maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/OpenMP/for_reduction_codegen_UDR.cpp

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

1091 lines
52 KiB
C++
Raw Normal View History

[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck %s
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-apple-darwin10 -emit-pch -o %t %s
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple x86_64-apple-darwin10 -emit-pch -o %t %s
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
[OPENMP] Sync __kmpc_alloc/_kmpc_free function with the runtime. Functions __kmpc_alloc/__kmpc_free are updated with the new interfaces. Patch synchronizes the compiler with the runtime. llvm-svn: 357933
2019-04-09 03:06:42 +08:00
enum omp_allocator_handle_t {
omp_null_allocator = 0,
omp_default_mem_alloc = 1,
omp_large_cap_mem_alloc = 2,
omp_const_mem_alloc = 3,
omp_high_bw_mem_alloc = 4,
omp_low_lat_mem_alloc = 5,
omp_cgroup_mem_alloc = 6,
omp_pteam_mem_alloc = 7,
omp_thread_mem_alloc = 8,
KMP_ALLOCATOR_MAX_HANDLE = __UINTPTR_MAX__
};
[OPENMP]Add codegen for reduction vars with allocate clause, NFC. Added test for the reduction variables with the allocate clause. llvm-svn: 357629
2019-04-04 03:59:09 +08:00
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
volatile double g, g_orig;
volatile double &g1 = g_orig;
struct BaseS {
int x;
};
struct BaseS1 {
float y;
};
template <class T>
struct S : public BaseS, public BaseS1 {
T f;
S(T a) : f(a + g) {}
S() : f(g) {}
[OPENMP]Add assignment operator in UDR test, NFC. Add assignment operator in the test to check that even if the operator was declare explicitly, the constructor is called in the user-defined reduction initializer anyway.
2019-11-15 01:58:49 +08:00
S& operator=(const S&);
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
~S() {}
};
void red(BaseS1&, const BaseS1&);
void red_plus(BaseS1&, const BaseS1&);
void init(BaseS1&, const BaseS1&);
void init1(BaseS1&, const BaseS1&);
void init2(BaseS1&, const BaseS1&);
void init_plus(BaseS1&, const BaseS1&);
#pragma omp declare reduction(operator& : BaseS1 : red(omp_out, omp_in)) initializer(init(omp_priv, omp_orig))
#pragma omp declare reduction(+ : BaseS1 : red_plus(omp_out, omp_in)) initializer(init_plus(omp_priv, omp_orig))
#pragma omp declare reduction(&& : S<float>, S<int> : omp_out.f *= omp_in.f) initializer(init1(omp_priv, omp_orig))
// CHECK-DAG: [[S_FLOAT_TY:%.+]] = type { %{{[^,]+}}, %{{[^,]+}}, float }
// CHECK-DAG: [[S_INT_TY:%.+]] = type { %{{[^,]+}}, %{{[^,]+}}, i{{[0-9]+}} }
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK-DAG: [[IMPLICIT_BARRIER_LOC:@.+]] = private unnamed_addr global %struct.ident_t { i32 0, i32 66, i32 0, i32 0, i8*
// CHECK-DAG: [[REDUCTION_LOC:@.+]] = private unnamed_addr global %struct.ident_t { i32 0, i32 18, i32 0, i32 0, i8*
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK-DAG: [[REDUCTION_LOCK:@.+]] = common global [8 x i32] zeroinitializer
[OPENMP]Use copy constructors instead of assignment operators in declare reduction initializers. Better to use copy constructor at the initialization of the declare reduction construct rather than assignment operator.
2019-11-13 00:19:26 +08:00
#pragma omp declare reduction(operator* : S<int> : omp_out.f = 17 * omp_in.f) initializer(omp_priv = S<int>())
// CHECK-LABEL: bazz
void bazz() {
S<int> s;
// CHECK: [[S_ADDR:%.+]] = alloca [[S_INT_TY]],
// CHECK: call {{.*}} [[S_INT_TY_CONSTR:@.+]]([[S_INT_TY]]* [[S_ADDR]])
// CHECK: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @{{.+}}, i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [[S_INT_TY]]*)* [[BAZZ_OUTLINE:@.+]] to void (i32*, i32*, ...)*), [[S_INT_TY]]* [[S_ADDR]])
// CHECK: call {{.*}} [[S_INT_TY_DESTR:@.+]]([[S_INT_TY]]*
// CHECK: ret void
#pragma omp parallel
#pragma omp simd reduction(*: s)
for (int I = 0; I < 10; ++I)
;
}
// CHECK: define internal void [[BAZZ_OUTLINE]](i32* {{.+}}, i32* {{.+}}, [[S_INT_TY]]* {{.+}})
// CHECK: [[S_PRIV_ADDR:%.+]] = alloca [[S_INT_TY]],
// CHECK: call void [[BAZZ_INIT:@.+]]([[S_INT_TY]]* [[S_PRIV_ADDR]], [[S_INT_TY]]* [[S_ORIG_ADDR:%.+]])
// CHECK: call void @{{.+}}([[S_INT_TY]]* [[S_ORIG_ADDR]], [[S_INT_TY]]* [[S_PRIV_ADDR]])
// CHECK-NEXT: call void [[S_INT_TY_DESTR]]([[S_INT_TY]]* [[S_PRIV_ADDR]])
// CHECK-NEXT: ret void
// CHECK: define internal void [[BAZZ_INIT]]([[S_INT_TY]]* {{.*}}[[S_PRIV_ADDR:%.+]], [[S_INT_TY]]* {{.*}}[[S_ORIG_ADDR:%.+]])
// CHECK: store [[S_INT_TY]]* [[S_PRIV_ADDR]], [[S_INT_TY]]** [[S_PRIV_ADDR_REF:%.+]],
// CHECK: [[S_PRIV_ADDR:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[S_PRIV_ADDR_REF]],
// CHECK: call void [[S_INT_TY_CONSTR]]([[S_INT_TY]]* [[S_PRIV_ADDR]])
// CHECK-NEXT: ret void
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
#pragma omp declare reduction(operator&& : int : omp_out = 111 & omp_in)
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
template <typename T, int length>
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
T tmain() {
T t;
S<T> test;
T t_var = T(), t_var1;
T vec[] = {1, 2};
S<T> s_arr[] = {1, 2};
S<T> &var = test;
S<T> var1;
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
S<T> arr[length];
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
#pragma omp declare reduction(operator& : T : omp_out = 15 + omp_in)
#pragma omp declare reduction(operator+ : T : omp_out = 1513 + omp_in) initializer(omp_priv = 321)
#pragma omp declare reduction(min : T : omp_out = 47 - omp_in) initializer(omp_priv = 432 / omp_orig)
#pragma omp declare reduction(operator&& : S<T> : omp_out.f = 17 * omp_in.f) initializer(init2(omp_priv, omp_orig))
#pragma omp declare reduction(operator&& : T : omp_out = 17 * omp_in)
#pragma omp parallel
#pragma omp for reduction(+ : t_var) reduction(& : var) reduction(&& : var1) reduction(min : t_var1) nowait
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
}
#pragma omp parallel
#pragma omp for reduction(&& : t_var)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
}
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
#pragma omp parallel
#pragma omp for reduction(+ : arr[1:length-2])
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
}
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
return T();
}
extern S<float> **foo();
#pragma omp declare reduction(operator- : float, double : omp_out = 333 + omp_in)
#pragma omp declare reduction(min : float, double : omp_out = 555 + omp_in)
int main() {
#pragma omp declare reduction(operator+ : float, double : omp_out = 222 - omp_in) initializer(omp_priv = -1)
S<float> test;
float t_var = 0, t_var1;
int vec[] = {1, 2};
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
S<float> s_arr[] = {1, 2, 3, 4};
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
S<float> &var = test;
S<float> var1, arrs[10][4];
S<float> **var2 = foo();
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
S<float> vvar2[5];
S<float>(&var3)[4] = s_arr;
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
#pragma omp declare reduction(operator+ : int : omp_out = 555 * omp_in) initializer(omp_priv = 888)
#pragma omp parallel
#pragma omp for reduction(+ : t_var) reduction(& : var) reduction(&& : var1) reduction(min : t_var1)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
}
int arr[10][vec[1]];
#pragma omp parallel for reduction(+ : arr[1][ : vec[1]]) reduction(& : arrs[1 : vec[1]][1 : 2])
for (int i = 0; i < 10; ++i)
++arr[1][i];
#pragma omp parallel
#pragma omp for reduction(+ : arr) reduction(& : arrs)
for (int i = 0; i < 10; ++i)
++arr[1][i];
#pragma omp parallel
#pragma omp for reduction(& : var2[0 : 5][1 : 6])
for (int i = 0; i < 10; ++i)
;
#pragma omp parallel
#pragma omp for reduction(& : vvar2[0 : 5])
for (int i = 0; i < 10; ++i)
;
#pragma omp parallel
#pragma omp for reduction(& : var3[1 : 2])
for (int i = 0; i < 10; ++i)
;
#pragma omp parallel
[OPENMP]Add codegen for reduction vars with allocate clause, NFC. Added test for the reduction variables with the allocate clause. llvm-svn: 357629
2019-04-04 03:59:09 +08:00
#pragma omp for reduction(& : var3) allocate(omp_cgroup_mem_alloc: var3)
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
