head	1.1;
branch	1.1.1;
access;
symbols
	netbsd-11-0-RC4:1.1.1.3
	netbsd-11-0-RC3:1.1.1.3
	netbsd-11-0-RC2:1.1.1.3
	netbsd-11-0-RC1:1.1.1.3
	perseant-exfatfs-base-20250801:1.1.1.3
	netbsd-11:1.1.1.3.0.10
	netbsd-11-base:1.1.1.3
	netbsd-10-1-RELEASE:1.1.1.3
	perseant-exfatfs-base-20240630:1.1.1.3
	perseant-exfatfs:1.1.1.3.0.8
	perseant-exfatfs-base:1.1.1.3
	netbsd-8-3-RELEASE:1.1.1.1
	netbsd-9-4-RELEASE:1.1.1.2
	netbsd-10-0-RELEASE:1.1.1.3
	netbsd-10-0-RC6:1.1.1.3
	netbsd-10-0-RC5:1.1.1.3
	netbsd-10-0-RC4:1.1.1.3
	netbsd-10-0-RC3:1.1.1.3
	netbsd-10-0-RC2:1.1.1.3
	netbsd-10-0-RC1:1.1.1.3
	netbsd-10:1.1.1.3.0.6
	netbsd-10-base:1.1.1.3
	netbsd-9-3-RELEASE:1.1.1.2
	cjep_sun2x:1.1.1.3.0.4
	cjep_sun2x-base:1.1.1.3
	cjep_staticlib_x-base1:1.1.1.3
	netbsd-9-2-RELEASE:1.1.1.2
	cjep_staticlib_x:1.1.1.3.0.2
	cjep_staticlib_x-base:1.1.1.3
	netbsd-9-1-RELEASE:1.1.1.2
	phil-wifi-20200421:1.1.1.3
	phil-wifi-20200411:1.1.1.3
	phil-wifi-20200406:1.1.1.3
	netbsd-8-2-RELEASE:1.1.1.1
	netbsd-9-0-RELEASE:1.1.1.2
	netbsd-9-0-RC2:1.1.1.2
	netbsd-9-0-RC1:1.1.1.2
	netbsd-9:1.1.1.2.0.2
	netbsd-9-base:1.1.1.2
	phil-wifi-20190609:1.1.1.2
	netbsd-8-1-RELEASE:1.1.1.1
	netbsd-8-1-RC1:1.1.1.1
	pgoyette-compat-merge-20190127:1.1.1.1.14.1
	pgoyette-compat-20190127:1.1.1.2
	pgoyette-compat-20190118:1.1.1.2
	pgoyette-compat-1226:1.1.1.2
	pgoyette-compat-1126:1.1.1.2
	pgoyette-compat-1020:1.1.1.2
	pgoyette-compat-0930:1.1.1.2
	pgoyette-compat-0906:1.1.1.2
	pgoyette-compat-0728:1.1.1.2
	clang-337282:1.1.1.2
	netbsd-8-0-RELEASE:1.1.1.1
	phil-wifi:1.1.1.1.0.16
	phil-wifi-base:1.1.1.1
	pgoyette-compat-0625:1.1.1.1
	netbsd-8-0-RC2:1.1.1.1
	pgoyette-compat-0521:1.1.1.1
	pgoyette-compat-0502:1.1.1.1
	pgoyette-compat-0422:1.1.1.1
	netbsd-8-0-RC1:1.1.1.1
	pgoyette-compat-0415:1.1.1.1
	pgoyette-compat-0407:1.1.1.1
	pgoyette-compat-0330:1.1.1.1
	pgoyette-compat-0322:1.1.1.1
	pgoyette-compat-0315:1.1.1.1
	pgoyette-compat:1.1.1.1.0.14
	pgoyette-compat-base:1.1.1.1
	clang-319952:1.1.1.1
	matt-nb8-mediatek:1.1.1.1.0.12
	matt-nb8-mediatek-base:1.1.1.1
	clang-309604:1.1.1.1
	perseant-stdc-iso10646:1.1.1.1.0.10
	perseant-stdc-iso10646-base:1.1.1.1
	netbsd-8:1.1.1.1.0.8
	netbsd-8-base:1.1.1.1
	prg-localcount2-base3:1.1.1.1
	prg-localcount2-base2:1.1.1.1
	prg-localcount2-base1:1.1.1.1
	prg-localcount2:1.1.1.1.0.6
	prg-localcount2-base:1.1.1.1
	pgoyette-localcount-20170426:1.1.1.1
	bouyer-socketcan-base1:1.1.1.1
	pgoyette-localcount:1.1.1.1.0.4
	pgoyette-localcount-20170320:1.1.1.1
	clang-294123:1.1.1.1
	bouyer-socketcan:1.1.1.1.0.2
	bouyer-socketcan-base:1.1.1.1
	clang-291444:1.1.1.1
	LLVM:1.1.1;
locks; strict;
comment	@// @;


1.1
date	2017.01.11.10.39.16;	author joerg;	state Exp;
branches
	1.1.1.1;
next	;
commitid	CNnUNfII1jgNmxBz;

1.1.1.1
date	2017.01.11.10.39.16;	author joerg;	state Exp;
branches
	1.1.1.1.4.1
	1.1.1.1.14.1
	1.1.1.1.16.1;
next	1.1.1.2;
commitid	CNnUNfII1jgNmxBz;

