= 8o0 <= i1 and 0 <= o1 <= 255 };
; CHECK-NEXT: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK-NEXT: ;
; CHECK-NEXT: new: { CopyStmt_0[i0, i1, i2] -> MemRef_arg7[i2, i1] };
; CHECK-NEXT: CopyStmt_1
; CHECK-NEXT: Domain :=
; CHECK-NEXT: { CopyStmt_1[i0, i1, i2] : 0 <= i0 <= 1055 and 0 <= i1 <= 1055 and 0 <= i2 <= 1023 };
; CHECK-NEXT: Schedule :=
; CHECK-NEXT: ;
; CHECK-NEXT: MustWriteAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK-NEXT: ;
; CHECK-NEXT: new: { CopyStmt_1[i0, i1, i2] -> Packed_A[o0, o1, o2] : 256*floor((-i2 + o1)/256) = -i2 + o1 and 96*floor((-i0 + 4o0 + o2)/96) = -i0 + 4o0 + o2 and 0 <= o1 <= 255 and o2 >= 0 and -4o0 <= o2 <= 95 - 4o0 and o2 <= 3 };
; CHECK-NEXT: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK-NEXT: ;
; CHECK-NEXT: new: { CopyStmt_1[i0, i1, i2] -> MemRef_arg6[i0, i2] };
;
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-unknown"
define internal void @kernel_gemm(i32 %arg, i32 %arg1, i32 %arg2, double %arg3, double %arg4, [1056 x double]* %arg5, [1024 x double]* %arg6, [1056 x double]* %arg7) #0 {
bb:
br label %bb8
bb8: ; preds = %bb29, %bb
%tmp = phi i64 [ 0, %bb ], [ %tmp30, %bb29 ]
br label %bb9
bb9: ; preds = %bb26, %bb8
%tmp10 = phi i64 [ 0, %bb8 ], [ %tmp27, %bb26 ]
%tmp11 = getelementptr inbounds [1056 x double], [1056 x double]* %arg5, i64 %tmp, i64 %tmp10
%tmp12 = load double, double* %tmp11, align 8
%tmp13 = fmul double %tmp12, %arg4
store double %tmp13, double* %tmp11, align 8
br label %Copy_0
Copy_0: ; preds = %Copy_0, %bb9
%tmp15 = phi i64 [ 0, %bb9 ], [ %tmp24, %Copy_0 ]
%tmp16 = getelementptr inbounds [1024 x double], [1024 x double]* %arg6, i64 %tmp, i64 %tmp15
%tmp17 = load double, double* %tmp16, align 8
%tmp18 = fmul double %tmp17, %arg3
%tmp19 = getelementptr inbounds [1056 x double], [1056 x double]* %arg7, i64 %tmp15, i64 %tmp10
%tmp20 = load double, double* %tmp19, align 8
%tmp21 = fmul double %tmp18, %tmp20
%tmp22 = load double, double* %tmp11, align 8
%tmp23 = fadd double %tmp22, %tmp21
store double %tmp23, double* %tmp11, align 8
%tmp24 = add nuw nsw i64 %tmp15, 1
%tmp25 = icmp ne i64 %tmp24, 1024
br i1 %tmp25, label %Copy_0, label %bb26
bb26: ; preds = %Copy_0
%tmp27 = add nuw nsw i64 %tmp10, 1
%tmp28 = icmp ne i64 %tmp27, 1056
br i1 %tmp28, label %bb9, label %bb29
bb29: ; preds = %bb26
%tmp30 = add nuw nsw i64 %tmp, 1
%tmp31 = icmp ne i64 %tmp30, 1056
br i1 %tmp31, label %bb8, label %bb32
bb32: ; preds = %bb29
ret void
}
attributes #0 = { nounwind uwtable "target-cpu"="x86-64" "target-features"="+aes,+avx,+cmov,+cx16,+fxsr,+mmx,+pclmul,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsaveopt" }

134
external/llvm-project/polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout_2.ll vendored Normal file
View File