for (int i = 0; i < 10; ++i)
;
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
return tmain<int, 42>();
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
}
// CHECK: define {{.*}}i{{[0-9]+}} @main()
// CHECK: [[TEST:%.+]] = alloca [[S_FLOAT_TY]],
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call {{.*}} [[S_FLOAT_TY_CONSTR:@.+]]([[S_FLOAT_TY]]* [[TEST]])
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 6, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, float*, [[S_FLOAT_TY]]*, [[S_FLOAT_TY]]*, float*, [2 x i32]*, [4 x [[S_FLOAT_TY]]]*)* [[MAIN_MICROTASK:@.+]] to void
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 5, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, i64, i64, i32*, [2 x i32]*, [10 x [4 x [[S_FLOAT_TY]]]]*)* [[MAIN_MICROTASK1:@.+]] to void
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 4, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, i64, i64, i32*, [10 x [4 x [[S_FLOAT_TY]]]]*)* [[MAIN_MICROTASK2:@.+]] to void
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 1, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, [[S_FLOAT_TY]]***)* [[MAIN_MICROTASK3:@.+]] to void
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 1, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, [5 x [[S_FLOAT_TY]]]*)* [[MAIN_MICROTASK4:@.+]] to void
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 1, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, [4 x [[S_FLOAT_TY]]]*)* [[MAIN_MICROTASK5:@.+]] to void
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 1, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, [4 x [[S_FLOAT_TY]]]*)* [[MAIN_MICROTASK6:@.+]] to void
// CHECK: = call {{.*}}i{{.+}} [[TMAIN_INT_42:@.+]]()
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call {{.*}} [[S_FLOAT_TY_DESTR:@.+]]([[S_FLOAT_TY]]*
// CHECK: ret
//
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: define internal void [[MAIN_MICROTASK]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, float* dereferenceable(4) %{{.+}}, [[S_FLOAT_TY]]* dereferenceable(12) %{{.+}}, [[S_FLOAT_TY]]* dereferenceable(12) %{{.+}}, float* dereferenceable(4) %{{.+}}, [2 x i32]* dereferenceable(8) %vec, [4 x [[S_FLOAT_TY]]]* dereferenceable(48) %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[T_VAR_PRIV:%.+]] = alloca float,
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_FLOAT_TY]],
// CHECK: [[VAR1_PRIV:%.+]] = alloca [[S_FLOAT_TY]],
// CHECK: [[T_VAR1_PRIV:%.+]] = alloca float,
// Reduction list for runtime.
// CHECK: [[RED_LIST:%.+]] = alloca [4 x i8*],
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_ADDR:%.+]],
// CHECK: [[T_VAR_REF:%.+]] = load float*, float** %
// CHECK: [[VAR1_REF:%.+]] = load [[S_FLOAT_TY]]*, [[S_FLOAT_TY]]** %
// CHECK: [[T_VAR1_REF:%.+]] = load float*, float** %
// For + reduction operation initial value of private variable is -1.
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_INIT1:@.+]](float* %{{.+}}, float* %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// For & reduction operation initial value of private variable is defined by call of 'init()' function.
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_INIT2:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// For && reduction operation initial value of private variable is 1.0.
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_INIT3:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// For min reduction operation initial value of private variable is largest repesentable value.
// CHECK: [[INIT:%.+]] = load float, float* @
// CHECK: store float [[INIT]], float* [[T_VAR1_PRIV]],
// CHECK: [[GTID_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[GTID_ADDR_ADDR]]
// CHECK: [[GTID:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[GTID_REF]]
// CHECK: call void @__kmpc_for_static_init_4(
// Skip checks for internal operations.
// CHECK: call void @__kmpc_for_static_fini(
// void *RedList[<n>] = {<ReductionVars>[0], ..., <ReductionVars>[<n>-1]};
// CHECK: [[T_VAR_PRIV_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 0
// CHECK: [[BITCAST:%.+]] = bitcast float* [[T_VAR_PRIV]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[T_VAR_PRIV_REF]],
// CHECK: [[VAR_PRIV_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 1
// CHECK: [[BITCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[VAR_PRIV]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[VAR_PRIV_REF]],
// CHECK: [[VAR1_PRIV_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 2
// CHECK: [[BITCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[VAR1_PRIV]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[VAR1_PRIV_REF]],
// CHECK: [[T_VAR1_PRIV_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 3
// CHECK: [[BITCAST:%.+]] = bitcast float* [[T_VAR1_PRIV]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[T_VAR1_PRIV_REF]],
// res = __kmpc_reduce(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>);
// CHECK: [[BITCAST:%.+]] = bitcast [4 x i8*]* [[RED_LIST]] to i8*
// CHECK: [[RES:%.+]] = call i32 @__kmpc_reduce(%{{.+}}* [[REDUCTION_LOC]], i32 [[GTID]], i32 4, i64 32, i8* [[BITCAST]], void (i8*, i8*)* [[REDUCTION_FUNC:@.+]], [8 x i32]* [[REDUCTION_LOCK]])
// switch(res)
// CHECK: switch i32 [[RES]], label %[[RED_DONE:.+]] [
// CHECK: i32 1, label %[[CASE1:.+]]
// CHECK: i32 2, label %[[CASE2:.+]]
// CHECK: ]
// case 1:
// t_var += t_var_reduction;
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB1:@.+]](float* %{{.+}}, float* %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// var = var.operator &(var_reduction);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// var1 = var1.operator &&(var1_reduction);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB3:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// t_var1 = min(t_var1, t_var1_reduction);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB4:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// __kmpc_end_reduce(<loc>, <gtid>, &<lock>);
// CHECK: call void @__kmpc_end_reduce(%{{.+}}* [[REDUCTION_LOC]], i32 [[GTID]], [8 x i32]* [[REDUCTION_LOCK]])
// break;
// CHECK: br label %[[RED_DONE]]
// case 2:
// t_var += t_var_reduction;
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB1]](float* %{{.+}}, float* %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// var = var.operator &(var_reduction);
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2]]
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// var1 = var1.operator &&(var1_reduction);
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB3]]
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// t_var1 = min(t_var1, t_var1_reduction);
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB4]]
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// __kmpc_end_reduce(<loc>, <gtid>, &<lock>);
// CHECK: call void @__kmpc_end_reduce(%{{.+}}* [[REDUCTION_LOC]], i32 [[GTID]], [8 x i32]* [[REDUCTION_LOCK]])
// break;
// CHECK: br label %[[RED_DONE]]
// CHECK: [[RED_DONE]]
// CHECK-DAG: call {{.*}} [[S_FLOAT_TY_DESTR]]([[S_FLOAT_TY]]* [[VAR_PRIV]])
// CHECK-DAG: call {{.*}} [[S_FLOAT_TY_DESTR]]([[S_FLOAT_TY]]*
// CHECK: call void @__kmpc_barrier(%{{.+}}* [[IMPLICIT_BARRIER_LOC]], i{{[0-9]+}} [[GTID]])
// CHECK: ret void
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[RED_COMB1]](float* noalias %0, float* noalias %1)
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: fsub float 2.220000e+02, %
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[RED_INIT1]](float* noalias %0, float* noalias %1)
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: store float -1.0{{.+}}, float*
// CHECK: define internal void [[RED_COMB2]](
// CHECK: call {{.*}}void @_Z3redR6BaseS1RKS_(
// CHECK: define internal void [[RED_INIT2]](
// CHECK: call {{.*}}void @_Z4initR6BaseS1RKS_(
// CHECK: define internal void [[RED_COMB3]](
// CHECK: fmul float
// CHECK: define internal void [[RED_INIT3]](
// CHECK: call {{.*}}void @_Z5init1R6BaseS1RKS_(
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// void reduce_func(void *lhs[<n>], void *rhs[<n>]) {
// *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]);
// ...