1.1.1.2
date	2018.07.17.18.31.40;	author joerg;	state Exp;
branches;
next	1.1.1.3;
commitid	wDzL46ALjrCZgwKA;

1.1.1.3
date	2019.11.13.22.22.43;	author joerg;	state dead;
branches;
next	;
commitid	QD8YATxuNG34YJKB;

1.1.1.1.4.1
date	2017.01.11.10.39.16;	author pgoyette;	state dead;
branches;
next	1.1.1.1.4.2;
commitid	jjw7cAwgyKq7RfKz;

1.1.1.1.4.2
date	2017.03.20.06.53.28;	author pgoyette;	state Exp;
branches;
next	;
commitid	jjw7cAwgyKq7RfKz;

1.1.1.1.14.1
date	2018.07.28.04.34.05;	author pgoyette;	state Exp;
branches;
next	;
commitid	1UP1xAIUxv1ZgRLA;

1.1.1.1.16.1
date	2019.06.10.21.46.26;	author christos;	state Exp;
branches;
next	1.1.1.1.16.2;
commitid	jtc8rnCzWiEEHGqB;

1.1.1.1.16.2
date	2020.04.13.07.50.11;	author martin;	state dead;
branches;
next	;
commitid	X01YhRUPVUDaec4C;


desc
@@


1.1
log
@Initial revision
@
text
@// Test host codegen.
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64  --check-prefix HCHECK
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32  --check-prefix HCHECK
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix HCHECK

// Test target codegen - host bc file has to be created first. (no significant differences with host version of target region)
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s

// expected-no-diagnostics
#ifndef HEADER
#define HEADER

// CHECK-DAG: %ident_t = type { i32, i32, i32, i32, i8* }
// CHECK-DAG: [[STR:@@.+]] = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00"
// CHECK-DAG: [[DEF_LOC_0:@@.+]] = private unnamed_addr constant %ident_t { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }

// CHECK-LABEL: define {{.*void}} @@{{.*}}without_schedule_clause{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}})
void without_schedule_clause(float *a, float *b, float *c, float *d) {
  #pragma omp target
  #pragma omp teams
  #pragma omp distribute
  for (int i = 33; i < 32000000; i += 7) {
    a[i] = b[i] * c[i] * d[i];
  }
}

// CHECK: define {{.*}}void @@.omp_outlined.(i32* noalias [[GBL_TIDP:%.+]], i32* noalias [[BND_TID:%.+]], float** dereferenceable({{[0-9]+}}) [[APTR:%.+]], float** dereferenceable({{[0-9]+}}) [[BPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[CPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[DPTR:%.+]])
// CHECK:  [[TID_ADDR:%.+]] = alloca i32*
// CHECK:  [[IV:%.+iv]] = alloca i32
// CHECK:  [[LB:%.+lb]] = alloca i32
// CHECK:  [[UB:%.+ub]] = alloca i32
// CHECK:  [[ST:%.+stride]] = alloca i32
// CHECK:  [[LAST:%.+last]] = alloca i32
// CHECK-DAG:  store i32* [[GBL_TIDP]], i32** [[TID_ADDR]]
// CHECK-DAG:  store i32 0, i32* [[LB]]
// CHECK-DAG:  store i32 4571423, i32* [[UB]]
// CHECK-DAG:  store i32 1, i32* [[ST]]
// CHECK-DAG:  store i32 0, i32* [[LAST]]
// CHECK-DAG:  [[GBL_TID:%.+]] = load i32*, i32** [[TID_ADDR]]
// CHECK-DAG:  [[GBL_TIDV:%.+]] = load i32, i32* [[GBL_TID]]
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]], i32 92, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 1)
// CHECK-DAG:  [[UBV0:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  [[USWITCH:%.+]] = icmp sgt i32 [[UBV0]], 4571423
// CHECK:  br i1 [[USWITCH]], label %[[BBCT:.+]], label %[[BBCF:.+]]
// CHECK-DAG:  [[BBCT]]:
// CHECK-DAG:  br label %[[BBCE:.+]]
// CHECK-DAG:  [[BBCF]]:
// CHECK-DAG:  [[UBV1:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  br label %[[BBCE]]
// CHECK:  [[BBCE]]:
// CHECK:  [[SELUB:%.+]] = phi i32 [ 4571423, %[[BBCT]] ], [ [[UBV1]], %[[BBCF]] ]
// CHECK:  store i32 [[SELUB]], i32* [[UB]]
// CHECK:  [[LBV0:%.+]] = load i32, i32* [[LB]]
// CHECK:  store i32 [[LBV0]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR:.+]]
// CHECK:  [[BBINNFOR]]:
// CHECK:  [[IVVAL0:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[UBV2:%.+]] = load i32, i32* [[UB]]
// CHECK:  [[IVLEUB:%.+]] = icmp sle i32 [[IVVAL0]], [[UBV2]]
// CHECK:  br i1 [[IVLEUB]], label %[[BBINNBODY:.+]], label %[[BBINNEND:.+]]
// CHECK:  [[BBINNBODY]]:
// CHECK:  {{.+}} = load i32, i32* [[IV]]
// ... loop body ...
// CHECK:  br label %[[BBBODYCONT:.+]]
// CHECK:  [[BBBODYCONT]]:
// CHECK:  br label %[[BBINNINC:.+]]
// CHECK:  [[BBINNINC]]:
// CHECK:  [[IVVAL1:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[IVINC:%.+]] = add nsw i32 [[IVVAL1]], 1
// CHECK:  store i32 [[IVINC]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR]]
// CHECK:  [[BBINNEND]]:
// CHECK:  br label %[[LPEXIT:.+]]
// CHECK:  [[LPEXIT]]:
// CHECK:  call void @@__kmpc_for_static_fini(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]])
// CHECK:  ret void