@@ -0,0 +1,134 @@
; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true \
; RUN: -polly-target-throughput-vector-fma=1 \
; RUN: -polly-target-latency-vector-fma=8 \
; RUN: -polly-target-1st-cache-level-associativity=8 \
; RUN: -polly-target-2nd-cache-level-associativity=8 \
; RUN: -polly-target-1st-cache-level-size=32768 \
; RUN: -polly-target-2nd-cache-level-size=262144 -polly-ast \
; RUN: -polly-target-vector-register-bitwidth=256 \
; RUN: -analyze < %s | FileCheck %s
;
; /* C := alpha*A*B + beta*C */
; /* _PB_NK % Kc != 0 */
; for (i = 0; i < _PB_NI; i++)
; for (j = 0; j < _PB_NJ; j++)
; {
; C[i][j] *= beta;
; for (k = 0; k < _PB_NK; ++k)
; C[i][j] += alpha * A[i][k] * B[k][j];
; }
;
; CHECK: {
; CHECK-NEXT: // 1st level tiling - Tiles
; CHECK-NEXT: for (int c0 = 0; c0 <= 32; c0 += 1)
; CHECK-NEXT: for (int c1 = 0; c1 <= 32; c1 += 1) {
; CHECK-NEXT: // 1st level tiling - Points
; CHECK-NEXT: for (int c2 = 0; c2 <= 31; c2 += 1)
; CHECK-NEXT: for (int c3 = 0; c3 <= 31; c3 += 1)
; CHECK-NEXT: Stmt_bb9(32 * c0 + c2, 32 * c1 + c3);
; CHECK-NEXT: }
; CHECK-NEXT: // Inter iteration alias-free
; CHECK-NEXT: // 1st level tiling - Tiles
; CHECK-NEXT: for (int c1 = 0; c1 <= 3; c1 += 1) {
; CHECK-NEXT: for (int c3 = 0; c3 <= 1055; c3 += 1)
; CHECK-NEXT: for (int c4 = 256 * c1; c4 <= min(1022, 256 * c1 + 255); c4 += 1)
; CHECK-NEXT: CopyStmt_0(0, c3, c4);
; CHECK-NEXT: for (int c2 = 0; c2 <= 10; c2 += 1) {
; CHECK-NEXT: for (int c3 = 96 * c2; c3 <= 96 * c2 + 95; c3 += 1)
; CHECK-NEXT: for (int c5 = 256 * c1; c5 <= min(1022, 256 * c1 + 255); c5 += 1)
; CHECK-NEXT: CopyStmt_1(c3, 0, c5);
; CHECK-NEXT: // 1st level tiling - Points
; CHECK-NEXT: // Register tiling - Tiles
; CHECK-NEXT: for (int c3 = 0; c3 <= 131; c3 += 1)
; CHECK-NEXT: for (int c4 = 0; c4 <= 23; c4 += 1)
; CHECK-NEXT: for (int c5 = 0; c5 <= min(255, -256 * c1 + 1022); c5 += 1) {
; CHECK-NEXT: // Loop Vectorizer Disabled
; CHECK-NEXT: // Register tiling - Points
; CHECK-NEXT: {
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 1, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 2, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 3, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 4, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 5, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 6, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 7, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 1, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 2, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 3, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 4, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 5, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 6, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 7, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 1, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 2, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 3, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 4, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 5, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 6, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 7, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 1, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 2, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 3, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 4, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 5, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 6, 256 * c1 + c5);
; CHECK-NEXT: Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 7, 256 * c1 + c5);
; CHECK-NEXT: }
; CHECK-NEXT: }
; CHECK-NEXT: }
; CHECK-NEXT: }
; CHECK-NEXT: }
;
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-unknown"
define internal void @kernel_gemm(i32 %arg, i32 %arg1, i32 %arg2, double %arg3, double %arg4, [1056 x double]* %arg5, [1023 x double]* %arg6, [1056 x double]* %arg7) #0 {
bb:
br label %bb8
bb8: ; preds = %bb29, %bb
%tmp = phi i64 [ 0, %bb ], [ %tmp30, %bb29 ]
br label %bb9
bb9: ; preds = %bb26, %bb8
%tmp10 = phi i64 [ 0, %bb8 ], [ %tmp27, %bb26 ]
%tmp11 = getelementptr inbounds [1056 x double], [1056 x double]* %arg5, i64 %tmp, i64 %tmp10
%tmp12 = load double, double* %tmp11, align 8
%tmp13 = fmul double %tmp12, %arg4
store double %tmp13, double* %tmp11, align 8
br label %Copy_0
Copy_0: ; preds = %Copy_0, %bb9
%tmp15 = phi i64 [ 0, %bb9 ], [ %tmp24, %Copy_0 ]
%tmp16 = getelementptr inbounds [1023 x double], [1023 x double]* %arg6, i64 %tmp, i64 %tmp15
%tmp17 = load double, double* %tmp16, align 8
%tmp18 = fmul double %tmp17, %arg3
%tmp19 = getelementptr inbounds [1056 x double], [1056 x double]* %arg7, i64 %tmp15, i64 %tmp10
%tmp20 = load double, double* %tmp19, align 8
%tmp21 = fmul double %tmp18, %tmp20
%tmp22 = load double, double* %tmp11, align 8
%tmp23 = fadd double %tmp22, %tmp21
store double %tmp23, double* %tmp11, align 8
%tmp24 = add nuw nsw i64 %tmp15, 1
%tmp25 = icmp ne i64 %tmp24, 1023
br i1 %tmp25, label %Copy_0, label %bb26
bb26: ; preds = %Copy_0
%tmp27 = add nuw nsw i64 %tmp10, 1
%tmp28 = icmp ne i64 %tmp27, 1056
br i1 %tmp28, label %bb9, label %bb29
bb29: ; preds = %bb26
%tmp30 = add nuw nsw i64 %tmp, 1
%tmp31 = icmp ne i64 %tmp30, 1056
br i1 %tmp31, label %bb8, label %bb32
bb32: ; preds = %bb29
ret void
}
attributes #0 = { nounwind uwtable "target-cpu"="x86-64" "target-features"="+aes,+avx,+cmov,+cx16,+fxsr,+mmx,+pclmul,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsaveopt" }