// *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1],
// *(Type<n>-1*)rhs[<n>-1]);
// }
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[REDUCTION_FUNC]](i8* %0, i8* %1)
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// t_var_lhs = (float*)lhs[0];
// CHECK: [[T_VAR_RHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_RHS:%.+]], i64 0, i64 0
// CHECK: [[T_VAR_RHS_VOID:%.+]] = load i8*, i8** [[T_VAR_RHS_REF]],
// CHECK: [[T_VAR_RHS:%.+]] = bitcast i8* [[T_VAR_RHS_VOID]] to float*
// t_var_rhs = (float*)rhs[0];
// CHECK: [[T_VAR_LHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS:%.+]], i64 0, i64 0
// CHECK: [[T_VAR_LHS_VOID:%.+]] = load i8*, i8** [[T_VAR_LHS_REF]],
// CHECK: [[T_VAR_LHS:%.+]] = bitcast i8* [[T_VAR_LHS_VOID]] to float*
// var_lhs = (S<float>*)lhs[1];
// CHECK: [[VAR_RHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_RHS]], i64 0, i64 1
// CHECK: [[VAR_RHS_VOID:%.+]] = load i8*, i8** [[VAR_RHS_REF]],
// CHECK: [[VAR_RHS:%.+]] = bitcast i8* [[VAR_RHS_VOID]] to [[S_FLOAT_TY]]*
// var_rhs = (S<float>*)rhs[1];
// CHECK: [[VAR_LHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS]], i64 0, i64 1
// CHECK: [[VAR_LHS_VOID:%.+]] = load i8*, i8** [[VAR_LHS_REF]],
// CHECK: [[VAR_LHS:%.+]] = bitcast i8* [[VAR_LHS_VOID]] to [[S_FLOAT_TY]]*
// var1_lhs = (S<float>*)lhs[2];
// CHECK: [[VAR1_RHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_RHS]], i64 0, i64 2
// CHECK: [[VAR1_RHS_VOID:%.+]] = load i8*, i8** [[VAR1_RHS_REF]],
// CHECK: [[VAR1_RHS:%.+]] = bitcast i8* [[VAR1_RHS_VOID]] to [[S_FLOAT_TY]]*
// var1_rhs = (S<float>*)rhs[2];
// CHECK: [[VAR1_LHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS]], i64 0, i64 2
// CHECK: [[VAR1_LHS_VOID:%.+]] = load i8*, i8** [[VAR1_LHS_REF]],
// CHECK: [[VAR1_LHS:%.+]] = bitcast i8* [[VAR1_LHS_VOID]] to [[S_FLOAT_TY]]*
// t_var1_lhs = (float*)lhs[3];
// CHECK: [[T_VAR1_RHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_RHS]], i64 0, i64 3
// CHECK: [[T_VAR1_RHS_VOID:%.+]] = load i8*, i8** [[T_VAR1_RHS_REF]],
// CHECK: [[T_VAR1_RHS:%.+]] = bitcast i8* [[T_VAR1_RHS_VOID]] to float*
// t_var1_rhs = (float*)rhs[3];
// CHECK: [[T_VAR1_LHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS]], i64 0, i64 3
// CHECK: [[T_VAR1_LHS_VOID:%.+]] = load i8*, i8** [[T_VAR1_LHS_REF]],
// CHECK: [[T_VAR1_LHS:%.+]] = bitcast i8* [[T_VAR1_LHS_VOID]] to float*
// t_var_lhs += t_var_rhs;
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB1]](float* %{{.+}}, float* %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// var_lhs = var_lhs.operator &(var_rhs);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// var1_lhs = var1_lhs.operator &&(var1_rhs);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB3]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// t_var1_lhs = min(t_var1_lhs, t_var1_rhs);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB4]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: ret void
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: define internal void [[RED_COMB4]](
// CHECK: fadd float 5.550000e+02, %
[OPENMP] Fix PR35013: Fix passing VLAs captures to outlined functions. Fixed passing of VLAs and variably-modified types to outlined functions. Synchronized passing with the types codegen. llvm-svn: 316488
2017-10-25 03:52:31 +08:00
// CHECK: define internal void [[MAIN_MICROTASK1]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, i64 %{{.+}}, i64 %{{.+}}, i32* {{.+}} %{{.+}}, [2 x i32]* dereferenceable(8) %{{.+}}, [10 x [4 x [[S_FLOAT_TY]]]]* dereferenceable(480) %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// Reduction list for runtime.
// CHECK: [[RED_LIST:%.+]] = alloca [4 x i8*],
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_ADDR:%.+]],
[OPENMP] Fix reduction tests, NFC. llvm-svn: 307911
2017-07-13 22:29:19 +08:00
// CHECK: store i{{[0-9]+}}* %{{.+}}, i{{[0-9]+}}**
// CHECK: store i{{[0-9]+}}* %{{.+}}, i{{[0-9]+}}** [[ARR_ADDR:%.+]],
// CHECK: [[ARR:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[ARR_ADDR]],
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
[OPENMP] Fix reduction tests, NFC. llvm-svn: 307912
2017-07-13 22:54:42 +08:00
// CHECK: [[UB_CAST:%.+]] = ptrtoint i32* [[UB1_UP:%.+]] to i64
// CHECK: [[LB_CAST:%.+]] = ptrtoint i32* [[LB1_0:%.+]] to i64
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DIFF:%.+]] = sub i64 [[UB_CAST]], [[LB_CAST]]
// CHECK: [[SIZE_1:%.+]] = sdiv exact i64 [[DIFF]], ptrtoint (i32* getelementptr (i32, i32* null, i32 1) to i64)
// CHECK: [[ARR_SIZE:%.+]] = add nuw i64 [[SIZE_1]], 1
// CHECK: call i8* @llvm.stacksave()
// CHECK: [[ARR_PRIV:%.+]] = alloca i32, i64 [[ARR_SIZE]],
// Check initialization of private copy.
// CHECK: [[END:%.+]] = getelementptr i32, i32* [[ARR_PRIV]], i64 [[ARR_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq i32* [[ARR_PRIV]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi i32*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_INIT5:@.+]](i32* %{{.+}}, i32* %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq i32* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// CHECK: [[ARRS_PRIV:%.+]] = alloca [[S_FLOAT_TY]], i64 [[ARRS_SIZE:%.+]],
// Check initialization of private copy.
// CHECK: [[END:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[ARRS_PRIV]], i64 [[ARRS_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq [[S_FLOAT_TY]]* [[ARRS_PRIV]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi [[S_FLOAT_TY]]*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_INIT2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq [[S_FLOAT_TY]]* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// CHECK: [[GTID_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[GTID_ADDR_ADDR]]
// CHECK: [[GTID:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[GTID_REF]]
// CHECK: call void @__kmpc_for_static_init_4(
// Skip checks for internal operations.
// CHECK: call void @__kmpc_for_static_fini(
// void *RedList[<n>] = {<ReductionVars>[0], ..., <ReductionVars>[<n>-1]};
// CHECK: [[ARR_PRIV_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 0
// CHECK: [[BITCAST:%.+]] = bitcast i32* [[ARR_PRIV]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[ARR_PRIV_REF]],
// CHECK: [[ARR_SIZE_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 1
// CHECK: [[BITCAST:%.+]] = inttoptr i64 [[ARR_SIZE]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[ARR_SIZE_REF]],
// CHECK: [[ARRS_PRIV_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 2
// CHECK: [[BITCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[ARRS_PRIV]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[ARRS_PRIV_REF]],
// CHECK: [[ARRS_SIZE_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 3
// CHECK: [[BITCAST:%.+]] = inttoptr i64 [[ARRS_SIZE]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[ARRS_SIZE_REF]],
// res = __kmpc_reduce(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>);
// CHECK: [[GTID_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[GTID_ADDR_ADDR]]
// CHECK: [[GTID:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[GTID_REF]]
// CHECK: [[BITCAST:%.+]] = bitcast [4 x i8*]* [[RED_LIST]] to i8*
// CHECK: [[RES:%.+]] = call i32 @__kmpc_reduce_nowait(%{{.+}}* [[REDUCTION_LOC]], i32 [[GTID]], i32 2, i64 32, i8* [[BITCAST]], void (i8*, i8*)* [[REDUCTION_FUNC:@.+]], [8 x i32]* [[REDUCTION_LOCK]])
// switch(res)
// CHECK: switch i32 [[RES]], label %[[RED_DONE:.+]] [
// CHECK: i32 1, label %[[CASE1:.+]]
// CHECK: i32 2, label %[[CASE2:.+]]
// CHECK: ]
// case 1:
// CHECK: [[CASE1]]
// arr[:] += arr_reduction[:];
// CHECK: [[END:%.+]] = getelementptr i32, i32* [[LB1_0]], i64 [[ARR_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq i32* [[LB1_0]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi i32*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB5:@.+]](i32* %{{.+}}, i32* %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq i32* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// arrs[:] = var.operator &(arrs_reduction[:]);
// CHECK: [[END:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[ARRS_LB:%.+]], i64 [[ARRS_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq [[S_FLOAT_TY]]* [[ARRS_LB]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi [[S_FLOAT_TY]]*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq [[S_FLOAT_TY]]* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// __kmpc_end_reduce(<loc>, <gtid>, &<lock>);
// CHECK: call void @__kmpc_end_reduce_nowait(%{{.+}}* [[REDUCTION_LOC]], i32 [[GTID]], [8 x i32]* [[REDUCTION_LOCK]])
// break;
// CHECK: br label %[[RED_DONE]]
// case 2:
// CHECK: [[CASE2]]
// arr[:] += arr_reduction[:];
// CHECK: [[END:%.+]] = getelementptr i32, i32* [[LB1_0]], i64 [[ARR_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq i32* [[LB1_0]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi i32*
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB5]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// CHECK: [[DONE:%.+]] = icmp eq i32* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// arrs[:] = var.operator &(arrs_reduction[:]);
// CHECK: [[END:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[ARRS_LB:%.+]], i64 [[ARRS_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq [[S_FLOAT_TY]]* [[ARRS_LB]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi [[S_FLOAT_TY]]*
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// CHECK: [[DONE:%.+]] = icmp eq [[S_FLOAT_TY]]* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// break;
// CHECK: br label %[[RED_DONE]]
// CHECK: [[RED_DONE]]
// Check destruction of private copy.
