timshen updated this revision to Diff 139037.
timshen added a comment.
Herald added a subscriber: christof.
Rebase.
https://reviews.llvm.org/D41376
Files:
libcxx/include/__config
libcxx/include/experimental/__config
libcxx/include/experimental/simd
libcxx/include/utility
libcxx/test/std/experimental/simd/simd.abi/vector_extension.pass.cpp
libcxx/test/std/experimental/simd/simd.access/default.pass.cpp
libcxx/test/std/experimental/simd/simd.casts/simd_cast.pass.cpp
libcxx/test/std/experimental/simd/simd.cons/broadcast.pass.cpp
libcxx/test/std/experimental/simd/simd.cons/default.pass.cpp
libcxx/test/std/experimental/simd/simd.cons/geneartor.pass.cpp
libcxx/test/std/experimental/simd/simd.cons/load.pass.cpp
libcxx/test/std/experimental/simd/simd.mem/load.pass.cpp
libcxx/test/std/experimental/simd/simd.mem/store.pass.cpp
Index: libcxx/test/std/experimental/simd/simd.mem/store.pass.cpp
===================================================================
--- /dev/null
+++ libcxx/test/std/experimental/simd/simd.mem/store.pass.cpp
@@ -0,0 +1,92 @@
+//===----------------------------------------------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// // stores [simd.store]
+// template <class U, class Flags> void copy_to(U* mem, Flags f) const;
+
+#include <experimental/simd>
+#include <cstdint>
+
+#include "test_macros.h"
+
+using namespace std::experimental::parallelism_v2;
+
+void test_store() {
+ fixed_size_simd<int32_t, 4> a([](int i) { return 4 - i; });
+ {
+ alignas(32) int32_t buffer[4] = {0};
+ a.copy_to(buffer, element_aligned_tag());
+ assert(buffer[0] == 4);
+ assert(buffer[1] == 3);
+ assert(buffer[2] == 2);
+ assert(buffer[3] == 1);
+ }
+ {
+ alignas(32) int32_t buffer[4] = {0};
+ a.copy_to(buffer, vector_aligned_tag());
+ assert(buffer[0] == 4);
+ assert(buffer[1] == 3);
+ assert(buffer[2] == 2);
+ assert(buffer[3] == 1);
+ }
+ {
+ alignas(32) int32_t buffer[4] = {0};
+ a.copy_to(buffer, overaligned_tag<32>());
+ assert(buffer[0] == 4);
+ assert(buffer[1] == 3);
+ assert(buffer[2] == 2);
+ assert(buffer[3] == 1);
+ }
+
+#if TEST_STD_VER > 14
+ {
+ alignas(32) int32_t buffer[4] = {0};
+ a.copy_to(buffer, element_aligned);
+ assert(buffer[0] == 4);
+ assert(buffer[1] == 3);
+ assert(buffer[2] == 2);
+ assert(buffer[3] == 1);
+ }
+ {
+ alignas(32) int32_t buffer[4] = {0};
+ a.copy_to(buffer, vector_aligned);
+ assert(buffer[0] == 4);
+ assert(buffer[1] == 3);
+ assert(buffer[2] == 2);
+ assert(buffer[3] == 1);
+ }
+ {
+ alignas(32) int32_t buffer[4] = {0};
+ a.copy_to(buffer, overaligned<32>);
+ assert(buffer[0] == 4);
+ assert(buffer[1] == 3);
+ assert(buffer[2] == 2);
+ assert(buffer[3] == 1);
+ }
+#endif
+}
+
+void test_converting_store() {
+ float buffer[4] = {0.};
+ fixed_size_simd<int32_t, 4> a([](int i) { return 1 << i; });
+ a.copy_to(buffer, element_aligned_tag());
+ assert(buffer[0] == 1.);
+ assert(buffer[1] == 2.);
+ assert(buffer[2] == 4.);
+ assert(buffer[3] == 8.);
+}
+
+int main() {
+ test_store();
+ test_converting_store();
+}
Index: libcxx/test/std/experimental/simd/simd.mem/load.pass.cpp
===================================================================
--- /dev/null
+++ libcxx/test/std/experimental/simd/simd.mem/load.pass.cpp
@@ -0,0 +1,118 @@
+//===----------------------------------------------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// loads [simd.load]
+// template <class U, class Flags> void copy_from(const U* mem, Flags f);
+
+#include <experimental/simd>
+#include <cstdint>
+
+#include "test_macros.h"
+
+using namespace std::experimental::parallelism_v2;
+
+template <class T, class... Args>
+auto not_supported_load(Args&&... args) -> decltype(
+ std::declval<native_simd<T>>().copy_from(std::forward<Args>(args)...),
+ void()) = delete;
+
+template <class T>
+void not_supported_load(...) {}
+
+template <class T, class... Args>
+auto supported_load(Args&&... args) -> decltype(
+ std::declval<native_simd<T>>().copy_from(std::forward<Args>(args)...),
+ void()) {}
+
+template <class T>
+void supported_load(...) = delete;
+
+void compile_load() {
+ supported_load<int>((int*)nullptr, element_aligned_tag());
+ supported_load<uint32_t>((int*)nullptr, element_aligned_tag());