107
external/llvm-project/polly/test/ScheduleOptimizer/one-dimensional-band.ll vendored Normal file
View File

@@ -0,0 +1,107 @@
; RUN: opt %loadPolly -polly-opt-isl -polly-ast -analyze < %s | FileCheck %s
;
; void jacobi1d(long T, long N, float *A, float *B) {
; long t, i, j;
; for (t = 0; t < T; t++) {
; for (i = 1; i < N - 1; i++)
; B[i] = 0.33333 * (A[i - 1] + A[i] + A[i + 1]);
; for (j = 1; j < N - 1; j++)
; A[j] = 0.33333 * (B[i - 1] + B[i] + B[i + 1]);
; }
; }
; Verify that we do not tile bands that have just a single dimension.
; CHECK: for (int c0 = 0; c0 < T; c0 += 1) {
; CHECK: for (int c1 = 0; c1 < N - 2; c1 += 1)
; CHECK: Stmt_for_body3(c0, c1);
; CHECK: for (int c1 = 0; c1 < N - 2; c1 += 1)
; CHECK: Stmt_for_body15(c0, c1);
; CHECK: }
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
define void @jacobi1d(i64 %T, i64 %N, float* %A, float* %B) {
entry:
%tmp = add i64 %N, -1
%tmp1 = icmp sgt i64 %tmp, 1
%smax = select i1 %tmp1, i64 %tmp, i64 1
br label %for.cond
for.cond: ; preds = %for.inc30, %entry
%t.0 = phi i64 [ 0, %entry ], [ %inc31, %for.inc30 ]
%cmp = icmp slt i64 %t.0, %T
br i1 %cmp, label %for.body, label %for.end32
for.body: ; preds = %for.cond
br label %for.cond1
for.cond1: ; preds = %for.inc, %for.body
%i.0 = phi i64 [ 1, %for.body ], [ %inc, %for.inc ]
%sub = add nsw i64 %N, -1
%cmp2 = icmp slt i64 %i.0, %sub
br i1 %cmp2, label %for.body3, label %for.end
for.body3: ; preds = %for.cond1
%sub4 = add nsw i64 %i.0, -1
%arrayidx = getelementptr inbounds float, float* %A, i64 %sub4
%tmp2 = load float, float* %arrayidx, align 4
%arrayidx5 = getelementptr inbounds float, float* %A, i64 %i.0
%tmp3 = load float, float* %arrayidx5, align 4
%add = fadd float %tmp2, %tmp3
%add6 = add nuw nsw i64 %i.0, 1
%arrayidx7 = getelementptr inbounds float, float* %A, i64 %add6
%tmp4 = load float, float* %arrayidx7, align 4
%add8 = fadd float %add, %tmp4
%conv = fpext float %add8 to double
%mul = fmul double %conv, 3.333300e-01
%conv9 = fptrunc double %mul to float
%arrayidx10 = getelementptr inbounds float, float* %B, i64 %i.0
store float %conv9, float* %arrayidx10, align 4
br label %for.inc
for.inc: ; preds = %for.body3
%inc = add nuw nsw i64 %i.0, 1
br label %for.cond1
for.end: ; preds = %for.cond1
br label %for.cond11
for.cond11: ; preds = %for.inc27, %for.end
%j.0 = phi i64 [ 1, %for.end ], [ %inc28, %for.inc27 ]
%sub12 = add nsw i64 %N, -1
%cmp13 = icmp slt i64 %j.0, %sub12
br i1 %cmp13, label %for.body15, label %for.end29
for.body15: ; preds = %for.cond11
%sub16 = add nsw i64 %smax, -1
%arrayidx17 = getelementptr inbounds float, float* %B, i64 %sub16
%tmp5 = load float, float* %arrayidx17, align 4
%arrayidx18 = getelementptr inbounds float, float* %B, i64 %smax
%tmp6 = load float, float* %arrayidx18, align 4
%add19 = fadd float %tmp5, %tmp6
%add20 = add nsw i64 %smax, 1
%arrayidx21 = getelementptr inbounds float, float* %B, i64 %add20
%tmp7 = load float, float* %arrayidx21, align 4
%add22 = fadd float %add19, %tmp7
%conv23 = fpext float %add22 to double
%mul24 = fmul double %conv23, 3.333300e-01
%conv25 = fptrunc double %mul24 to float
%arrayidx26 = getelementptr inbounds float, float* %A, i64 %j.0
store float %conv25, float* %arrayidx26, align 4
br label %for.inc27
for.inc27: ; preds = %for.body15
%inc28 = add nuw nsw i64 %j.0, 1
br label %for.cond11
for.end29: ; preds = %for.cond11
br label %for.inc30
for.inc30: ; preds = %for.end29
%inc31 = add nuw nsw i64 %t.0, 1
br label %for.cond
for.end32: ; preds = %for.cond
ret void
}