// CHECK-LABEL: define {{.*void}} @@{{.*}}static_not_chunked{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}})
void static_not_chunked(float *a, float *b, float *c, float *d) {
  #pragma omp target
  #pragma omp teams
  #pragma omp distribute dist_schedule(static)
  for (int i = 32000000; i > 33; i += -7) {
        a[i] = b[i] * c[i] * d[i];
  }
}

// CHECK: define {{.*}}void @@.omp_outlined.{{.*}}(i32* noalias [[GBL_TIDP:%.+]], i32* noalias [[BND_TID:%.+]], float** dereferenceable({{[0-9]+}}) [[APTR:%.+]], float** dereferenceable({{[0-9]+}}) [[BPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[CPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[DPTR:%.+]])
// CHECK:  [[TID_ADDR:%.+]] = alloca i32*
// CHECK:  [[IV:%.+iv]] = alloca i32
// CHECK:  [[LB:%.+lb]] = alloca i32
// CHECK:  [[UB:%.+ub]] = alloca i32
// CHECK:  [[ST:%.+stride]] = alloca i32
// CHECK:  [[LAST:%.+last]] = alloca i32
// CHECK-DAG:  store i32* [[GBL_TIDP]], i32** [[TID_ADDR]]
// CHECK-DAG:  store i32 0, i32* [[LB]]
// CHECK-DAG:  store i32 4571423, i32* [[UB]]
// CHECK-DAG:  store i32 1, i32* [[ST]]
// CHECK-DAG:  store i32 0, i32* [[LAST]]
// CHECK-DAG:  [[GBL_TID:%.+]] = load i32*, i32** [[TID_ADDR]]
// CHECK-DAG:  [[GBL_TIDV:%.+]] = load i32, i32* [[GBL_TID]]
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]], i32 92, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 1)
// CHECK-DAG:  [[UBV0:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  [[USWITCH:%.+]] = icmp sgt i32 [[UBV0]], 4571423
// CHECK:  br i1 [[USWITCH]], label %[[BBCT:.+]], label %[[BBCF:.+]]
// CHECK-DAG:  [[BBCT]]:
// CHECK-DAG:  br label %[[BBCE:.+]]
// CHECK-DAG:  [[BBCF]]:
// CHECK-DAG:  [[UBV1:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  br label %[[BBCE]]
// CHECK:  [[BBCE]]:
// CHECK:  [[SELUB:%.+]] = phi i32 [ 4571423, %[[BBCT]] ], [ [[UBV1]], %[[BBCF]] ]
// CHECK:  store i32 [[SELUB]], i32* [[UB]]
// CHECK:  [[LBV0:%.+]] = load i32, i32* [[LB]]
// CHECK:  store i32 [[LBV0]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR:.+]]
// CHECK:  [[BBINNFOR]]:
// CHECK:  [[IVVAL0:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[UBV2:%.+]] = load i32, i32* [[UB]]
// CHECK:  [[IVLEUB:%.+]] = icmp sle i32 [[IVVAL0]], [[UBV2]]
// CHECK:  br i1 [[IVLEUB]], label %[[BBINNBODY:.+]], label %[[BBINNEND:.+]]
// CHECK:  [[BBINNBODY]]:
// CHECK:  {{.+}} = load i32, i32* [[IV]]
// ... loop body ...
// CHECK:  br label %[[BBBODYCONT:.+]]
// CHECK:  [[BBBODYCONT]]:
// CHECK:  br label %[[BBINNINC:.+]]
// CHECK:  [[BBINNINC]]:
// CHECK:  [[IVVAL1:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[IVINC:%.+]] = add nsw i32 [[IVVAL1]], 1
// CHECK:  store i32 [[IVINC]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR]]
// CHECK:  [[BBINNEND]]:
// CHECK:  br label %[[LPEXIT:.+]]
// CHECK:  [[LPEXIT]]:
// CHECK:  call void @@__kmpc_for_static_fini(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]])
// CHECK:  ret void


// CHECK-LABEL: define {{.*void}} @@{{.*}}static_chunked{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}})
void static_chunked(float *a, float *b, float *c, float *d) {
  #pragma omp target
  #pragma omp teams
#pragma omp distribute dist_schedule(static, 5)
  for (unsigned i = 131071; i <= 2147483647; i += 127) {
    a[i] = b[i] * c[i] * d[i];
  }
}