+ supported_load<double>((float*)nullptr, element_aligned_tag());
+ supported_load<uint16_t>((unsigned int*)nullptr, element_aligned_tag());
+ supported_load<uint32_t>((float*)nullptr, element_aligned_tag());
+
+ not_supported_load<int>((int*)nullptr, int());
+}
+
+void test_load() {
+ alignas(32) int32_t buffer[] = {4, 3, 2, 1};
+ {
+ fixed_size_simd<int32_t, 4> a;
+ a.copy_from(buffer, element_aligned_tag());
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+ {
+ fixed_size_simd<int32_t, 4> a;
+ a.copy_from(buffer, vector_aligned_tag());
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+ {
+ fixed_size_simd<int32_t, 4> a;
+ a.copy_from(buffer, overaligned_tag<32>());
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+
+#if TEST_STD_VER > 14
+ {
+ fixed_size_simd<int32_t, 4> a;
+ a.copy_from(buffer, element_aligned);
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+ {
+ fixed_size_simd<int32_t, 4> a;
+ a.copy_from(buffer, vector_aligned);
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+ {
+ fixed_size_simd<int32_t, 4> a;
+ a.copy_from(buffer, overaligned<32>);
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+#endif
+}
+
+void test_converting_load() {
+ float buffer[] = {1., 2., 4., 8.};
+ fixed_size_simd<int32_t, 4> a;
+ a.copy_from(buffer, element_aligned_tag());
+ assert(a[0] == 1);
+ assert(a[1] == 2);
+ assert(a[2] == 4);
+ assert(a[3] == 8);
+}
+
+int main() {
+ test_load();
+ test_converting_load();
+}
Index: libcxx/test/std/experimental/simd/simd.cons/load.pass.cpp
===================================================================
--- /dev/null
+++ libcxx/test/std/experimental/simd/simd.cons/load.pass.cpp
@@ -0,0 +1,110 @@
+//===----------------------------------------------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.class]
+// template <class U, class Flags> simd(const U* mem, Flags f);
+
+#include <cstdint>
+#include <experimental/simd>
+
+#include "test_macros.h"
+
+using namespace std::experimental::parallelism_v2;
+
+template <class T, class... Args>
+auto not_supported_native_simd_ctor(Args&&... args)
+ -> decltype(native_simd<T>(std::forward<Args>(args)...), void()) = delete;
+
+template <class T>
+void not_supported_native_simd_ctor(...) {}
+
+template <class T, class... Args>
+auto supported_native_simd_ctor(Args&&... args)
+ -> decltype(native_simd<T>(std::forward<Args>(args)...), void()) {}
+
+template <class T>
+void supported_native_simd_ctor(...) = delete;
+
+void compile_load_ctor() {
+ supported_native_simd_ctor<int>((int*)nullptr, element_aligned_tag());
+ supported_native_simd_ctor<uint32_t>((int*)nullptr, element_aligned_tag());
+ supported_native_simd_ctor<double>((float*)nullptr, element_aligned_tag());
+ supported_native_simd_ctor<uint16_t>((unsigned int*)nullptr,
+ element_aligned_tag());
+ supported_native_simd_ctor<uint32_t>((float*)nullptr, element_aligned_tag());
+
+ not_supported_native_simd_ctor<int>((int*)nullptr, int());
+}
+
+void test_load_ctor() {
+ alignas(32) int32_t buffer[] = {4, 3, 2, 1};
+ {
+ fixed_size_simd<int32_t, 4> a(buffer, element_aligned_tag());
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+ {
+ fixed_size_simd<int32_t, 4> a(buffer, vector_aligned_tag());
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+ {
+ fixed_size_simd<int32_t, 4> a(buffer, overaligned_tag<32>());
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+
+#if TEST_STD_VER > 14
+ {
+ fixed_size_simd<int32_t, 4> a(buffer, element_aligned);
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+ {
+ fixed_size_simd<int32_t, 4> a(buffer, vector_aligned);
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+ {
+ fixed_size_simd<int32_t, 4> a(buffer, overaligned<32>);
+ assert(a[0] == 4);
+ assert(a[1] == 3);
+ assert(a[2] == 2);
+ assert(a[3] == 1);
+ }
+#endif
+}
+
+void test_converting_load_ctor() {
+ float buffer[] = {1., 2., 4., 8.};
+ fixed_size_simd<int32_t, 4> a(buffer, element_aligned_tag());
+ assert(a[0] == 1);
+ assert(a[1] == 2);
+ assert(a[2] == 4);
+ assert(a[3] == 8);
+}
+
+int main() {
+ test_load_ctor();
+ test_converting_load_ctor();
+}
Index: libcxx/test/std/experimental/simd/simd.cons/geneartor.pass.cpp
===================================================================