69
external/llvm-project/polly/test/ScheduleOptimizer/outer_coincidence.ll vendored Normal file
View File

@@ -0,0 +1,69 @@
; RUN: opt %loadPolly -polly-opt-isl -polly-ast -polly-tiling=0 -polly-parallel -polly-opt-outer-coincidence=no -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -polly-opt-isl -polly-ast -polly-tiling=0 -polly-parallel -polly-opt-outer-coincidence=yes -analyze < %s | FileCheck %s --check-prefix=OUTER
; By skewing, the diagonal can be made parallel. ISL does this when the Check
; the 'outer_coincidence' option is enabled.
;
; void func(int m, int n, float A[static const restrict m][n]) {
; for (int i = 1; i < m; i+=1)
; for (int j = 1; j < n; j+=1)
; A[i][j] = A[i-1][j] + A[i][j-1];
;}
define void @func(i64 %m, i64 %n, float* noalias nonnull %A) #0 {
entry:
br label %for.cond
for.cond: ; preds = %for.inc11, %entry
%i.0 = phi i64 [ 1, %entry ], [ %add12, %for.inc11 ]
%cmp = icmp slt i64 %i.0, %m
br i1 %cmp, label %for.cond1.preheader, label %for.end13
for.cond1.preheader: ; preds = %for.cond
br label %for.cond1
for.cond1: ; preds = %for.cond1.preheader, %for.body3
%j.0 = phi i64 [ %add10, %for.body3 ], [ 1, %for.cond1.preheader ]
%cmp2 = icmp slt i64 %j.0, %n
br i1 %cmp2, label %for.body3, label %for.inc11
for.body3: ; preds = %for.cond1
%sub = add nsw i64 %i.0, -1
%tmp = mul nsw i64 %sub, %n
%arrayidx = getelementptr inbounds float, float* %A, i64 %tmp
%arrayidx4 = getelementptr inbounds float, float* %arrayidx, i64 %j.0
%tmp13 = load float, float* %arrayidx4, align 4
%sub5 = add nsw i64 %j.0, -1
%tmp14 = mul nsw i64 %i.0, %n
%arrayidx6 = getelementptr inbounds float, float* %A, i64 %tmp14
%arrayidx7 = getelementptr inbounds float, float* %arrayidx6, i64 %sub5
%tmp15 = load float, float* %arrayidx7, align 4
%add = fadd float %tmp13, %tmp15
%tmp16 = mul nsw i64 %i.0, %n
%arrayidx8 = getelementptr inbounds float, float* %A, i64 %tmp16
%arrayidx9 = getelementptr inbounds float, float* %arrayidx8, i64 %j.0
store float %add, float* %arrayidx9, align 4
%add10 = add nuw nsw i64 %j.0, 1
br label %for.cond1
for.inc11: ; preds = %for.cond1
%add12 = add nuw nsw i64 %i.0, 1
br label %for.cond
for.end13: ; preds = %for.cond
ret void
}
; CHECK: #pragma minimal dependence distance: 1
; CHECK-NEXT: for (int c0 = 0; c0 < m - 1; c0 += 1)
; CHECK-NEXT: #pragma minimal dependence distance: 1
; CHECK-NEXT: for (int c1 = 0; c1 < n - 1; c1 += 1)
; CHECK-NEXT: Stmt_for_body3(c0, c1);
; OUTER: #pragma minimal dependence distance: 1
; OUTER-NEXT: for (int c0 = 0; c0 < m + n - 3; c0 += 1)
; OUTER-NEXT: #pragma simd
; OUTER-NEXT: #pragma known-parallel
; OUTER-NEXT: for (int c1 = max(0, -n + c0 + 2); c1 <= min(m - 2, c0); c1 += 1)
; OUTER-NEXT: Stmt_for_body3(c1, c0 - c1);