// CHECK: [[END:%.+]] = getelementptr inbounds [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[ARRS_PRIV]], i64 [[ARRS_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq [[S_FLOAT_TY]]* [[ARRS_PRIV]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi [[S_FLOAT_TY]]*
// CHECK: call void @_ZN1SIfED1Ev([[S_FLOAT_TY]]* %
// CHECK: [[DONE:%.+]] = icmp eq [[S_FLOAT_TY]]* %{{.+}}, [[ARRS_PRIV]]
// CHECK: br i1 [[DONE]],
// CHECK: call void @llvm.stackrestore(i8*
// CHECK: ret void
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[RED_COMB5]](i32* noalias %0, i32* noalias %1)
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: mul nsw i32 555, %
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[RED_INIT5]](i32* noalias %0, i32* noalias %1)
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: store i32 888, i32* %
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// void reduce_func(void *lhs[<n>], void *rhs[<n>]) {
// *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]);
// ...
// *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1],
// *(Type<n>-1*)rhs[<n>-1]);
// }
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[REDUCTION_FUNC]](i8* %0, i8* %1)
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// arr_rhs = (int*)rhs[0];
// CHECK: [[ARR_RHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_RHS:%.+]], i64 0, i64 0
// CHECK: [[ARR_RHS_VOID:%.+]] = load i8*, i8** [[ARR_RHS_REF]],
// CHECK: [[ARR_RHS:%.+]] = bitcast i8* [[ARR_RHS_VOID]] to i32*
// arr_lhs = (int*)lhs[0];
// CHECK: [[ARR_LHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS:%.+]], i64 0, i64 0
// CHECK: [[ARR_LHS_VOID:%.+]] = load i8*, i8** [[ARR_LHS_REF]],
// CHECK: [[ARR_LHS:%.+]] = bitcast i8* [[ARR_LHS_VOID]] to i32*
// arr_size = (size_t)lhs[1];
// CHECK: [[ARR_SIZE_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS]], i64 0, i64 1
// CHECK: [[ARR_SIZE_VOID:%.+]] = load i8*, i8** [[ARR_SIZE_REF]],
// CHECK: [[ARR_SIZE:%.+]] = ptrtoint i8* [[ARR_SIZE_VOID]] to i64
// arrs_rhs = (S<float>*)rhs[2];
// CHECK: [[ARRS_RHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_RHS]], i64 0, i64 2
// CHECK: [[ARRS_RHS_VOID:%.+]] = load i8*, i8** [[ARRS_RHS_REF]],
// CHECK: [[ARRS_RHS:%.+]] = bitcast i8* [[ARRS_RHS_VOID]] to [[S_FLOAT_TY]]*
// arrs_lhs = (S<float>*)lhs[2];
// CHECK: [[ARRS_LHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS]], i64 0, i64 2
// CHECK: [[ARRS_LHS_VOID:%.+]] = load i8*, i8** [[ARRS_LHS_REF]],
// CHECK: [[ARRS_LHS:%.+]] = bitcast i8* [[ARRS_LHS_VOID]] to [[S_FLOAT_TY]]*
// arrs_size = (size_t)lhs[3];
// CHECK: [[ARRS_SIZE_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS]], i64 0, i64 3
// CHECK: [[ARRS_SIZE_VOID:%.+]] = load i8*, i8** [[ARRS_SIZE_REF]],
// CHECK: [[ARRS_SIZE:%.+]] = ptrtoint i8* [[ARRS_SIZE_VOID]] to i64
// arr_lhs[:] += arr_rhs[:];
// CHECK: [[END:%.+]] = getelementptr i32, i32* [[ARR_LHS]], i64 [[ARR_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq i32* [[ARR_LHS]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi i32*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB5]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq i32* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// arrs_lhs = arrs_lhs.operator &(arrs_rhs);
// CHECK: [[END:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[ARRS_LB:%.+]], i64 [[ARRS_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq [[S_FLOAT_TY]]* [[ARRS_LB]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi [[S_FLOAT_TY]]*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq [[S_FLOAT_TY]]* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// CHECK: ret void
[OPENMP] Fix PR35013: Fix passing VLAs captures to outlined functions. Fixed passing of VLAs and variably-modified types to outlined functions. Synchronized passing with the types codegen. llvm-svn: 316488
2017-10-25 03:52:31 +08:00
// CHECK: define internal void [[MAIN_MICROTASK2]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, i64 %{{.+}}, i64 %{{.+}}, i32* {{.+}} %{{.+}}, [10 x [4 x [[S_FLOAT_TY]]]]* dereferenceable(480) %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[ARRS_PRIV:%.+]] = alloca [10 x [4 x [[S_FLOAT_TY]]]],
// Reduction list for runtime.
// CHECK: [[RED_LIST:%.+]] = alloca [3 x i8*],
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_ADDR:%.+]],
[OPENMP] Codegen for reduction clauses in 'taskloop' directives. Adds codegen for taskloop-based directives. llvm-svn: 308174
2017-07-17 21:30:36 +08:00
// CHECK: [[ARR_SIZE:%.+]] = udiv exact i64
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call i8* @llvm.stacksave()
// CHECK: [[ARR_PRIV:%.+]] = alloca i32, i64 [[ARR_SIZE]],
// Check initialization of private copy.
// CHECK: [[END:%.+]] = getelementptr i32, i32* [[ARR_PRIV]], i64 [[ARR_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq i32* [[ARR_PRIV]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi i32*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_INIT5]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq i32* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// Check initialization of private copy.
// CHECK: [[BEGIN:%.+]] = getelementptr inbounds [10 x [4 x [[S_FLOAT_TY]]]], [10 x [4 x [[S_FLOAT_TY]]]]* [[ARRS_PRIV]], i32 0, i32 0, i32 0
[OPENMP] Generalization of codegen for reduction clauses. Reworked codegen for reduction clauses for future support of reductions in task-based directives. llvm-svn: 307910
2017-07-13 21:36:14 +08:00
// CHECK: [[LHS_BEGIN:%.+]] = bitcast [10 x [4 x [[S_FLOAT_TY]]]]* %{{.+}} to [[S_FLOAT_TY]]*
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[END:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[BEGIN]], i64 40
// CHECK: [[ISEMPTY:%.+]] = icmp eq [[S_FLOAT_TY]]* [[BEGIN]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi [[S_FLOAT_TY]]*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_INIT2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq [[S_FLOAT_TY]]* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
[OPENMP] Generalization of codegen for reduction clauses. Reworked codegen for reduction clauses for future support of reductions in task-based directives. llvm-svn: 307910
2017-07-13 21:36:14 +08:00
// CHECK: [[LHS_BEGIN:%.+]] = bitcast [10 x [4 x [[S_FLOAT_TY]]]]* %{{.+}} to [[S_FLOAT_TY]]*
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[ARRS_PRIV_BEGIN:%.+]] = bitcast [10 x [4 x [[S_FLOAT_TY]]]]* [[ARRS_PRIV]] to [[S_FLOAT_TY]]*
// CHECK: [[GTID_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[GTID_ADDR_ADDR]]
// CHECK: [[GTID:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[GTID_REF]]
// CHECK: call void @__kmpc_for_static_init_4(
// Skip checks for internal operations.