--- libcxx/test/std/experimental/simd/simd.cons/geneartor.pass.cpp
+++ libcxx/test/std/experimental/simd/simd.cons/geneartor.pass.cpp
@@ -14,30 +14,69 @@
// [simd.class]
// template <class G> explicit simd(G&& gen);
-#include <cstdint>
#include <experimental/simd>
+#include <cstdint>
using namespace std::experimental::parallelism_v2;
template <class T, class... Args>
-auto not_supported_native_simd_ctor(Args&&... args)
- -> decltype(native_simd<T>(std::forward<Args>(args)...), void()) = delete;
+auto not_supported_simd128_ctor(Args&&... args)
+ -> decltype(fixed_size_simd<T, 16 / sizeof(T)>(std::forward<Args>(args)...),
+ void()) = delete;
template <class T>
-void not_supported_native_simd_ctor(...) {}
+void not_supported_simd128_ctor(...) {}
template <class T, class... Args>
-auto supported_native_simd_ctor(Args&&... args)
- -> decltype(native_simd<T>(std::forward<Args>(args)...), void()) {}
+auto supported_simd128_ctor(Args&&... args)
+ -> decltype(fixed_size_simd<T, 16 / sizeof(T)>(std::forward<Args>(args)...),
+ void()) {}
template <class T>
-void supported_native_simd_ctor(...) = delete;
+void supported_simd128_ctor(...) = delete;
+
+struct identity {
+ template <size_t value>
+ int operator()(std::integral_constant<size_t, value>) const {
+ return value;
+ }
+};
void compile_generator() {
- supported_native_simd_ctor<int>([](int i) { return i; });
- not_supported_native_simd_ctor<int>([](int i) { return float(i); });
- not_supported_native_simd_ctor<int>([](intptr_t i) { return (int*)(i); });
- not_supported_native_simd_ctor<int>([](int* i) { return i; });
+ supported_simd128_ctor<int>(identity());
+ not_supported_simd128_ctor<int>([](int i) { return float(i); });
+ not_supported_simd128_ctor<int>([](intptr_t i) { return (int*)(i); });
+ not_supported_simd128_ctor<int>([](int* i) { return i; });
+}
+
+struct limited_identity {
+ template <size_t value>
+ typename std::conditional<value <= 2, int32_t, int64_t>::type
+ operator()(std::integral_constant<size_t, value>) const {
+ return value;
+ }
+};
+
+void compile_limited_identity() {
+ supported_simd128_ctor<int64_t>(limited_identity());
+ not_supported_simd128_ctor<int32_t>(limited_identity());
+}
+
+void test_generator() {
+ {
+ fixed_size_simd<int32_t, 4> a([](int i) { return i; });
+ assert(a[0] == 0);
+ assert(a[1] == 1);
+ assert(a[2] == 2);
+ assert(a[3] == 3);
+ }
+ {
+ fixed_size_simd<int32_t, 4> a([](int i) { return 2 * i - 1; });
+ assert(a[0] == -1);
+ assert(a[1] == 1);
+ assert(a[2] == 3);
+ assert(a[3] == 5);
+ }
}
-int main() {}
+int main() { test_generator(); }
Index: libcxx/test/std/experimental/simd/simd.cons/default.pass.cpp
===================================================================
--- /dev/null
+++ libcxx/test/std/experimental/simd/simd.cons/default.pass.cpp
@@ -0,0 +1,22 @@
+//===----------------------------------------------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.class]
+// simd() = default;
+
+#include <cstdint>
+#include <experimental/simd>
+
+using namespace std::experimental::parallelism_v2;
+
+int main() { (void)native_simd<int32_t>(); }
Index: libcxx/test/std/experimental/simd/simd.cons/broadcast.pass.cpp
===================================================================
--- libcxx/test/std/experimental/simd/simd.cons/broadcast.pass.cpp
+++ libcxx/test/std/experimental/simd/simd.cons/broadcast.pass.cpp
@@ -52,4 +52,26 @@
not_supported_native_simd_ctor<int>(3.);
}
-int main() {}
+void compile_convertible() {
+ struct ConvertibleToInt {
+ operator int64_t() const;
+ };
+ supported_native_simd_ctor<int64_t>(ConvertibleToInt());
+
+ struct NotConvertibleToInt {};
+ not_supported_native_simd_ctor<int64_t>(NotConvertibleToInt());
+}
+
+void compile_unsigned() {
+ not_supported_native_simd_ctor<int>(3u);
+ supported_native_simd_ctor<uint16_t>(3u);
+}
+
+void test_broadcast() {
+ native_simd<int> a(3);
+ for (size_t i = 0; i < a.size(); i++) {
+ assert(a[i] == 3);
+ }
+}
+
+int main() { test_broadcast(); }
Index: libcxx/test/std/experimental/simd/simd.casts/simd_cast.pass.cpp
===================================================================
--- libcxx/test/std/experimental/simd/simd.casts/simd_cast.pass.cpp