76
external/llvm-project/polly/test/ScheduleOptimizer/pattern-matching-based-opts-after-delicm.ll vendored Normal file
View File

@@ -0,0 +1,76 @@
; RUN: opt %loadPolly \
; RUN: -polly-pattern-matching-based-opts=true \
; RUN: -polly-optree -polly-delicm -polly-simplify \
; RUN: -polly-opt-isl -debug < %s 2>&1 \
; RUN: | FileCheck %s
; REQUIRES: asserts
; Check that the pattern matching detects the matrix multiplication pattern
; after a full run of -polly-optree and -polly-delicm, where the write access
; is not through the original memory access, but trough a PHI node that was
; delicmed. This test covers the polybench 2mm and 3mm cases.
;
; CHECK: The matrix multiplication pattern was detected
;
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
; Function Attrs: norecurse nounwind uwtable
define void @kernel_2mm(i32 %ni, i32 %nj, i32 %nk, i32 %nl, double %alpha, double %beta, [1800 x double]* nocapture %tmp, [2200 x double]* nocapture readonly %A, [1800 x double]* nocapture readonly %B, [2400 x double]* nocapture readnone %C, [2400 x double]* nocapture readnone %D) local_unnamed_addr #0 {
entry:
br label %entry.split
entry.split: ; preds = %entry
br label %for.body
for.body: ; preds = %for.inc25, %entry.split
%indvars.iv50 = phi i64 [ 0, %entry.split ], [ %indvars.iv.next51, %for.inc25 ]
br label %for.body3
for.body3: ; preds = %for.inc22, %for.body
%indvars.iv46 = phi i64 [ 0, %for.body ], [ %indvars.iv.next47, %for.inc22 ]
%arrayidx5 = getelementptr inbounds [1800 x double], [1800 x double]* %tmp, i64 %indvars.iv50, i64 %indvars.iv46
store double 0.000000e+00, double* %arrayidx5, align 8, !tbaa !2
br label %for.body8
for.body8: ; preds = %for.body8, %for.body3
%0 = phi double [ 0.000000e+00, %for.body3 ], [ %add, %for.body8 ]
%indvars.iv = phi i64 [ 0, %for.body3 ], [ %indvars.iv.next, %for.body8 ]
%arrayidx12 = getelementptr inbounds [2200 x double], [2200 x double]* %A, i64 %indvars.iv50, i64 %indvars.iv
%1 = load double, double* %arrayidx12, align 8, !tbaa !2
%mul = fmul double %1, %alpha
%arrayidx16 = getelementptr inbounds [1800 x double], [1800 x double]* %B, i64 %indvars.iv, i64 %indvars.iv46
%2 = load double, double* %arrayidx16, align 8, !tbaa !2
%mul17 = fmul double %mul, %2
%add = fadd double %0, %mul17
store double %add, double* %arrayidx5, align 8, !tbaa !2
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 2200
br i1 %exitcond, label %for.inc22, label %for.body8
for.inc22: ; preds = %for.body8
%indvars.iv.next47 = add nuw nsw i64 %indvars.iv46, 1
%exitcond48 = icmp eq i64 %indvars.iv.next47, 1800
br i1 %exitcond48, label %for.inc25, label %for.body3
for.inc25: ; preds = %for.inc22
%indvars.iv.next51 = add nuw nsw i64 %indvars.iv50, 1
%exitcond52 = icmp eq i64 %indvars.iv.next51, 1600
br i1 %exitcond52, label %for.end27, label %for.body
for.end27: ; preds = %for.inc25
ret void
}
attributes #0 = { norecurse nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="haswell" "target-features"="+aes,+avx,+avx2,+bmi,+bmi2,+cmov,+cx16,+f16c,+fma,+fsgsbase,+fxsr,+lzcnt,+mmx,+movbe,+pclmul,+popcnt,+rdrnd,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsaveopt,-adx,-avx512bw,-avx512cd,-avx512dq,-avx512er,-avx512f,-avx512ifma,-avx512pf,-avx512vbmi,-avx512vl,-avx512vpopcntdq,-clflushopt,-clwb,-clzero,-fma4,-lwp,-mwaitx,-pku,-prefetchwt1,-prfchw,-rdseed,-rtm,-sgx,-sha,-sse4a,-tbm,-xop,-xsavec,-xsaves" "unsafe-fp-math"="false" "use-soft-float"="false" }
!llvm.module.flags = !{!0}
!llvm.ident = !{!1}
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"clang version 6.0.0 (trunk 309912) (llvm/trunk 309933)"}
!2 = !{!3, !3, i64 0}
!3 = !{!"double", !4, i64 0}
!4 = !{!"omnipotent char", !5, i64 0}
!5 = !{!"Simple C/C++ TBAA"}