// CHECK: call void @__kmpc_for_static_fini(
// void *RedList[<n>] = {<ReductionVars>[0], ..., <ReductionVars>[<n>-1]};
// CHECK: [[ARR_PRIV_REF:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[RED_LIST]], i64 0, i64 0
// CHECK: [[BITCAST:%.+]] = bitcast i32* [[ARR_PRIV]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[ARR_PRIV_REF]],
// CHECK: [[ARR_SIZE_REF:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[RED_LIST]], i64 0, i64 1
// CHECK: [[BITCAST:%.+]] = inttoptr i64 [[ARR_SIZE]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[ARR_SIZE_REF]],
// CHECK: [[ARRS_PRIV_REF:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[RED_LIST]], i64 0, i64 2
// CHECK: [[BITCAST:%.+]] = bitcast [[S_FLOAT_TY]]* [[ARRS_PRIV_BEGIN]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[ARRS_PRIV_REF]],
// res = __kmpc_reduce(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>);
// CHECK: [[GTID_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[GTID_ADDR_ADDR]]
// CHECK: [[GTID:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[GTID_REF]]
// CHECK: [[BITCAST:%.+]] = bitcast [3 x i8*]* [[RED_LIST]] to i8*
// CHECK: [[RES:%.+]] = call i32 @__kmpc_reduce(%{{.+}}* [[REDUCTION_LOC]], i32 [[GTID]], i32 2, i64 24, i8* [[BITCAST]], void (i8*, i8*)* [[REDUCTION_FUNC:@.+]], [8 x i32]* [[REDUCTION_LOCK]])
// switch(res)
// CHECK: switch i32 [[RES]], label %[[RED_DONE:.+]] [
// CHECK: i32 1, label %[[CASE1:.+]]
// CHECK: i32 2, label %[[CASE2:.+]]
// CHECK: ]
// case 1:
// CHECK: [[CASE1]]
// arr[:] += arr_reduction[:];
// CHECK: [[END:%.+]] = getelementptr i32, i32* [[LB1_0:%.+]], i64 [[ARR_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq i32* [[LB1_0]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi i32*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB5]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq i32* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// arrs[:] = var.operator &(arrs_reduction[:]);
// CHECK: [[END:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[LHS_BEGIN]], i64 40
// CHECK: [[ISEMPTY:%.+]] = icmp eq [[S_FLOAT_TY]]* [[LHS_BEGIN]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi [[S_FLOAT_TY]]*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq [[S_FLOAT_TY]]* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// __kmpc_end_reduce(<loc>, <gtid>, &<lock>);
// CHECK: call void @__kmpc_end_reduce(%{{.+}}* [[REDUCTION_LOC]], i32 [[GTID]], [8 x i32]* [[REDUCTION_LOCK]])
// break;
// CHECK: br label %[[RED_DONE]]
// case 2:
// CHECK: [[CASE2]]
// arr[:] += arr_reduction[:];
// CHECK: [[END:%.+]] = getelementptr i32, i32* [[LB1_0]], i64 [[ARR_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq i32* [[LB1_0]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi i32*
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB5]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// CHECK: [[DONE:%.+]] = icmp eq i32* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// arrs[:] = var.operator &(arrs_reduction[:]);
// CHECK: [[END:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[LHS_BEGIN]], i64 40
// CHECK: [[ISEMPTY:%.+]] = icmp eq [[S_FLOAT_TY]]* [[LHS_BEGIN]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi [[S_FLOAT_TY]]*
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// CHECK: [[DONE:%.+]] = icmp eq [[S_FLOAT_TY]]* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// break;
// CHECK: br label %[[RED_DONE]]
// CHECK: [[RED_DONE]]
// Check destruction of private copy.
// CHECK: [[BEGIN:%.+]] = getelementptr inbounds [10 x [4 x [[S_FLOAT_TY]]]], [10 x [4 x [[S_FLOAT_TY]]]]* [[ARRS_PRIV]], i32 0, i32 0, i32 0
// CHECK: [[END:%.+]] = getelementptr inbounds [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[BEGIN]], i64 40
// CHECK: br
// CHECK: phi [[S_FLOAT_TY]]*
// CHECK: call void @_ZN1SIfED1Ev([[S_FLOAT_TY]]* %
// CHECK: [[DONE:%.+]] = icmp eq [[S_FLOAT_TY]]* %{{.+}}, [[BEGIN]]
// CHECK: br i1 [[DONE]],
// CHECK: call void @llvm.stackrestore(i8*
// CHECK: call void @__kmpc_barrier(
// CHECK: ret void
// void reduce_func(void *lhs[<n>], void *rhs[<n>]) {
// *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]);
// ...
// *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1],
// *(Type<n>-1*)rhs[<n>-1]);
// }
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[REDUCTION_FUNC]](i8* %0, i8* %1)
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// arr_rhs = (int*)rhs[0];
// CHECK: [[ARR_RHS_REF:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[RED_LIST_RHS:%.+]], i64 0, i64 0
// CHECK: [[ARR_RHS_VOID:%.+]] = load i8*, i8** [[ARR_RHS_REF]],
// CHECK: [[ARR_RHS:%.+]] = bitcast i8* [[ARR_RHS_VOID]] to i32*
// arr_lhs = (int*)lhs[0];
// CHECK: [[ARR_LHS_REF:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[RED_LIST_LHS:%.+]], i64 0, i64 0
// CHECK: [[ARR_LHS_VOID:%.+]] = load i8*, i8** [[ARR_LHS_REF]],
// CHECK: [[ARR_LHS:%.+]] = bitcast i8* [[ARR_LHS_VOID]] to i32*
// arr_size = (size_t)lhs[1];
// CHECK: [[ARR_SIZE_REF:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[RED_LIST_LHS]], i64 0, i64 1
// CHECK: [[ARR_SIZE_VOID:%.+]] = load i8*, i8** [[ARR_SIZE_REF]],
// CHECK: [[ARR_SIZE:%.+]] = ptrtoint i8* [[ARR_SIZE_VOID]] to i64
// arrs_rhs = (S<float>*)rhs[2];
// CHECK: [[ARRS_RHS_REF:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[RED_LIST_RHS]], i64 0, i64 2
// CHECK: [[ARRS_RHS_VOID:%.+]] = load i8*, i8** [[ARRS_RHS_REF]],
// CHECK: [[ARRS_RHS:%.+]] = bitcast i8* [[ARRS_RHS_VOID]] to [[S_FLOAT_TY]]*
// arrs_lhs = (S<float>*)lhs[2];
// CHECK: [[ARRS_LHS_REF:%.+]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[RED_LIST_LHS]], i64 0, i64 2
// CHECK: [[ARRS_LHS_VOID:%.+]] = load i8*, i8** [[ARRS_LHS_REF]],
// CHECK: [[ARRS_LHS:%.+]] = bitcast i8* [[ARRS_LHS_VOID]] to [[S_FLOAT_TY]]*
// arr_lhs[:] += arr_rhs[:];
// CHECK: [[END:%.+]] = getelementptr i32, i32* [[ARR_LHS]], i64 [[ARR_SIZE]]
// CHECK: [[ISEMPTY:%.+]] = icmp eq i32* [[ARR_LHS]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi i32*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB5]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq i32* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// arrs_lhs = arrs_lhs.operator &(arrs_rhs);
// CHECK: [[END:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[ARRS_LB:%.+]], i64 40
// CHECK: [[ISEMPTY:%.+]] = icmp eq [[S_FLOAT_TY]]* [[ARRS_LB]], [[END]]
// CHECK: br i1 [[ISEMPTY]],
// CHECK: phi [[S_FLOAT_TY]]*
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[DONE:%.+]] = icmp eq [[S_FLOAT_TY]]* %{{.+}}, [[END]]
// CHECK: br i1 [[DONE]],
// CHECK: ret void
// CHECK: define internal void [[MAIN_MICROTASK3]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, [[S_FLOAT_TY]]*** dereferenceable(8) %{{.+}})
// CHECK: [[VAR2_ORIG_ADDR:%.+]] = alloca [[S_FLOAT_TY]]***,
// Reduction list for runtime.
// CHECK: [[RED_LIST:%.+]] = alloca [2 x i8*],
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_ADDR:%.+]],
// CHECK: [[VAR2_ORIG:%.+]] = load [[S_FLOAT_TY]]***, [[S_FLOAT_TY]]**** [[VAR2_ORIG_ADDR]],
// CHECK: [[LAST:%.+]] = ptrtoint [[S_FLOAT_TY]]* %{{.+}} to i64
[OPENMP] Further reduction test fix, NFC. llvm-svn: 307914
2017-07-13 23:02:27 +08:00
// CHECK: [[FIRST:%.+]] = ptrtoint [[S_FLOAT_TY]]* [[LOW:%.+]] to i64
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[BYTE_DIF:%.+]] = sub i64 [[LAST]], [[FIRST]]
// CHECK: [[DIF:%.+]] = sdiv exact i64 [[BYTE_DIF]], ptrtoint ([[S_FLOAT_TY]]* getelementptr ([[S_FLOAT_TY]], [[S_FLOAT_TY]]* null, i32 1) to i64)
// CHECK: [[SIZE:%.+]] = add nuw i64 [[DIF]], 1
// CHECK: call i8* @llvm.stacksave()
// CHECK: [[VAR2_PRIV:%.+]] = alloca [[S_FLOAT_TY]], i64 [[SIZE]],
[OPENMP] Generalization of codegen for reduction clauses. Reworked codegen for reduction clauses for future support of reductions in task-based directives. llvm-svn: 307910
2017-07-13 21:36:14 +08:00
// CHECK: [[LD:%.+]] = load [[S_FLOAT_TY]]**, [[S_FLOAT_TY]]*** [[VAR2_ORIG]],
// CHECK: [[ORIG_START:%.+]] = load [[S_FLOAT_TY]]*, [[S_FLOAT_TY]]** [[LD]],
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[START:%.+]] = ptrtoint [[S_FLOAT_TY]]* [[ORIG_START]] to i64
// CHECK: [[LOW_BOUND:%.+]] = ptrtoint [[S_FLOAT_TY]]* [[LOW]] to i64
// CHECK: [[OFFSET_BYTES:%.+]] = sub i64 [[START]], [[LOW_BOUND]]
// CHECK: [[OFFSET:%.+]] = sdiv exact i64 [[OFFSET_BYTES]], ptrtoint ([[S_FLOAT_TY]]* getelementptr ([[S_FLOAT_TY]], [[S_FLOAT_TY]]* null, i32 1) to i64)
// CHECK: [[PSEUDO_VAR2_PRIV:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[VAR2_PRIV]], i64 [[OFFSET]]
// CHECK: store [[S_FLOAT_TY]]** [[REF:.+]], [[S_FLOAT_TY]]*** %
// CHECK: store [[S_FLOAT_TY]]* [[PSEUDO_VAR2_PRIV]], [[S_FLOAT_TY]]** [[REF]]
// CHECK: ret void
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: define internal void [[MAIN_MICROTASK4]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, [5 x [[S_FLOAT_TY]]]* dereferenceable(60) %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: [[VVAR2_ORIG_ADDR:%.+]] = alloca [5 x [[S_FLOAT_TY]]]*,
// CHECK: [[VVAR2_PRIV:%.+]] = alloca [5 x [[S_FLOAT_TY]]],
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// Reduction list for runtime.