// CHECK: define {{.*}}void @@.omp_outlined.{{.*}}(i32* noalias [[GBL_TIDP:%.+]], i32* noalias [[BND_TID:%.+]], float** dereferenceable({{[0-9]+}}) [[APTR:%.+]], float** dereferenceable({{[0-9]+}}) [[BPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[CPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[DPTR:%.+]])
// CHECK:  [[TID_ADDR:%.+]] = alloca i32*
// CHECK:  [[IV:%.+iv]] = alloca i32
// CHECK:  [[LB:%.+lb]] = alloca i32
// CHECK:  [[UB:%.+ub]] = alloca i32
// CHECK:  [[ST:%.+stride]] = alloca i32
// CHECK:  [[LAST:%.+last]] = alloca i32
// CHECK-DAG:  store i32* [[GBL_TIDP]], i32** [[TID_ADDR]]
// CHECK-DAG:  store i32 0, i32* [[LB]]
// CHECK-DAG:  store i32 16908288, i32* [[UB]]
// CHECK-DAG:  store i32 1, i32* [[ST]]
// CHECK-DAG:  store i32 0, i32* [[LAST]]
// CHECK-DAG:  [[GBL_TID:%.+]] = load i32*, i32** [[TID_ADDR]]
// CHECK-DAG:  [[GBL_TIDV:%.+]] = load i32, i32* [[GBL_TID]]
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]], i32 91, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 5)
// CHECK-DAG:  [[UBV0:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  [[USWITCH:%.+]] = icmp ugt i32 [[UBV0]], 16908288
// CHECK:  br i1 [[USWITCH]], label %[[BBCT:.+]], label %[[BBCF:.+]]
// CHECK-DAG:  [[BBCT]]:
// CHECK-DAG:  br label %[[BBCE:.+]]
// CHECK-DAG:  [[BBCF]]:
// CHECK-DAG:  [[UBV1:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  br label %[[BBCE]]
// CHECK:  [[BBCE]]:
// CHECK:  [[SELUB:%.+]] = phi i32 [ 16908288, %[[BBCT]] ], [ [[UBV1]], %[[BBCF]] ]
// CHECK:  store i32 [[SELUB]], i32* [[UB]]
// CHECK:  [[LBV0:%.+]] = load i32, i32* [[LB]]
// CHECK:  store i32 [[LBV0]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR:.+]]
// CHECK:  [[BBINNFOR]]:
// CHECK:  [[IVVAL0:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[UBV2:%.+]] = load i32, i32* [[UB]]
// CHECK:  [[IVLEUB:%.+]] = icmp ule i32 [[IVVAL0]], [[UBV2]]
// CHECK:  br i1 [[IVLEUB]], label %[[BBINNBODY:.+]], label %[[BBINNEND:.+]]
// CHECK:  [[BBINNBODY]]:
// CHECK:  {{.+}} = load i32, i32* [[IV]]
// ... loop body ...
// CHECK:  br label %[[BBBODYCONT:.+]]
// CHECK:  [[BBBODYCONT]]:
// CHECK:  br label %[[BBINNINC:.+]]
// CHECK:  [[BBINNINC]]:
// CHECK:  [[IVVAL1:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[IVINC:%.+]] = add i32 [[IVVAL1]], 1
// CHECK:  store i32 [[IVINC]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR]]
// CHECK:  [[BBINNEND]]:
// CHECK:  br label %[[LPEXIT:.+]]
// CHECK:  [[LPEXIT]]:
// CHECK:  call void @@__kmpc_for_static_fini(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]])
// CHECK:  ret void

// CHECK-LABEL: test_precond
void test_precond() {
  char a = 0;
  #pragma omp target
  #pragma omp teams
  #pragma omp distribute
  for(char i = a; i < 10; ++i);
}

// a is passed as a parameter to the outlined functions
// CHECK:  define {{.*}}void @@.omp_outlined.{{.*}}(i32* noalias [[GBL_TIDP:%.+]], i32* noalias [[BND_TID:%.+]], i8* dereferenceable({{[0-9]+}}) [[APARM:%.+]])
// CHECK:  store i8* [[APARM]], i8** [[APTRADDR:%.+]]
// ..many loads of %0..
// CHECK:  [[A2:%.+]] = load i8*, i8** [[APTRADDR]]
// CHECK:  [[AVAL0:%.+]] = load i8, i8* [[A2]]
// CHECK:  store i8 [[AVAL0]], i8* [[CAP_EXPR:%.+]],
// CHECK:  [[AVAL1:%.+]] = load i8, i8* [[CAP_EXPR]]
// CHECK:  load i8, i8* [[CAP_EXPR]]
// CHECK:  [[AVAL2:%.+]] = load i8, i8* [[CAP_EXPR]]
// CHECK:  [[ACONV:%.+]] = sext i8 [[AVAL2]] to i32
// CHECK:  [[ACMP:%.+]] = icmp slt i32 [[ACONV]], 10
// CHECK:  br i1 [[ACMP]], label %[[PRECOND_THEN:.+]], label %[[PRECOND_END:.+]]
// CHECK:  [[PRECOND_THEN]]
// CHECK:  call void @@__kmpc_for_static_init_4
// CHECK:  call void @@__kmpc_for_static_fini
// CHECK:  [[PRECOND_END]]

// no templates for now, as these require special handling in target regions and/or declare target

// HCHECK-LABEL: fint
// HCHECK: call {{.*}}i32 {{.+}}ftemplate
// HCHECK: ret i32