66
external/llvm-project/polly/test/ScheduleOptimizer/pattern-matching-based-opts.ll vendored Normal file
View File

@@ -0,0 +1,66 @@
; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=false \
; RUN: -debug < %s 2>&1| FileCheck %s
; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true -debug < %s 2>&1| FileCheck %s --check-prefix=PATTERN-MATCHING-OPTS
; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true -stats -disable-output < %s 2>&1| FileCheck %s --check-prefix=STATS -match-full-lines
; REQUIRES: asserts
;
; /* C := alpha*A*B + beta*C */
; for (i = 0; i < _PB_NI; i++)
; for (j = 0; j < _PB_NJ; j++)
; {
; C[i][j] *= beta;
; for (k = 0; k < _PB_NK; ++k)
; C[i][j] += alpha * A[i][k] * B[k][j];
; }
;
; CHECK-NOT: The matrix multiplication pattern was detected
; PATTERN-MATCHING-OPTS: The matrix multiplication pattern was detected
; STATS: 1 polly-opt-isl - Number of matrix multiplication patterns detected and optimized
;
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-unknown"
define internal void @kernel_gemm(i32 %arg, i32 %arg1, i32 %arg2, double %arg3, double %arg4, [1056 x double]* %arg5, [1024 x double]* %arg6, [1056 x double]* %arg7) #0 {
bb:
br label %bb8
bb8: ; preds = %bb29, %bb
%tmp = phi i64 [ 0, %bb ], [ %tmp30, %bb29 ]
br label %bb9
bb9: ; preds = %bb26, %bb8
%tmp10 = phi i64 [ 0, %bb8 ], [ %tmp27, %bb26 ]
%tmp11 = getelementptr inbounds [1056 x double], [1056 x double]* %arg5, i64 %tmp, i64 %tmp10
%tmp12 = load double, double* %tmp11, align 8
%tmp13 = fmul double %tmp12, %arg4
store double %tmp13, double* %tmp11, align 8
br label %Copy_0
Copy_0: ; preds = %Copy_0, %bb9
%tmp15 = phi i64 [ 0, %bb9 ], [ %tmp24, %Copy_0 ]
%tmp16 = getelementptr inbounds [1024 x double], [1024 x double]* %arg6, i64 %tmp, i64 %tmp15
%tmp17 = load double, double* %tmp16, align 8
%tmp18 = fmul double %tmp17, %arg3
%tmp19 = getelementptr inbounds [1056 x double], [1056 x double]* %arg7, i64 %tmp15, i64 %tmp10
%tmp20 = load double, double* %tmp19, align 8
%tmp21 = fmul double %tmp18, %tmp20
%tmp22 = load double, double* %tmp11, align 8
%tmp23 = fadd double %tmp22, %tmp21
store double %tmp23, double* %tmp11, align 8
%tmp24 = add nuw nsw i64 %tmp15, 1
%tmp25 = icmp ne i64 %tmp24, 1024
br i1 %tmp25, label %Copy_0, label %bb26
bb26: ; preds = %Copy_0
%tmp27 = add nuw nsw i64 %tmp10, 1
%tmp28 = icmp ne i64 %tmp27, 1056
br i1 %tmp28, label %bb9, label %bb29
bb29: ; preds = %bb26
%tmp30 = add nuw nsw i64 %tmp, 1
%tmp31 = icmp ne i64 %tmp30, 1056
br i1 %tmp31, label %bb8, label %bb32
bb32: ; preds = %bb29
ret void
}