+++ libcxx/test/std/experimental/simd/simd.casts/simd_cast.pass.cpp
@@ -13,6 +13,7 @@
//
// [simd.casts]
// template <class T, class U, class Abi> see below simd_cast(const simd<U, Abi>&);
+
#include <experimental/simd>
#include <cstdint>
Index: libcxx/test/std/experimental/simd/simd.access/default.pass.cpp
===================================================================
--- /dev/null
+++ libcxx/test/std/experimental/simd/simd.access/default.pass.cpp
@@ -0,0 +1,213 @@
+//===----------------------------------------------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// scalar access [simd.subscr]
+// reference operator[](size_t);
+// value_type operator[](size_t) const;
+
+#include <experimental/simd>
+#include <cassert>
+#include <cstdint>
+
+using namespace std::experimental::parallelism_v2;
+
+void test_access() {
+ {
+ native_simd<int> a(42), b(4);
+ static_assert(std::is_convertible<decltype(a[0]), int8_t>::value, "");
+
+ assert(a[0] == 42);
+ assert(!a[0] == !42);
+ assert(~a[0] == ~42);
+ assert(+a[0] == +42);
+ assert(-a[0] == -42);
+ assert(a[0] + b[0] == 42 + 4);
+ assert(a[0] - b[0] == 42 - 4);
+ assert(a[0] * b[0] == 42 * 4);
+ assert(a[0] / b[0] == 42 / 4);
+ assert(a[0] % b[0] == 42 % 4);
+ assert(a[0] << b[0] == (42 << 4));
+ assert(a[0] >> b[0] == (42 >> 4));
+ assert(a[0] < b[0] == false);
+ assert(a[0] <= b[0] == false);
+ assert(a[0] > b[0] == true);
+ assert(a[0] >= b[0] == true);
+ assert(a[0] == b[0] == false);
+ assert(a[0] != b[0] == true);
+ assert((a[0] & b[0]) == (42 & 4));
+ assert((a[0] | b[0]) == (42 | 4));
+ assert((a[0] ^ b[0]) == (42 ^ 4));
+ assert((a[0] && b[0]) == true);
+ assert((a[0] || b[0]) == true);
+
+ {
+ auto c = a;
+ ++c[0];
+ assert(c[0] == 42 + 1);
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ auto ret = c[0]++;
+ assert(ret == 42);
+ assert(c[0] == 42 + 1);
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ --c[0];
+ assert(c[0] == 42 - 1);
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ auto ret = c[0]--;
+ assert(ret == 42);
+ assert(c[0] == 42 - 1);
+ assert(c[1] == 42);
+ }
+
+ {
+ auto c = a;
+ c[0] += b[0];
+ assert(c[0] == 42 + 4);
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ c[0] -= b[0];
+ assert(c[0] == 42 - 4);
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ c[0] *= b[0];
+ assert(c[0] == 42 * 4);
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ c[0] /= b[0];
+ assert(c[0] == 42 / 4);
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ c[0] %= b[0];
+ assert(c[0] == 42 % 4);
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ c[0] >>= b[0];
+ assert(c[0] == (42 >> 4));
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ c[0] <<= b[0];
+ assert(c[0] == (42 << 4));
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ c[0] &= b[0];
+ assert(c[0] == (42 & 4));
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ c[0] |= b[0];
+ assert(c[0] == (42 | 4));
+ assert(c[1] == 42);
+ }
+ {
+ auto c = a;
+ c[0] ^= b[0];
+ assert(c[0] == (42 ^ 4));
+ assert(c[1] == 42);
+ }
+
+ {
+ auto c = a;
+ (void)(a[0] + (c[0] += a[0]));
+ }
+ {
+ auto c = a;
+ (void)(a[0] + (c[0] -= a[0]));
+ }
+ {
+ auto c = a;
+ (void)(a[0] + (c[0] *= a[0]));
+ }
+ {
+ auto c = a;
+ (void)(a[0] + (c[0] /= a[0]));
+ }
+ {
+ auto c = a;
+ (void)(a[0] + (c[0] %= a[0]));
+ }
+ {
+ auto c = a;
+ (void)(a[0] + (c[0] >>= a[0]));
+ }
+ {
+ auto c = a;
+ (void)(a[0] + (c[0] <<= a[0]));
+ }
+ {
+ auto c = a;
+ (void)(a[0] + (c[0] &= a[0]));
+ }
+ {
+ auto c = a;
+ (void)(a[0] + (c[0] |= a[0]));
+ }
+ {
+ auto c = a;
+ (void)(a[0] + (c[0] ^= a[0]));
+ }
+ }
+ {
+ const native_simd<int> a(42);
+ const native_simd<int> b(4);
+ static_assert(std::is_same<decltype(a[0]), int>::value, "");
+
+ assert(a[0] == 42);
+ assert(!a[0] == !42);
+ assert(~a[0] == ~42);
+ assert(+a[0] == +42);
+ assert(-a[0] == -42);
+ assert(a[0] + b[0] == 42 + 4);
+ assert(a[0] - b[0] == 42 - 4);
+ assert(a[0] * b[0] == 42 * 4);
+ assert(a[0] / b[0] == 42 / 4);
+ assert(a[0] % b[0] == 42 % 4);
+ assert(a[0] << b[0] == (42 << 4));
+ assert(a[0] >> b[0] == (42 >> 4));
+ assert(a[0] < b[0] == false);
+ assert(a[0] <= b[0] == false);
+ assert(a[0] > b[0] == true);
+ assert(a[0] >= b[0] == true);
+ assert(a[0] == b[0] == false);