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: [[RED_LIST:%.+]] = alloca [1 x i8*],
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_ADDR:%.+]],
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: [[VVAR2_ORIG:%.+]] = load [5 x [[S_FLOAT_TY]]]*, [5 x [[S_FLOAT_TY]]]** [[VVAR2_ORIG_ADDR]],
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: [[LOW:%.+]] = getelementptr inbounds [5 x [[S_FLOAT_TY]]], [5 x [[S_FLOAT_TY]]]* [[VVAR2_ORIG]], i64 0, i64 0
// CHECK: [[ORIG_START:%.+]] = bitcast [5 x [[S_FLOAT_TY]]]* [[VVAR2_ORIG]] to [[S_FLOAT_TY]]*
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[START:%.+]] = ptrtoint [[S_FLOAT_TY]]* [[ORIG_START]] to i64
// CHECK: [[LOW_BOUND:%.+]] = ptrtoint [[S_FLOAT_TY]]* [[LOW]] to i64
// CHECK: [[OFFSET_BYTES:%.+]] = sub i64 [[START]], [[LOW_BOUND]]
// CHECK: [[OFFSET:%.+]] = sdiv exact i64 [[OFFSET_BYTES]], ptrtoint ([[S_FLOAT_TY]]* getelementptr ([[S_FLOAT_TY]], [[S_FLOAT_TY]]* null, i32 1) to i64)
Fix PR35542: Correct adjusting of private reduction variable The adjustment is calculated with CreatePtrDiff() which returns the difference in (base) elements. This is passed to CreateGEP() so make sure that the GEP base has the correct pointer type: It needs to be a pointer to the base type, not a pointer to a constant sized array. Differential Revision: https://reviews.llvm.org/D40911 llvm-svn: 319931
2017-12-07 03:15:28 +08:00
// CHECK: [[VVAR2_PRIV_PTR:%.+]] = bitcast [5 x [[S_FLOAT_TY]]]* [[VVAR2_PRIV]] to [[S_FLOAT_TY]]*
// CHECK: [[VVAR2_PRIV:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[VVAR2_PRIV_PTR]], i64 [[OFFSET]]
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: ret void
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: define internal void [[MAIN_MICROTASK5]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, [4 x [[S_FLOAT_TY]]]* dereferenceable(48) %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: [[VAR3_ORIG_ADDR:%.+]] = alloca [4 x [[S_FLOAT_TY]]]*,
// CHECK: [[VAR3_PRIV:%.+]] = alloca [2 x [[S_FLOAT_TY]]],
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// Reduction list for runtime.
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: [[RED_LIST:%.+]] = alloca [1 x i8*],
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_ADDR:%.+]],
[OPENMP]Simplify codegen for the outlined regions. Simplified codegen for the outlined regions, excluding duplication code for handling variables with the reference types. llvm-svn: 361529
2019-05-24 02:19:54 +08:00
// CHECK: [[VAR3_ORIG:%.+]] = load [4 x [[S_FLOAT_TY]]]*, [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR]],
// CHECK: store [4 x [[S_FLOAT_TY]]]* [[VAR3_ORIG]], [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR:%.+]],
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: [[VAR3_ORIG:%.+]] = load [4 x [[S_FLOAT_TY]]]*, [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR]],
// CHECK: store [4 x [[S_FLOAT_TY]]]* [[VAR3_ORIG]], [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR:%.+]],
// CHECK: [[VAR3_ORIG:%.+]] = load [4 x [[S_FLOAT_TY]]]*, [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR]],
// CHECK: [[LOW:%.+]] = getelementptr inbounds [4 x [[S_FLOAT_TY]]], [4 x [[S_FLOAT_TY]]]* [[VAR3_ORIG]], i64 0, i64 1
// CHECK: [[VAR3_ORIG:%.+]] = load [4 x [[S_FLOAT_TY]]]*, [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR]],
// CHECK: [[VAR3_ORIG:%.+]] = load [4 x [[S_FLOAT_TY]]]*, [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR]],
// CHECK: [[ORIG_START:%.+]] = bitcast [4 x [[S_FLOAT_TY]]]* [[VAR3_ORIG]] to [[S_FLOAT_TY]]*
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[START:%.+]] = ptrtoint [[S_FLOAT_TY]]* [[ORIG_START]] to i64
// CHECK: [[LOW_BOUND:%.+]] = ptrtoint [[S_FLOAT_TY]]* [[LOW]] to i64
// CHECK: [[OFFSET_BYTES:%.+]] = sub i64 [[START]], [[LOW_BOUND]]
// CHECK: [[OFFSET:%.+]] = sdiv exact i64 [[OFFSET_BYTES]], ptrtoint ([[S_FLOAT_TY]]* getelementptr ([[S_FLOAT_TY]], [[S_FLOAT_TY]]* null, i32 1) to i64)
Fix PR35542: Correct adjusting of private reduction variable The adjustment is calculated with CreatePtrDiff() which returns the difference in (base) elements. This is passed to CreateGEP() so make sure that the GEP base has the correct pointer type: It needs to be a pointer to the base type, not a pointer to a constant sized array. Differential Revision: https://reviews.llvm.org/D40911 llvm-svn: 319931
2017-12-07 03:15:28 +08:00
// CHECK: [[VAR3_PRIV_PTR:%.+]] = bitcast [2 x [[S_FLOAT_TY]]]* [[VAR3_PRIV]] to [[S_FLOAT_TY]]*
// CHECK: [[PSEUDO_VAR3_PRIV:%.+]] = getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* [[VAR3_PRIV_PTR]], i64 [[OFFSET]]
// CHECK: [[VAR3_PRIV:%.+]] = bitcast [[S_FLOAT_TY]]* [[PSEUDO_VAR3_PRIV]] to [4 x [[S_FLOAT_TY]]]*
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: store [4 x [[S_FLOAT_TY]]]* [[VAR3_PRIV]], [4 x [[S_FLOAT_TY]]]** %
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: ret void
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: define internal void [[MAIN_MICROTASK6]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, [4 x [[S_FLOAT_TY]]]* dereferenceable(48) %{{.+}})
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: [[VAR3_ORIG_ADDR:%.+]] = alloca [4 x [[S_FLOAT_TY]]]*,
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// Reduction list for runtime.
// CHECK: [[RED_LIST:%.+]] = alloca [1 x i8*],
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_ADDR:%.+]],
[OPENMP]Simplify codegen for the outlined regions. Simplified codegen for the outlined regions, excluding duplication code for handling variables with the reference types. llvm-svn: 361529
2019-05-24 02:19:54 +08:00
// CHECK: [[VAR3_ORIG:%.+]] = load [4 x [[S_FLOAT_TY]]]*, [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR]],
// CHECK: store [4 x [[S_FLOAT_TY]]]* [[VAR3_ORIG]], [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR:%.+]],
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: [[VAR3_ORIG:%.+]] = load [4 x [[S_FLOAT_TY]]]*, [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR]],
// CHECK: store [4 x [[S_FLOAT_TY]]]* [[VAR3_ORIG]], [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR:%.+]],
// CHECK: [[VAR3_ORIG:%.+]] = load [4 x [[S_FLOAT_TY]]]*, [4 x [[S_FLOAT_TY]]]** [[VAR3_ORIG_ADDR]],
[OPENMP] Sync __kmpc_alloc/_kmpc_free function with the runtime. Functions __kmpc_alloc/__kmpc_free are updated with the new interfaces. Patch synchronizes the compiler with the runtime. llvm-svn: 357933
2019-04-09 03:06:42 +08:00
// CHECK: [[VAR3_VOID_PTR:%.+]] = call i8* @__kmpc_alloc(i32 [[GTID:%.+]], i64 48, i8* inttoptr (i64 6 to i8*))
[OPENMP]Use copy constructors instead of assignment operators in declare reduction initializers. Better to use copy constructor at the initialization of the declare reduction construct rather than assignment operator.