69
external/llvm-project/polly/test/ScheduleOptimizer/pattern-matching-based-opts_10.ll vendored Normal file
View File

@@ -0,0 +1,69 @@
; RUN: opt %loadPolly -polly-opt-isl -polly-invariant-load-hoisting=true \
; RUN: -polly-pattern-matching-based-opts=true \
; RUN: -polly-target-throughput-vector-fma=1 \
; RUN: -polly-target-latency-vector-fma=1 \
; RUN: -polly-codegen -polly-target-1st-cache-level-associativity=8 \
; RUN: -polly-target-2nd-cache-level-associativity=8 \
; RUN: -polly-target-1st-cache-level-size=32768 \
; RUN: -polly-target-vector-register-bitwidth=256 \
; RUN: -polly-target-2nd-cache-level-size=262144 -S < %s \
; RUN: | FileCheck %s
;
; This test case checks whether Polly generates second level alias metadata
; to distinguish the specific accesses in case of the ublas gemm kernel.
;
; CHECK: !11 = distinct !{!11, !0, !"second level alias metadata"}
; CHECK: !12 = distinct !{!12, !0, !"second level alias metadata"}
; CHECK: !13 = !{!3, !4, !5, !6, !11}
; CHECK: !14 = distinct !{!14, !0, !"second level alias metadata"}
; CHECK: !15 = !{!3, !4, !5, !6, !11, !12}
; CHECK: !16 = distinct !{!16, !0, !"second level alias metadata"}
; CHECK: !17 = !{!3, !4, !5, !6, !11, !12, !14}
;
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-unknown"
define internal void @kernel_gemm(i32 %arg, i32 %arg1, i32 %arg2, double %arg3, double %arg4, [1056 x double]* %arg5, [1024 x double]* %arg6, [1056 x double]* %arg7) {
bb:
br label %bb8
bb8: ; preds = %bb29, %bb
%tmp = phi i64 [ 0, %bb ], [ %tmp30, %bb29 ]
br label %bb9
bb9: ; preds = %bb26, %bb8
%tmp10 = phi i64 [ 0, %bb8 ], [ %tmp27, %bb26 ]
%tmp11 = getelementptr inbounds [1056 x double], [1056 x double]* %arg5, i64 %tmp, i64 %tmp10
%tmp12 = load double, double* %tmp11, align 8
%tmp13 = fmul double %tmp12, %arg4
store double %tmp13, double* %tmp11, align 8
br label %Copy_0
Copy_0: ; preds = %Copy_0, %bb9
%tmp15 = phi i64 [ 0, %bb9 ], [ %tmp24, %Copy_0 ]
%tmp16 = getelementptr inbounds [1024 x double], [1024 x double]* %arg6, i64 %tmp, i64 %tmp15
%tmp17 = load double, double* %tmp16, align 8
%tmp18 = fmul double %tmp17, %arg3
%tmp19 = getelementptr inbounds [1056 x double], [1056 x double]* %arg7, i64 %tmp15, i64 %tmp10
%tmp20 = load double, double* %tmp19, align 8
%tmp21 = fmul double %tmp18, %tmp20
%tmp22 = load double, double* %tmp11, align 8
%tmp23 = fadd double %tmp22, %tmp21
store double %tmp23, double* %tmp11, align 8
%tmp24 = add nuw nsw i64 %tmp15, 1
%tmp25 = icmp ne i64 %tmp24, 1024
br i1 %tmp25, label %Copy_0, label %bb26
bb26: ; preds = %Copy_0
%tmp27 = add nuw nsw i64 %tmp10, 1
%tmp28 = icmp ne i64 %tmp27, 1056
br i1 %tmp28, label %bb9, label %bb29
bb29: ; preds = %bb26
%tmp30 = add nuw nsw i64 %tmp, 1
%tmp31 = icmp ne i64 %tmp30, 1056
br i1 %tmp31, label %bb8, label %bb32
bb32: ; preds = %bb29
ret void
}