+ assert(a[0] != b[0] == true);
+ assert((a[0] & b[0]) == (42 & 4));
+ assert((a[0] | b[0]) == (42 | 4));
+ assert((a[0] ^ b[0]) == (42 ^ 4));
+ assert((a[0] && b[0]) == true);
+ assert((a[0] || b[0]) == true);
+ }
+}
+
+int main() { test_access(); }
Index: libcxx/test/std/experimental/simd/simd.abi/vector_extension.pass.cpp
===================================================================
--- /dev/null
+++ libcxx/test/std/experimental/simd/simd.abi/vector_extension.pass.cpp
@@ -0,0 +1,59 @@
+//===----------------------------------------------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// UNSUPPORTED: c++98, c++03
+
+// <experimental/simd>
+//
+// [simd.abi]
+
+#include <experimental/simd>
+#include <cstdint>
+
+using namespace std::experimental::parallelism_v2;
+
+constexpr inline int reg_width() {
+#if defined(__AVX__)
+ return 32;
+#else
+ return 16;
+#endif
+}
+
+#ifndef _LIBCPP_HAS_NO_VECTOR_EXTENSION
+
+static_assert(sizeof(simd<char, __simd_abi<_StorageKind::_VecExt, 1>>) == 1,
+ "");
+static_assert(sizeof(simd<char, __simd_abi<_StorageKind::_VecExt, 2>>) == 2,
+ "");
+static_assert(sizeof(simd<char, __simd_abi<_StorageKind::_VecExt, 3>>) == 4,
+ "");
+static_assert(sizeof(simd<char, __simd_abi<_StorageKind::_VecExt, 12>>) == 16,
+ "");
+static_assert(sizeof(simd<int32_t, __simd_abi<_StorageKind::_VecExt, 3>>) == 16,
+ "");
+static_assert(sizeof(simd<int32_t, __simd_abi<_StorageKind::_VecExt, 5>>) == 32,
+ "");
+static_assert(
+ std::is_same<simd_abi::native<int8_t>,
+ __simd_abi<_StorageKind::_VecExt, reg_width()>>::value,
+ "");
+#else
+static_assert(
+ std::is_same<simd_abi::native<int8_t>,
+ __simd_abi<_StorageKind::_Array, reg_width()>>::value,
+ "");
+
+#endif
+
+static_assert(std::is_same<simd_abi::compatible<int8_t>,
+ __simd_abi<_StorageKind::_Array, 16>>::value,
+ "");
+
+int main() {}
Index: libcxx/include/utility
===================================================================
--- libcxx/include/utility
+++ libcxx/include/utility
@@ -833,7 +833,7 @@
#endif
-#if _LIBCPP_STD_VER > 11
+#if _LIBCPP_STD_VER >= 11
template<class _Tp, _Tp... _Ip>
struct _LIBCPP_TEMPLATE_VIS integer_sequence
@@ -886,7 +886,7 @@
template<class... _Tp>
using index_sequence_for = make_index_sequence<sizeof...(_Tp)>;
-#endif // _LIBCPP_STD_VER > 11
+#endif // _LIBCPP_STD_VER >= 11
#if _LIBCPP_STD_VER > 11
template<class _T1, class _T2 = _T1>
Index: libcxx/include/experimental/simd
===================================================================
--- libcxx/include/experimental/simd
+++ libcxx/include/experimental/simd
@@ -589,6 +589,7 @@
*/
#include <experimental/__config>
+#include <algorithm>
#include <array>
#include <cstddef>
#include <functional>
@@ -602,23 +603,235 @@
enum class _StorageKind {
_Scalar,
_Array,
+ _VecExt,
};
template <_StorageKind __kind, int _Np>
struct __simd_abi {};
template <class _Tp, class _Abi>
-struct __simd_storage_traits {};
+class __simd_storage {};
template <class _Tp, int __num_element>
-struct __simd_storage_traits<_Tp,
- __simd_abi<_StorageKind::_Array, __num_element>> {
- using type = std::array<_Tp, __num_element>;
+class __simd_storage<_Tp, __simd_abi<_StorageKind::_Array, __num_element>> {
+ std::array<_Tp, __num_element> __storage_;
+
+ template <class, class>
+ friend struct simd;
+
+ template <class, class>
+ friend struct simd_mask;
+
+public:
+ _Tp __get(size_t __index) const { return __storage_[__index]; };
+ void __set(size_t __index, _Tp __val) { __storage_[__index] = __val; }
};
template <class _Tp>
-struct __simd_storage_traits<_Tp, __simd_abi<_StorageKind::_Scalar, 1>> {
- using type = _Tp;
+class __simd_storage<_Tp, __simd_abi<_StorageKind::_Scalar, 1>> {
+ _Tp __storage_;
+
+ template <class, class>
+ friend struct simd;
+
+ template <class, class>
+ friend struct simd_mask;
+
+public:
+ _Tp __get(size_t __index) const { return (&__storage_)[__index]; };
+ void __set(size_t __index, _Tp __val) { (&__storage_)[__index] = __val; }
+};
+
+#ifndef _LIBCPP_HAS_NO_VECTOR_EXTENSION
+
+constexpr size_t __floor_pow_of_2(size_t __val) {
+ return ((__val - 1) & __val) == 0 ? __val
+ : __floor_pow_of_2((__val - 1) & __val);
+}
+
+constexpr size_t __ceil_pow_of_2(size_t __val) {