2019-11-13 00:19:26 +08:00
// CHECK: [[VAR3_PRIV:%.+]] = bitcast i8* [[VAR3_VOID_PTR]] to [4 x [[S_FLOAT_TY]]]*
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: getelementptr inbounds [4 x [[S_FLOAT_TY]]], [4 x [[S_FLOAT_TY]]]* [[VAR3_PRIV]], i32 0, i32 0
// CHECK: bitcast [4 x [[S_FLOAT_TY]]]* [[VAR3_ORIG]] to [[S_FLOAT_TY]]*
// CHECK: getelementptr [[S_FLOAT_TY]], [[S_FLOAT_TY]]* %{{.+}}, i64 4
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: store [4 x [[S_FLOAT_TY]]]* [[VAR3_PRIV]], [4 x [[S_FLOAT_TY]]]** %
[OPENMP] Sync __kmpc_alloc/_kmpc_free function with the runtime. Functions __kmpc_alloc/__kmpc_free are updated with the new interfaces. Patch synchronizes the compiler with the runtime. llvm-svn: 357933
2019-04-09 03:06:42 +08:00
// CHECK: call void @__kmpc_free(i32 [[GTID]], i8* [[VAR3_VOID_PTR]], i8* inttoptr (i64 6 to i8*))
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: ret void
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: define {{.*}} i{{[0-9]+}} [[TMAIN_INT_42]]()
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[TEST:%.+]] = alloca [[S_INT_TY]],
[OPENMP]Use copy constructors instead of assignment operators in declare reduction initializers. Better to use copy constructor at the initialization of the declare reduction construct rather than assignment operator.
2019-11-13 00:19:26 +08:00
// CHECK: call {{.*}} [[S_INT_TY_CONSTR]]([[S_INT_TY]]* [[TEST]])
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 6, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, i32*, [[S_INT_TY]]*, [[S_INT_TY]]*, i32*, [2 x i32]*, [2 x [[S_INT_TY]]]*)* [[TMAIN_MICROTASK:@.+]] to void
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// Not interested in this one:
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 4,
// CHECK: call void (%{{.+}}*, i{{[0-9]+}}, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)*, ...) @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{[0-9]+}} 5, void (i{{[0-9]+}}*, i{{[0-9]+}}*, ...)* bitcast (void (i{{[0-9]+}}*, i{{[0-9]+}}*, [42 x [[S_INT_TY]]]*, [2 x i32]*, i32*, [2 x [[S_INT_TY]]]*, [[S_INT_TY]]*)* [[TMAIN_MICROTASK2:@.+]] to void
[OPENMP]Use copy constructors instead of assignment operators in declare reduction initializers. Better to use copy constructor at the initialization of the declare reduction construct rather than assignment operator.
2019-11-13 00:19:26 +08:00
// CHECK: call {{.*}} [[S_INT_TY_DESTR]]([[S_INT_TY]]*
// CHECK: call {{.*}} [[S_INT_TY_DESTR]]([[S_INT_TY]]*
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: ret
//
// CHECK: define internal void [[TMAIN_MICROTASK]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, i32* dereferenceable(4) %{{.+}}, [[S_INT_TY]]* dereferenceable(12) %{{.+}}, [[S_INT_TY]]* dereferenceable(12) %{{.+}}, i32* dereferenceable(4) %{{.+}}, [2 x i32]* dereferenceable(8) %{{.+}}, [2 x [[S_INT_TY]]]* dereferenceable(24) %{{.+}})
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
// CHECK: alloca i{{[0-9]+}},
[OPENMP] Fix PR35486: crash when collapsing loops with dependent iteration spaces. Though it is incorrect from point of view of OpenMP standard to have dependent iteration space in OpenMP loops, compiler should not crash. Patch fixes this problem. llvm-svn: 319700
2017-12-05 05:30:42 +08:00
// CHECK: alloca i{{[0-9]+}},
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[T_VAR_PRIV:%.+]] = alloca i{{[0-9]+}},
// CHECK: [[VAR_PRIV:%.+]] = alloca [[S_INT_TY]],
// CHECK: [[VAR1_PRIV:%.+]] = alloca [[S_INT_TY]],
// CHECK: [[T_VAR1_PRIV:%.+]] = alloca i{{[0-9]+}},
// Reduction list for runtime.
// CHECK: [[RED_LIST:%.+]] = alloca [4 x i8*],
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_ADDR:%.+]],
// CHECK: [[T_VAR_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** %
// CHECK: [[VAR1_REF:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** %
// CHECK: [[T_VAR1_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** %
// For + reduction operation initial value of private variable is 0.
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_INIT6:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// For & reduction operation initial value of private variable is ones in all bits.
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_INIT2:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// For && reduction operation initial value of private variable is 1.0.
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_INIT7:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// For min reduction operation initial value of private variable is largest repesentable value.
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_INIT8:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: [[GTID_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[GTID_ADDR_ADDR]]
// CHECK: [[GTID:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[GTID_REF]]
// CHECK: call void @__kmpc_for_static_init_4(
// Skip checks for internal operations.
// CHECK: call void @__kmpc_for_static_fini(
// void *RedList[<n>] = {<ReductionVars>[0], ..., <ReductionVars>[<n>-1]};
// CHECK: [[T_VAR_PRIV_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 0
// CHECK: [[BITCAST:%.+]] = bitcast i{{[0-9]+}}* [[T_VAR_PRIV]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[T_VAR_PRIV_REF]],
// CHECK: [[VAR_PRIV_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 1
// CHECK: [[BITCAST:%.+]] = bitcast [[S_INT_TY]]* [[VAR_PRIV]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[VAR_PRIV_REF]],
// CHECK: [[VAR1_PRIV_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 2
// CHECK: [[BITCAST:%.+]] = bitcast [[S_INT_TY]]* [[VAR1_PRIV]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[VAR1_PRIV_REF]],
// CHECK: [[T_VAR1_PRIV_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST]], i64 0, i64 3
// CHECK: [[BITCAST:%.+]] = bitcast i{{[0-9]+}}* [[T_VAR1_PRIV]] to i8*
// CHECK: store i8* [[BITCAST]], i8** [[T_VAR1_PRIV_REF]],
// res = __kmpc_reduce_nowait(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>);
// CHECK: [[BITCAST:%.+]] = bitcast [4 x i8*]* [[RED_LIST]] to i8*
// CHECK: [[RES:%.+]] = call i32 @__kmpc_reduce_nowait(%{{.+}}* [[REDUCTION_LOC]], i32 [[GTID]], i32 4, i64 32, i8* [[BITCAST]], void (i8*, i8*)* [[REDUCTION_FUNC:@.+]], [8 x i32]* [[REDUCTION_LOCK]])
// switch(res)
// CHECK: switch i32 [[RES]], label %[[RED_DONE:.+]] [
// CHECK: i32 1, label %[[CASE1:.+]]
// CHECK: i32 2, label %[[CASE2:.+]]
// CHECK: ]
// case 1:
// t_var += t_var_reduction;
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB6:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// var = var.operator &(var_reduction);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// var1 = var1.operator &&(var1_reduction);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB7:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// t_var1 = min(t_var1, t_var1_reduction);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB8:@.+]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// __kmpc_end_reduce_nowait(<loc>, <gtid>, &<lock>);
// CHECK: call void @__kmpc_end_reduce_nowait(%{{.+}}* [[REDUCTION_LOC]], i32 [[GTID]], [8 x i32]* [[REDUCTION_LOCK]])
// break;
// CHECK: br label %[[RED_DONE]]
// case 2:
// t_var += t_var_reduction;
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB6]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// var = var.operator &(var_reduction);
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// var1 = var1.operator &&(var1_reduction);
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB7]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// t_var1 = min(t_var1, t_var1_reduction);
// CHECK: call void @__kmpc_critical(
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB8]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: call void @__kmpc_end_critical(
// break;
// CHECK: br label %[[RED_DONE]]
// CHECK: [[RED_DONE]]
// CHECK-DAG: call {{.*}} [[S_INT_TY_DESTR]]([[S_INT_TY]]* [[VAR_PRIV]])
// CHECK-DAG: call {{.*}} [[S_INT_TY_DESTR]]([[S_INT_TY]]*
// CHECK: ret void
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[RED_COMB6]](i32* noalias %0, i32* noalias %1)
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: add nsw i32 1513, %
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[RED_INIT6]](i32* noalias %0, i32* noalias %1)
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: store i32 321, i32* %
// CHECK: define internal void [[RED_COMB7]](
// CHECK: mul nsw i32 17, %
// CHECK: define internal void [[RED_INIT7]](
// CHECK: call void @_Z5init2R6BaseS1RKS_(
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[RED_COMB8]](i32* noalias %0, i32* noalias %1)
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: sub nsw i32 47, %
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[RED_INIT8]](i32* noalias %0, i32* noalias %1)
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: sdiv i32 432, %
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// void reduce_func(void *lhs[<n>], void *rhs[<n>]) {
// *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]);
// ...