64
external/llvm-project/polly/test/ScheduleOptimizer/pattern-matching-based-opts_11.ll vendored Normal file
View File

@@ -0,0 +1,64 @@
; RUN: opt %loadPolly -polly-import-jscop \
; RUN: -polly-import-jscop-postfix=transformed \
; RUN: -polly-pattern-matching-based-opts=true \
; RUN: -polly-target-throughput-vector-fma=1 \
; RUN: -polly-target-latency-vector-fma=8 \
; RUN: -polly-target-1st-cache-level-associativity=8 \
; RUN: -polly-target-2nd-cache-level-associativity=8 \
; RUN: -polly-target-1st-cache-level-size=32768 \
; RUN: -polly-target-vector-register-bitwidth=256 \
; RUN: -polly-target-2nd-cache-level-size=262144 \
; RUN: -polly-opt-isl -debug < %s 2>&1 \
; RUN: | FileCheck %s
; REQUIRES: asserts
;
; Check that the pattern matching detects the matrix multiplication pattern
; in case scalar memory accesses were replaced by accesses to newly created
; arrays.
;
; CHECK: The matrix multiplication pattern was detected
;
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-unknown"
define void @kernel_gemm(i32 %ni, i32 %nj, i32 %nk, double %A, [1024 x double]* %B, [1024 x double]* %C) {
entry:
br label %entry.split
entry.split: ; preds = %entry
br label %for.cond1.preheader
for.cond1.preheader: ; preds = %for.inc16, %entry.split
%indvars.iv35 = phi i64 [ 0, %entry.split ], [ %indvars.iv.next36, %for.inc16 ]
br label %for.cond4.preheader
for.cond4.preheader: ; preds = %for.inc13, %for.cond1.preheader
%indvars.iv32 = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next33, %for.inc13 ]
br label %for.body6
for.body6: ; preds = %for.body6, %for.cond4.preheader
%indvars.iv = phi i64 [ 0, %for.cond4.preheader ], [ %indvars.iv.next, %for.body6 ]
%arrayidx8 = getelementptr inbounds [1024 x double], [1024 x double]* %B, i64 %indvars.iv, i64 %indvars.iv32
%tmp = load double, double* %arrayidx8, align 8
%mul = fmul double %tmp, %A
%arrayidx12 = getelementptr inbounds [1024 x double], [1024 x double]* %C, i64 %indvars.iv35, i64 %indvars.iv32
%tmp1 = load double, double* %arrayidx12, align 8
%add = fadd double %tmp1, %mul
store double %add, double* %arrayidx12, align 8
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp ne i64 %indvars.iv.next, 1024
br i1 %exitcond, label %for.body6, label %for.inc13
for.inc13: ; preds = %for.body6
%indvars.iv.next33 = add nuw nsw i64 %indvars.iv32, 1
%exitcond34 = icmp ne i64 %indvars.iv.next33, 1024
br i1 %exitcond34, label %for.cond4.preheader, label %for.inc16
for.inc16: ; preds = %for.inc13
%indvars.iv.next36 = add nuw nsw i64 %indvars.iv35, 1
%exitcond37 = icmp ne i64 %indvars.iv.next36, 1024
br i1 %exitcond37, label %for.cond1.preheader, label %for.end18
for.end18: ; preds = %for.inc16
ret void
}

708
external/llvm-project/polly/test/ScheduleOptimizer/pattern-matching-based-opts_12.ll vendored Normal file
View File

File diff suppressed because it is too large Load Diff

Some files were not shown because too many files have changed in this diff Show More