+ return __val == 1 ? 1 : __floor_pow_of_2(__val - 1) << 1;
+}
+
+template <class _Tp, size_t __bytes>
+struct __vec_ext_traits {
+#if !defined(_LIBCPP_COMPILER_CLANG)
+ typedef _Tp type __attribute__((vector_size(__ceil_pow_of_2(__bytes))));
+#endif
+};
+
+#if defined(_LIBCPP_COMPILER_CLANG)
+#define _SPECIALIZE_VEC_EXT(_TYPE, _NUM_ELEMENT) \
+ template <> \
+ struct __vec_ext_traits<_TYPE, sizeof(_TYPE) * _NUM_ELEMENT> { \
+ using type = \
+ _TYPE __attribute__((vector_size(sizeof(_TYPE) * _NUM_ELEMENT))); \
+ }
+
+#define _SPECIALIZE_VEC_EXT_32(_TYPE) \
+ _SPECIALIZE_VEC_EXT(_TYPE, 1); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 2); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 3); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 4); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 5); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 6); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 7); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 8); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 9); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 10); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 11); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 12); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 13); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 14); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 15); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 16); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 17); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 18); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 19); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 20); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 21); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 22); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 23); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 24); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 25); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 26); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 27); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 28); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 29); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 30); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 31); \
+ _SPECIALIZE_VEC_EXT(_TYPE, 32);
+
+_SPECIALIZE_VEC_EXT_32(char);
+_SPECIALIZE_VEC_EXT_32(char16_t);
+_SPECIALIZE_VEC_EXT_32(char32_t);
+_SPECIALIZE_VEC_EXT_32(wchar_t);
+_SPECIALIZE_VEC_EXT_32(signed char);
+_SPECIALIZE_VEC_EXT_32(signed short);
+_SPECIALIZE_VEC_EXT_32(signed int);
+_SPECIALIZE_VEC_EXT_32(signed long);
+_SPECIALIZE_VEC_EXT_32(signed long long);
+_SPECIALIZE_VEC_EXT_32(unsigned char);
+_SPECIALIZE_VEC_EXT_32(unsigned short);
+_SPECIALIZE_VEC_EXT_32(unsigned int);
+_SPECIALIZE_VEC_EXT_32(unsigned long);
+_SPECIALIZE_VEC_EXT_32(unsigned long long);
+_SPECIALIZE_VEC_EXT_32(float);
+_SPECIALIZE_VEC_EXT_32(double);
+_SPECIALIZE_VEC_EXT_32(long double);
+
+#undef _SPECIALIZE_VEC_EXT_32
+#undef _SPECIALIZE_VEC_EXT
+#endif
+
+template <class _Tp, int __num_element>
+class __simd_storage<_Tp, __simd_abi<_StorageKind::_VecExt, __num_element>> {
+ using _StorageType =
+ typename __vec_ext_traits<_Tp, sizeof(_Tp) * __num_element>::type;
+
+ _StorageType __storage_;
+
+ template <class, class>
+ friend struct simd;
+
+ template <class, class>
+ friend struct simd_mask;
+
+public:
+ _Tp __get(size_t __index) const { return __storage_[__index]; };
+ void __set(size_t __index, _Tp __val) { __storage_[__index] = __val; }
+};
+
+#endif // _LIBCPP_HAS_NO_VECTOR_EXTENSION
+
+template <class _Vp, class _Tp, class _Abi>
+class __simd_reference {
+ static_assert(std::is_same<_Vp, _Tp>::value, "");
+
+ template <class, class>
+ friend struct simd;
+
+ template <class, class>
+ friend struct simd_mask;
+
+ __simd_storage<_Tp, _Abi>* __ptr_;
+ size_t __index_;
+
+ __simd_reference(__simd_storage<_Tp, _Abi>* __ptr, size_t __index)
+ : __ptr_(__ptr), __index_(__index) {}
+
+ __simd_reference(const __simd_reference&) = default;
+
+public:
+ __simd_reference() = delete;
+ __simd_reference& operator=(const __simd_reference&) = delete;
+