// HCHECK: load i16, i16*
// HCHECK: store i16 %
// HCHECK: call i32 @@__tgt_target_teams(
// HCHECK: call void @@__kmpc_for_static_init_4(
template <typename T>
T ftemplate() {
  short aa = 0;

#pragma omp target
#pragma omp teams
#pragma omp distribute dist_schedule(static, aa)
  for (int i = 0; i < 100; i++) {
  }
  return T();
}

int fint(void) { return ftemplate<int>(); }

#endif
@


1.1.1.1
log
@Import Clang pre-4.0.0 r291444.
@
text
@@


1.1.1.1.16.1
log
@Sync with HEAD
@
text
@a8 8
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}

a18 10
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// SIMD-ONLY1-NOT: {{__kmpc|__tgt}}

d23 1
a23 1
// CHECK-DAG: %struct.ident_t = type { i32, i32, i32, i32, i8* }
d25 1
a25 2
// CHECK-DAG: [[DEF_LOC_0:@@.+]] = private unnamed_addr constant %struct.ident_t { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }
// CHECK-DAG: [[DEF_LOC_DISTRIBUTE_0:@@.+]] = private unnamed_addr constant %struct.ident_t { i32 0, i32 2050, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }
d37 1
a37 1
// CHECK: define {{.*}}void @@{{.+}}(i32* noalias [[GBL_TIDP:%.+]], i32* noalias [[BND_TID:%.+]], float** dereferenceable({{[0-9]+}}) [[APTR:%.+]], float** dereferenceable({{[0-9]+}}) [[BPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[CPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[DPTR:%.+]])
d51 1
a51 1
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]], i32 92, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 1)
d85 1
a85 1
// CHECK:  call void @@__kmpc_for_static_fini(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]])
d113 1
a113 1
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]], i32 92, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 1)
d147 1
a147 1
// CHECK:  call void @@__kmpc_for_static_fini(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]])
d175 1
a175 1
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]], i32 91, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 5)
d209 1
a209 1
// CHECK:  call void @@__kmpc_for_static_fini(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]])
@


1.1.1.1.16.2
log
@Mostly merge changes from HEAD upto 20200411
@
text
@@


1.1.1.1.14.1
log
@Sync with HEAD
@
text
@a8 8
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}

a18 10
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// SIMD-ONLY1-NOT: {{__kmpc|__tgt}}

d23 1
a23 1
// CHECK-DAG: %struct.ident_t = type { i32, i32, i32, i32, i8* }
d25 1
a25 2
// CHECK-DAG: [[DEF_LOC_0:@@.+]] = private unnamed_addr constant %struct.ident_t { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }
// CHECK-DAG: [[DEF_LOC_DISTRIBUTE_0:@@.+]] = private unnamed_addr constant %struct.ident_t { i32 0, i32 2050, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }
d37 1
a37 1
// CHECK: define {{.*}}void @@{{.+}}(i32* noalias [[GBL_TIDP:%.+]], i32* noalias [[BND_TID:%.+]], float** dereferenceable({{[0-9]+}}) [[APTR:%.+]], float** dereferenceable({{[0-9]+}}) [[BPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[CPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[DPTR:%.+]])
d51 1
a51 1
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]], i32 92, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 1)
d85 1
a85 1
// CHECK:  call void @@__kmpc_for_static_fini(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]])
d113 1
a113 1
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]], i32 92, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 1)
d147 1
a147 1
// CHECK:  call void @@__kmpc_for_static_fini(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]])
d175 1
a175 1
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]], i32 91, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 5)
d209 1
a209 1
// CHECK:  call void @@__kmpc_for_static_fini(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]])
@


1.1.1.2
log
@Import clang r337282 from trunk
@
text
@a8 8
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}

a18 10
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY1 %s
// SIMD-ONLY1-NOT: {{__kmpc|__tgt}}

d23 1
a23 1
// CHECK-DAG: %struct.ident_t = type { i32, i32, i32, i32, i8* }
d25 1
a25 2
// CHECK-DAG: [[DEF_LOC_0:@@.+]] = private unnamed_addr constant %struct.ident_t { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }
// CHECK-DAG: [[DEF_LOC_DISTRIBUTE_0:@@.+]] = private unnamed_addr constant %struct.ident_t { i32 0, i32 2050, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }
d37 1
a37 1
// CHECK: define {{.*}}void @@{{.+}}(i32* noalias [[GBL_TIDP:%.+]], i32* noalias [[BND_TID:%.+]], float** dereferenceable({{[0-9]+}}) [[APTR:%.+]], float** dereferenceable({{[0-9]+}}) [[BPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[CPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[DPTR:%.+]])
d51 1
a51 1
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]], i32 92, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 1)
d85 1
a85 1
// CHECK:  call void @@__kmpc_for_static_fini(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]])
d113 1
a113 1
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]], i32 92, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 1)
d147 1
a147 1
// CHECK:  call void @@__kmpc_for_static_fini(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]])
d175 1
a175 1
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]], i32 91, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 5)
d209 1
a209 1
// CHECK:  call void @@__kmpc_for_static_fini(%struct.ident_t* [[DEF_LOC_DISTRIBUTE_0]], i32 [[GBL_TIDV]])
@