// *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1],
// *(Type<n>-1*)rhs[<n>-1]);
// }
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[REDUCTION_FUNC]](i8* %0, i8* %1)
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// t_var_lhs = (i{{[0-9]+}}*)lhs[0];
// CHECK: [[T_VAR_RHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_RHS:%.+]], i64 0, i64 0
// CHECK: [[T_VAR_RHS_VOID:%.+]] = load i8*, i8** [[T_VAR_RHS_REF]],
// CHECK: [[T_VAR_RHS:%.+]] = bitcast i8* [[T_VAR_RHS_VOID]] to i{{[0-9]+}}*
// t_var_rhs = (i{{[0-9]+}}*)rhs[0];
// CHECK: [[T_VAR_LHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS:%.+]], i64 0, i64 0
// CHECK: [[T_VAR_LHS_VOID:%.+]] = load i8*, i8** [[T_VAR_LHS_REF]],
// CHECK: [[T_VAR_LHS:%.+]] = bitcast i8* [[T_VAR_LHS_VOID]] to i{{[0-9]+}}*
// var_lhs = (S<i{{[0-9]+}}>*)lhs[1];
// CHECK: [[VAR_RHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_RHS]], i64 0, i64 1
// CHECK: [[VAR_RHS_VOID:%.+]] = load i8*, i8** [[VAR_RHS_REF]],
// CHECK: [[VAR_RHS:%.+]] = bitcast i8* [[VAR_RHS_VOID]] to [[S_INT_TY]]*
// var_rhs = (S<i{{[0-9]+}}>*)rhs[1];
// CHECK: [[VAR_LHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS]], i64 0, i64 1
// CHECK: [[VAR_LHS_VOID:%.+]] = load i8*, i8** [[VAR_LHS_REF]],
// CHECK: [[VAR_LHS:%.+]] = bitcast i8* [[VAR_LHS_VOID]] to [[S_INT_TY]]*
// var1_lhs = (S<i{{[0-9]+}}>*)lhs[2];
// CHECK: [[VAR1_RHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_RHS]], i64 0, i64 2
// CHECK: [[VAR1_RHS_VOID:%.+]] = load i8*, i8** [[VAR1_RHS_REF]],
// CHECK: [[VAR1_RHS:%.+]] = bitcast i8* [[VAR1_RHS_VOID]] to [[S_INT_TY]]*
// var1_rhs = (S<i{{[0-9]+}}>*)rhs[2];
// CHECK: [[VAR1_LHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS]], i64 0, i64 2
// CHECK: [[VAR1_LHS_VOID:%.+]] = load i8*, i8** [[VAR1_LHS_REF]],
// CHECK: [[VAR1_LHS:%.+]] = bitcast i8* [[VAR1_LHS_VOID]] to [[S_INT_TY]]*
// t_var1_lhs = (i{{[0-9]+}}*)lhs[3];
// CHECK: [[T_VAR1_RHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_RHS]], i64 0, i64 3
// CHECK: [[T_VAR1_RHS_VOID:%.+]] = load i8*, i8** [[T_VAR1_RHS_REF]],
// CHECK: [[T_VAR1_RHS:%.+]] = bitcast i8* [[T_VAR1_RHS_VOID]] to i{{[0-9]+}}*
// t_var1_rhs = (i{{[0-9]+}}*)rhs[3];
// CHECK: [[T_VAR1_LHS_REF:%.+]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[RED_LIST_LHS]], i64 0, i64 3
// CHECK: [[T_VAR1_LHS_VOID:%.+]] = load i8*, i8** [[T_VAR1_LHS_REF]],
// CHECK: [[T_VAR1_LHS:%.+]] = bitcast i8* [[T_VAR1_LHS_VOID]] to i{{[0-9]+}}*
// t_var_lhs += t_var_rhs;
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB6]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// var_lhs = var_lhs.operator &(var_rhs);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB2]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// var1_lhs = var1_lhs.operator &&(var1_rhs);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB7]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// t_var1_lhs = min(t_var1_lhs, t_var1_rhs);
[OPENMP][NVPTX]Mark more functions as always_inline for better performance. Internally generated functions must be marked as always_inlines in most cases. Patch marks some extra reduction function + outlined parallel functions as always_inline for better performance, but only if the optimization is requested. llvm-svn: 361269
2019-05-21 23:11:58 +08:00
// CHECK: call void [[RED_COMB8]](
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
// CHECK: ret void
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: define internal void [[TMAIN_MICROTASK2]](i{{[0-9]+}}* noalias [[GTID_ADDR:%.+]], i{{[0-9]+}}* noalias %{{.+}}, [42 x [[S_INT_TY]]]* dereferenceable(504) %{{.*}}, [2 x i32]* dereferenceable(8) %{{.*}}, i32* dereferenceable(4) %{{.*}}, [2 x [[S_INT_TY]]]* dereferenceable(24) %{{.*}}, [[S_INT_TY]]* dereferenceable(12) %{{.*}})
// CHECK: [[ARR_ORIG_ADDR:%.+]] = alloca [42 x [[S_INT_TY]]]*,
// CHECK: [[ARR_PRIV:%.+]] = alloca [40 x [[S_INT_TY]]],
// Reduction list for runtime.
// CHECK: [[RED_LIST:%.+]] = alloca [1 x i8*],
// CHECK: store i{{[0-9]+}}* [[GTID_ADDR]], i{{[0-9]+}}** [[GTID_ADDR_ADDR:%.+]],
// CHECK: [[ARR_ORIG:%.+]] = load [42 x [[S_INT_TY]]]*, [42 x [[S_INT_TY]]]** [[ARR_ORIG_ADDR]],
// CHECK: [[LOW:%.+]] = getelementptr inbounds [42 x [[S_INT_TY]]], [42 x [[S_INT_TY]]]* [[ARR_ORIG]], i64 0, i64 1
// CHECK: [[ORIG_START:%.+]] = bitcast [42 x [[S_INT_TY]]]* [[ARR_ORIG]] to [[S_INT_TY]]*
// CHECK: [[START:%.+]] = ptrtoint [[S_INT_TY]]* [[ORIG_START]] to i64
// CHECK: [[LOW_BOUND:%.+]] = ptrtoint [[S_INT_TY]]* [[LOW]] to i64
// CHECK: [[OFFSET_BYTES:%.+]] = sub i64 [[START]], [[LOW_BOUND]]
// CHECK: [[OFFSET:%.+]] = sdiv exact i64 [[OFFSET_BYTES]], ptrtoint ([[S_INT_TY]]* getelementptr ([[S_INT_TY]], [[S_INT_TY]]* null, i32 1) to i64)
Fix PR35542: Correct adjusting of private reduction variable The adjustment is calculated with CreatePtrDiff() which returns the difference in (base) elements. This is passed to CreateGEP() so make sure that the GEP base has the correct pointer type: It needs to be a pointer to the base type, not a pointer to a constant sized array. Differential Revision: https://reviews.llvm.org/D40911 llvm-svn: 319931
2017-12-07 03:15:28 +08:00
// CHECK: [[ARR_PRIV_PTR:%.+]] = bitcast [40 x [[S_INT_TY]]]* [[ARR_PRIV]] to [[S_INT_TY]]*
// CHECK: [[PSEUDO_ARR_PRIV:%.+]] = getelementptr [[S_INT_TY]], [[S_INT_TY]]* [[ARR_PRIV_PTR]], i64 [[OFFSET]]
// CHECK: [[ARR_PRIV:%.+]] = bitcast [[S_INT_TY]]* [[PSEUDO_ARR_PRIV]] to [42 x [[S_INT_TY]]]*
[OpenMP] Avoid VLAs for some reductions on array sections In some cases the compiler can deduce the length of an array section as constants. With this information, VLAs can be avoided in place of a constant sized array or even a scalar value if the length is 1. Example: int a[4], b[2]; pragma omp parallel reduction(+: a[1:2], b[1:1]) { } For chained array sections, this optimization is restricted to cases where all array sections except the last have a constant length 1. This trivially guarantees that there are no holes in the memory region that needs to be privatized. Example: int c[3][4]; pragma omp parallel reduction(+: c[1:1][1:2]) { } This relands commit r316229 that I reverted in r316235 because it failed on some bots. During investigation I found that this was because Clang and GCC evaluate the two arguments to emplace_back() in ReductionCodeGen::emitSharedLValue() in a different order, hence leading to a different order of generated instructions in the final LLVM IR. Fix this by passing in the arguments from temporary variables that are evaluated in a defined order. Differential Revision: https://reviews.llvm.org/D39136 llvm-svn: 316362
2017-10-24 03:01:35 +08:00
// CHECK: ret void
[OPENMP 4.0] Use 'declare reduction' constructs in 'reduction' clauses. OpenMP 4.0 allows to define custom reduction operations using '#pragma omp declare reduction' construct. Patch allows to use this custom defined reduction operations in 'reduction' clauses. llvm-svn: 263701
2016-03-17 18:19:46 +08:00
#endif