+ operator _Vp() const { return __ptr_->__get(__index_); }
+
+ __simd_reference operator=(_Vp __value) && {
+ __ptr_->__set(__index_, __value);
+ return *this;
+ }
+
+ __simd_reference operator++() && {
+ return std::move(*this) = __ptr_->__get(__index_) + 1;
+ }
+
+ _Vp operator++(int) && {
+ auto __val = __ptr_->__get(__index_);
+ __ptr_->__set(__index_, __val + 1);
+ return __val;
+ }
+
+ __simd_reference operator--() && {
+ return std::move(*this) = __ptr_->__get(__index_) - 1;
+ }
+
+ _Vp operator--(int) && {
+ auto __val = __ptr_->__get(__index_);
+ __ptr_->__set(__index_, __val - 1);
+ return __val;
+ }
+
+ __simd_reference operator+=(_Vp __value) && {
+ return std::move(*this) = __ptr_->__get(__index_) + __value;
+ }
+
+ __simd_reference operator-=(_Vp __value) && {
+ return std::move(*this) = __ptr_->__get(__index_) - __value;
+ }
+
+ __simd_reference operator*=(_Vp __value) && {
+ return std::move(*this) = __ptr_->__get(__index_) * __value;
+ }
+
+ __simd_reference operator/=(_Vp __value) && {
+ return std::move(*this) = __ptr_->__get(__index_) / __value;
+ }
+
+ __simd_reference operator%=(_Vp __value) && {
+ return std::move(*this) = __ptr_->__get(__index_) % __value;
+ }
+
+ __simd_reference operator>>=(_Vp __value) && {
+ return std::move(*this) = __ptr_->__get(__index_) >> __value;
+ }
+
+ __simd_reference operator<<=(_Vp __value) && {
+ return std::move(*this) = __ptr_->__get(__index_) << __value;
+ }
+
+ __simd_reference operator&=(_Vp __value) && {
+ return std::move(*this) = __ptr_->__get(__index_) & __value;
+ }
+
+ __simd_reference operator|=(_Vp __value) && {
+ return std::move(*this) = __ptr_->__get(__index_) | __value;
+ }
+
+ __simd_reference operator^=(_Vp __value) && {
+ return std::move(*this) = __ptr_->__get(__index_) ^ __value;
+ }
};
template <class _To, class _From>
@@ -658,6 +871,17 @@
return static_cast<_Tp>(__first) + __variadic_sum<_Tp>(__rest...);
}
+template <class _Tp>
+struct __nodeduce {
+ using type = _Tp;
+};
+
+template <class _Tp>
+constexpr bool __vectorizable() {
+ return std::is_arithmetic<_Tp>::value && !std::is_const<_Tp>::value &&
+ !std::is_volatile<_Tp>::value && !std::is_same<_Tp, bool>::value;
+}
+
_LIBCPP_END_NAMESPACE_EXPERIMENTAL_SIMD
_LIBCPP_BEGIN_NAMESPACE_EXPERIMENTAL_SIMD_ABI
@@ -668,12 +892,20 @@
#if _LIBCPP_STD_VER > 14 && !defined(_LIBCPP_HAS_NO_VARIABLE_TEMPLATES)
template <class _Tp>
-_LIBCPP_INLINE_VAR constexpr int max_fixed_size = 32;
+_LIBCPP_INLINE_VAR constexpr size_t max_fixed_size = 32;
#endif
+
template <class _Tp>
using compatible = fixed_size<16 / sizeof(_Tp)>;
+
template <class _Tp>
-using native = compatible<_Tp>;
+using native =
+#ifndef _LIBCPP_HAS_NO_VECTOR_EXTENSION
+ __simd_abi<_StorageKind::_VecExt,
+ _LIBCPP_NATIVE_SIMD_WIDTH_IN_BYTES / sizeof(_Tp)>;
+#else
+ fixed_size<_Tp, _LIBCPP_NATIVE_SIMD_WIDTH_IN_BYTES / sizeof(_Tp)>;
+#endif // _LIBCPP_HAS_NO_VECTOR_EXTENSION
_LIBCPP_END_NAMESPACE_EXPERIMENTAL_SIMD_ABI
_LIBCPP_BEGIN_NAMESPACE_EXPERIMENTAL_SIMD
@@ -762,6 +994,7 @@
"Element type should be vectorizable");
};
+// TODO: implement it.
template <class _Tp, class _Up = typename _Tp::value_type>
struct memory_alignment;
@@ -910,11 +1143,6 @@
class where_expression;
// masked assignment [simd.mask.where]
-template <class _Tp>
-struct __nodeduce {
- using type = _Tp;
-};
-
template <class _Tp, class _Abi>
where_expression<simd_mask<_Tp, _Abi>, simd<_Tp, _Abi>>
where(const typename simd<_Tp, _Abi>::mask_type&, simd<_Tp, _Abi>&) noexcept;
@@ -1051,7 +1279,23 @@
// TODO: implement simd
template <class _Tp, class _Abi>
class simd {
+public:
+ using value_type = _Tp;
+ using reference = __simd_reference<_Tp, _Tp, _Abi>;
+ using mask_type = simd_mask<_Tp, _Abi>;
+ using abi_type = _Abi;
+
+ simd() = default;
+ simd(const simd&) = default;
+ simd& operator=(const simd&) = default;
+
+ static constexpr size_t size() noexcept {
+ return simd_size<_Tp, _Abi>::value;
+ }
+
private:
+ __simd_storage<_Tp, _Abi> __s_;
+
template <class _Up>
static constexpr bool __can_broadcast() {
return (std::is_arithmetic<_Up>::value &&
@@ -1064,57 +1308,97 @@
std::is_unsigned<_Tp>::value);
}
-public:
- using value_type = _Tp;
- // TODO: this is strawman implementation. Turn it into a proxy type.