1.1.1.3
log
@Mark old LLVM instance as dead.
@
text
@@


1.1.1.1.4.1
log
@file distribute_codegen.cpp was added on branch pgoyette-localcount on 2017-03-20 06:53:28 +0000
@
text
@d1 263
@


1.1.1.1.4.2
log
@Sync with HEAD
@
text
@a0 263
// Test host codegen.
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64  --check-prefix HCHECK
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32  --check-prefix HCHECK
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix HCHECK

// Test target codegen - host bc file has to be created first. (no significant differences with host version of target region)
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s

// expected-no-diagnostics
#ifndef HEADER
#define HEADER

// CHECK-DAG: %ident_t = type { i32, i32, i32, i32, i8* }
// CHECK-DAG: [[STR:@@.+]] = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00"
// CHECK-DAG: [[DEF_LOC_0:@@.+]] = private unnamed_addr constant %ident_t { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }

// CHECK-LABEL: define {{.*void}} @@{{.*}}without_schedule_clause{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}})
void without_schedule_clause(float *a, float *b, float *c, float *d) {
  #pragma omp target
  #pragma omp teams
  #pragma omp distribute
  for (int i = 33; i < 32000000; i += 7) {
    a[i] = b[i] * c[i] * d[i];
  }
}

// CHECK: define {{.*}}void @@.omp_outlined.(i32* noalias [[GBL_TIDP:%.+]], i32* noalias [[BND_TID:%.+]], float** dereferenceable({{[0-9]+}}) [[APTR:%.+]], float** dereferenceable({{[0-9]+}}) [[BPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[CPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[DPTR:%.+]])
// CHECK:  [[TID_ADDR:%.+]] = alloca i32*
// CHECK:  [[IV:%.+iv]] = alloca i32
// CHECK:  [[LB:%.+lb]] = alloca i32
// CHECK:  [[UB:%.+ub]] = alloca i32
// CHECK:  [[ST:%.+stride]] = alloca i32
// CHECK:  [[LAST:%.+last]] = alloca i32
// CHECK-DAG:  store i32* [[GBL_TIDP]], i32** [[TID_ADDR]]
// CHECK-DAG:  store i32 0, i32* [[LB]]
// CHECK-DAG:  store i32 4571423, i32* [[UB]]
// CHECK-DAG:  store i32 1, i32* [[ST]]
// CHECK-DAG:  store i32 0, i32* [[LAST]]
// CHECK-DAG:  [[GBL_TID:%.+]] = load i32*, i32** [[TID_ADDR]]
// CHECK-DAG:  [[GBL_TIDV:%.+]] = load i32, i32* [[GBL_TID]]
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]], i32 92, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 1)
// CHECK-DAG:  [[UBV0:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  [[USWITCH:%.+]] = icmp sgt i32 [[UBV0]], 4571423
// CHECK:  br i1 [[USWITCH]], label %[[BBCT:.+]], label %[[BBCF:.+]]
// CHECK-DAG:  [[BBCT]]:
// CHECK-DAG:  br label %[[BBCE:.+]]
// CHECK-DAG:  [[BBCF]]:
// CHECK-DAG:  [[UBV1:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  br label %[[BBCE]]
// CHECK:  [[BBCE]]:
// CHECK:  [[SELUB:%.+]] = phi i32 [ 4571423, %[[BBCT]] ], [ [[UBV1]], %[[BBCF]] ]
// CHECK:  store i32 [[SELUB]], i32* [[UB]]
// CHECK:  [[LBV0:%.+]] = load i32, i32* [[LB]]
// CHECK:  store i32 [[LBV0]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR:.+]]
// CHECK:  [[BBINNFOR]]:
// CHECK:  [[IVVAL0:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[UBV2:%.+]] = load i32, i32* [[UB]]
// CHECK:  [[IVLEUB:%.+]] = icmp sle i32 [[IVVAL0]], [[UBV2]]
// CHECK:  br i1 [[IVLEUB]], label %[[BBINNBODY:.+]], label %[[BBINNEND:.+]]
// CHECK:  [[BBINNBODY]]:
// CHECK:  {{.+}} = load i32, i32* [[IV]]
// ... loop body ...
// CHECK:  br label %[[BBBODYCONT:.+]]
// CHECK:  [[BBBODYCONT]]:
// CHECK:  br label %[[BBINNINC:.+]]
// CHECK:  [[BBINNINC]]:
// CHECK:  [[IVVAL1:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[IVINC:%.+]] = add nsw i32 [[IVVAL1]], 1
// CHECK:  store i32 [[IVINC]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR]]
// CHECK:  [[BBINNEND]]:
// CHECK:  br label %[[LPEXIT:.+]]
// CHECK:  [[LPEXIT]]:
// CHECK:  call void @@__kmpc_for_static_fini(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]])
// CHECK:  ret void


// CHECK-LABEL: define {{.*void}} @@{{.*}}static_not_chunked{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}})
void static_not_chunked(float *a, float *b, float *c, float *d) {
  #pragma omp target
  #pragma omp teams
  #pragma omp distribute dist_schedule(static)
  for (int i = 32000000; i > 33; i += -7) {
        a[i] = b[i] * c[i] * d[i];
  }
}

// CHECK: define {{.*}}void @@.omp_outlined.{{.*}}(i32* noalias [[GBL_TIDP:%.+]], i32* noalias [[BND_TID:%.+]], float** dereferenceable({{[0-9]+}}) [[APTR:%.+]], float** dereferenceable({{[0-9]+}}) [[BPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[CPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[DPTR:%.+]])
// CHECK:  [[TID_ADDR:%.+]] = alloca i32*
// CHECK:  [[IV:%.+iv]] = alloca i32
// CHECK:  [[LB:%.+lb]] = alloca i32
// CHECK:  [[UB:%.+ub]] = alloca i32
// CHECK:  [[ST:%.+stride]] = alloca i32
// CHECK:  [[LAST:%.+last]] = alloca i32
// CHECK-DAG:  store i32* [[GBL_TIDP]], i32** [[TID_ADDR]]
// CHECK-DAG:  store i32 0, i32* [[LB]]
// CHECK-DAG:  store i32 4571423, i32* [[UB]]
// CHECK-DAG:  store i32 1, i32* [[ST]]
// CHECK-DAG:  store i32 0, i32* [[LAST]]
// CHECK-DAG:  [[GBL_TID:%.+]] = load i32*, i32** [[TID_ADDR]]
// CHECK-DAG:  [[GBL_TIDV:%.+]] = load i32, i32* [[GBL_TID]]
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]], i32 92, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 1)
// CHECK-DAG:  [[UBV0:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  [[USWITCH:%.+]] = icmp sgt i32 [[UBV0]], 4571423
// CHECK:  br i1 [[USWITCH]], label %[[BBCT:.+]], label %[[BBCF:.+]]
// CHECK-DAG:  [[BBCT]]:
// CHECK-DAG:  br label %[[BBCE:.+]]
// CHECK-DAG:  [[BBCF]]:
// CHECK-DAG:  [[UBV1:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  br label %[[BBCE]]
// CHECK:  [[BBCE]]:
// CHECK:  [[SELUB:%.+]] = phi i32 [ 4571423, %[[BBCT]] ], [ [[UBV1]], %[[BBCF]] ]
// CHECK:  store i32 [[SELUB]], i32* [[UB]]
// CHECK:  [[LBV0:%.+]] = load i32, i32* [[LB]]
// CHECK:  store i32 [[LBV0]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR:.+]]
// CHECK:  [[BBINNFOR]]:
// CHECK:  [[IVVAL0:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[UBV2:%.+]] = load i32, i32* [[UB]]
// CHECK:  [[IVLEUB:%.+]] = icmp sle i32 [[IVVAL0]], [[UBV2]]
// CHECK:  br i1 [[IVLEUB]], label %[[BBINNBODY:.+]], label %[[BBINNEND:.+]]
// CHECK:  [[BBINNBODY]]:
// CHECK:  {{.+}} = load i32, i32* [[IV]]
// ... loop body ...
// CHECK:  br label %[[BBBODYCONT:.+]]
// CHECK:  [[BBBODYCONT]]:
// CHECK:  br label %[[BBINNINC:.+]]
// CHECK:  [[BBINNINC]]:
// CHECK:  [[IVVAL1:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[IVINC:%.+]] = add nsw i32 [[IVVAL1]], 1
// CHECK:  store i32 [[IVINC]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR]]
// CHECK:  [[BBINNEND]]:
// CHECK:  br label %[[LPEXIT:.+]]
// CHECK:  [[LPEXIT]]:
// CHECK:  call void @@__kmpc_for_static_fini(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]])
// CHECK:  ret void


// CHECK-LABEL: define {{.*void}} @@{{.*}}static_chunked{{.*}}(float* {{.+}}, float* {{.+}}, float* {{.+}}, float* {{.+}})
void static_chunked(float *a, float *b, float *c, float *d) {
  #pragma omp target
  #pragma omp teams
#pragma omp distribute dist_schedule(static, 5)
  for (unsigned i = 131071; i <= 2147483647; i += 127) {
    a[i] = b[i] * c[i] * d[i];
  }
}