- using reference = _Tp&;
- using mask_type = simd_mask<_Tp, _Abi>;
-
- using abi_type = _Abi;
+ template <class _Generator, size_t... __indicies>
+ static constexpr decltype(
+ std::forward_as_tuple(std::declval<_Generator>()(
+ std::integral_constant<size_t, __indicies>())...),
+ bool())
+ __can_generate(std::index_sequence<__indicies...>) {
+ return !__variadic_sum<bool>(
+ !__can_broadcast<decltype(std::declval<_Generator>()(
+ std::integral_constant<size_t, __indicies>()))>()...);
+ }
- static constexpr size_t size() noexcept {
- return simd_size<_Tp, _Abi>::value;
+ template <class _Generator>
+ static bool __can_generate(...) {
+ return false;
}
- simd() = default;
+ template <class _Generator, size_t... __indicies>
+ void __generator_init(_Generator&& __g, std::index_sequence<__indicies...>) {
+ int __unused[] = {((*this)[__indicies] =
+ __g(std::integral_constant<size_t, __indicies>()),
+ 0)...};
+ (void)__unused;
+ }
+public:
// implicit type conversion constructor
template <class _Up,
class = typename std::enable_if<
std::is_same<_Abi, simd_abi::fixed_size<size()>>::value &&
__is_non_narrowing_arithmetic_convertible<_Up, _Tp>()>::type>
- simd(const simd<_Up, simd_abi::fixed_size<size()>>&) {}
+ simd(const simd<_Up, simd_abi::fixed_size<size()>>& __v) {
+ for (size_t __i = 0; __i < size(); __i++) {
+ (*this)[__i] = static_cast<_Tp>(__v[__i]);
+ }
+ }
// implicit broadcast constructor
template <class _Up,
class = typename std::enable_if<__can_broadcast<_Up>()>::type>
- simd(_Up&&);
+ simd(_Up&& __rv) {
+ auto __v = static_cast<_Tp>(__rv);
+ for (size_t __i = 0; __i < size(); __i++) {
+ (*this)[__i] = __v;
+ }
+ }
// generator constructor
- // TODO: for now only check for the index 0. This is because C++11 doesn't
- // have index_sequence, and it's hard to check for all indicies without using
- // index_sequence.
template <class _Generator,
- int = decltype(simd(std::declval<_Generator>()(
- std::integral_constant<size_t, 0>())),
- int())()>
- explicit simd(_Generator&&);
+ int = typename std::enable_if<
+ __can_generate<_Generator>(std::make_index_sequence<size()>()),
+ int>::type()>
+ explicit simd(_Generator&& __g) {
+ __generator_init(std::forward<_Generator>(__g),
+ std::make_index_sequence<size()>());
+ }
// load constructor
- template <class _Up, class _Flags>
- simd(const _Up*, _Flags);
+ template <
+ class _Up, class _Flags,
+ class = typename std::enable_if<__vectorizable<_Up>()>::type,
+ class = typename std::enable_if<is_simd_flag_type<_Flags>::value>::type>
+ simd(const _Up* __buffer, _Flags) {
+ // TODO: optimize for overaligned flags
+ for (size_t __i = 0; __i < size(); __i++) {
+ (*this)[__i] = static_cast<_Tp>(__buffer[__i]);
+ }
+ }
// loads [simd.load]
template <class _Up, class _Flags>
- void copy_from(const _Up*, _Flags);
+ typename std::enable_if<__vectorizable<_Up>() &&
+ is_simd_flag_type<_Flags>::value>::type
+ copy_from(const _Up* __buffer, _Flags) {
+ *this = simd(__buffer, _Flags());
+ }
// stores [simd.store]
template <class _Up, class _Flags>
- void copy_to(_Up*, _Flags) const;
+ typename std::enable_if<__vectorizable<_Up>() &&
+ is_simd_flag_type<_Flags>::value>::type
+ copy_to(_Up* __buffer, _Flags) const {
+ // TODO: optimize for overaligned flags
+ for (size_t __i = 0; __i < size(); __i++) {
+ __buffer[__i] = static_cast<_Up>((*this)[__i]);
+ }
+ }
// scalar access [simd.subscr]
- reference operator[](size_t);
- value_type operator[](size_t) const;
+ reference operator[](size_t __i) { return reference(&__s_, __i); }
+
+ value_type operator[](size_t __i) const { return __s_.__get(__i); }
// unary operators [simd.unary]
simd& operator++();
Index: libcxx/include/experimental/__config
===================================================================
--- libcxx/include/experimental/__config
+++ libcxx/include/experimental/__config
@@ -66,4 +66,11 @@
#define _LIBCPP_END_NAMESPACE_EXPERIMENTAL_SIMD_ABI \
} _LIBCPP_END_NAMESPACE_EXPERIMENTAL_SIMD
+// TODO: support more targets
+#if defined(__AVX__)
+#define _LIBCPP_NATIVE_SIMD_WIDTH_IN_BYTES 32
+#else
+#define _LIBCPP_NATIVE_SIMD_WIDTH_IN_BYTES 16
+#endif
+
#endif
Index: libcxx/include/__config
===================================================================
--- libcxx/include/__config
+++ libcxx/include/__config
@@ -1313,6 +1313,10 @@
# endif // defined(_LIBCPP_ABI_MICROSOFT) && !defined(_LIBCPP_BUILDING_LIBRARY)
#endif // _LIBCPP_NO_AUTO_LINK
+#if !defined(_LIBCPP_COMPILER_CLANG) && !defined(_LIBCPP_COMPILER_GCC)
+#define _LIBCPP_HAS_NO_VECTOR_EXTENSION
+#endif // defined(_LIBCPP_COMPILER_CLANG) || defined(_LIBCPP_COMPILER_GCC)
+
#endif // __cplusplus
#endif // _LIBCPP_CONFIG
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