// CHECK: define {{.*}}void @@.omp_outlined.{{.*}}(i32* noalias [[GBL_TIDP:%.+]], i32* noalias [[BND_TID:%.+]], float** dereferenceable({{[0-9]+}}) [[APTR:%.+]], float** dereferenceable({{[0-9]+}}) [[BPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[CPTR:%.+]], float** dereferenceable({{[0-9]+}}) [[DPTR:%.+]])
// CHECK:  [[TID_ADDR:%.+]] = alloca i32*
// CHECK:  [[IV:%.+iv]] = alloca i32
// CHECK:  [[LB:%.+lb]] = alloca i32
// CHECK:  [[UB:%.+ub]] = alloca i32
// CHECK:  [[ST:%.+stride]] = alloca i32
// CHECK:  [[LAST:%.+last]] = alloca i32
// CHECK-DAG:  store i32* [[GBL_TIDP]], i32** [[TID_ADDR]]
// CHECK-DAG:  store i32 0, i32* [[LB]]
// CHECK-DAG:  store i32 16908288, i32* [[UB]]
// CHECK-DAG:  store i32 1, i32* [[ST]]
// CHECK-DAG:  store i32 0, i32* [[LAST]]
// CHECK-DAG:  [[GBL_TID:%.+]] = load i32*, i32** [[TID_ADDR]]
// CHECK-DAG:  [[GBL_TIDV:%.+]] = load i32, i32* [[GBL_TID]]
// CHECK:  call void @@__kmpc_for_static_init_{{.+}}(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]], i32 91, i32* %.omp.is_last, i32* %.omp.lb, i32* %.omp.ub, i32* %.omp.stride, i32 1, i32 5)
// CHECK-DAG:  [[UBV0:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  [[USWITCH:%.+]] = icmp ugt i32 [[UBV0]], 16908288
// CHECK:  br i1 [[USWITCH]], label %[[BBCT:.+]], label %[[BBCF:.+]]
// CHECK-DAG:  [[BBCT]]:
// CHECK-DAG:  br label %[[BBCE:.+]]
// CHECK-DAG:  [[BBCF]]:
// CHECK-DAG:  [[UBV1:%.+]] = load i32, i32* [[UB]]
// CHECK-DAG:  br label %[[BBCE]]
// CHECK:  [[BBCE]]:
// CHECK:  [[SELUB:%.+]] = phi i32 [ 16908288, %[[BBCT]] ], [ [[UBV1]], %[[BBCF]] ]
// CHECK:  store i32 [[SELUB]], i32* [[UB]]
// CHECK:  [[LBV0:%.+]] = load i32, i32* [[LB]]
// CHECK:  store i32 [[LBV0]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR:.+]]
// CHECK:  [[BBINNFOR]]:
// CHECK:  [[IVVAL0:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[UBV2:%.+]] = load i32, i32* [[UB]]
// CHECK:  [[IVLEUB:%.+]] = icmp ule i32 [[IVVAL0]], [[UBV2]]
// CHECK:  br i1 [[IVLEUB]], label %[[BBINNBODY:.+]], label %[[BBINNEND:.+]]
// CHECK:  [[BBINNBODY]]:
// CHECK:  {{.+}} = load i32, i32* [[IV]]
// ... loop body ...
// CHECK:  br label %[[BBBODYCONT:.+]]
// CHECK:  [[BBBODYCONT]]:
// CHECK:  br label %[[BBINNINC:.+]]
// CHECK:  [[BBINNINC]]:
// CHECK:  [[IVVAL1:%.+]] = load i32, i32* [[IV]]
// CHECK:  [[IVINC:%.+]] = add i32 [[IVVAL1]], 1
// CHECK:  store i32 [[IVINC]], i32* [[IV]]
// CHECK:  br label %[[BBINNFOR]]
// CHECK:  [[BBINNEND]]:
// CHECK:  br label %[[LPEXIT:.+]]
// CHECK:  [[LPEXIT]]:
// CHECK:  call void @@__kmpc_for_static_fini(%ident_t* [[DEF_LOC_0]], i32 [[GBL_TIDV]])
// CHECK:  ret void

// CHECK-LABEL: test_precond
void test_precond() {
  char a = 0;
  #pragma omp target
  #pragma omp teams
  #pragma omp distribute
  for(char i = a; i < 10; ++i);
}

// a is passed as a parameter to the outlined functions
// CHECK:  define {{.*}}void @@.omp_outlined.{{.*}}(i32* noalias [[GBL_TIDP:%.+]], i32* noalias [[BND_TID:%.+]], i8* dereferenceable({{[0-9]+}}) [[APARM:%.+]])
// CHECK:  store i8* [[APARM]], i8** [[APTRADDR:%.+]]
// ..many loads of %0..
// CHECK:  [[A2:%.+]] = load i8*, i8** [[APTRADDR]]
// CHECK:  [[AVAL0:%.+]] = load i8, i8* [[A2]]
// CHECK:  store i8 [[AVAL0]], i8* [[CAP_EXPR:%.+]],
// CHECK:  [[AVAL1:%.+]] = load i8, i8* [[CAP_EXPR]]
// CHECK:  load i8, i8* [[CAP_EXPR]]
// CHECK:  [[AVAL2:%.+]] = load i8, i8* [[CAP_EXPR]]
// CHECK:  [[ACONV:%.+]] = sext i8 [[AVAL2]] to i32
// CHECK:  [[ACMP:%.+]] = icmp slt i32 [[ACONV]], 10
// CHECK:  br i1 [[ACMP]], label %[[PRECOND_THEN:.+]], label %[[PRECOND_END:.+]]
// CHECK:  [[PRECOND_THEN]]
// CHECK:  call void @@__kmpc_for_static_init_4
// CHECK:  call void @@__kmpc_for_static_fini
// CHECK:  [[PRECOND_END]]

// no templates for now, as these require special handling in target regions and/or declare target

// HCHECK-LABEL: fint
// HCHECK: call {{.*}}i32 {{.+}}ftemplate
// HCHECK: ret i32

// HCHECK: load i16, i16*
// HCHECK: store i16 %
// HCHECK: call i32 @@__tgt_target_teams(
// HCHECK: call void @@__kmpc_for_static_init_4(
template <typename T>
T ftemplate() {
  short aa = 0;

#pragma omp target
#pragma omp teams
#pragma omp distribute dist_schedule(static, aa)
  for (int i = 0; i < 100; i++) {
  }
  return T();
}

int fint(void) { return ftemplate<int>(); }

#endif
@


