Merged
Conversation
Add an MSVC-compatible <arm64_neon.h> resource header that forwards to Clang's generated <arm_neon.h>. This lets ARM64 Windows code using the MSVC header name lower NEON intrinsics through Clang builtins instead of leaving external neon_* calls such as neon_ld1m4_q32 Fix llvm#195683
llvmorg-github-actions
Bot
added
clang
|
@llvm/pr-subscribers-clang Author: GkvJwa ChangesAdd an MSVC-compatible <arm64_neon.h> resource header that forwards to Fix #195683 Full diff: https://github.com/llvm/llvm-project/pull/196014.diff 4 Files Affected:
diff --git a/clang/lib/Headers/CMakeLists.txt b/clang/lib/Headers/CMakeLists.txt
index d60ae2b5961e0..ce34f8b9410a7 100644
--- a/clang/lib/Headers/CMakeLists.txt
+++ b/clang/lib/Headers/CMakeLists.txt
@@ -55,6 +55,7 @@ set(arm_only_files
)
set(aarch64_only_files
+ arm64_neon.h
arm64intr.h
arm_neon_sve_bridge.h
)
diff --git a/clang/lib/Headers/arm64_neon.h b/clang/lib/Headers/arm64_neon.h
new file mode 100644
index 0000000000000..380e88d545621
--- /dev/null
+++ b/clang/lib/Headers/arm64_neon.h
@@ -0,0 +1,15 @@
+/*===---- arm64_neon.h - ARM64 NEON intrinsics -----------------------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __ARM64_NEON_H
+#define __ARM64_NEON_H
+
+#include <arm_neon.h>
+
+#endif /* __ARM64_NEON_H */
diff --git a/clang/lib/Headers/module.modulemap b/clang/lib/Headers/module.modulemap
index 3fcaa55f1110e..c8f96df1672c1 100644
--- a/clang/lib/Headers/module.modulemap
+++ b/clang/lib/Headers/module.modulemap
@@ -50,6 +50,12 @@ module _Builtin_intrinsics [system] [extern_c] {
header "arm64intr.h"
export *
+
+ explicit module neon {
+ requires neon
+ header "arm64_neon.h"
+ export *
+ }
}
explicit module intel {
diff --git a/clang/test/CodeGen/arm64-neon-header.c b/clang/test/CodeGen/arm64-neon-header.c
new file mode 100644
index 0000000000000..f0aea4093caad
--- /dev/null
+++ b/clang/test/CodeGen/arm64-neon-header.c
@@ -0,0 +1,13 @@
+// RUN: %clang_cc1 -triple arm64-pc-windows-msvc -fms-compatibility \
+// RUN: -emit-llvm -o - %s | FileCheck %s
+
+#include <arm64_neon.h>
+
+// CHECK-LABEL: define{{.*}} @test_vld1q_s32_x4(
+// CHECK-NOT: neon_ld1m4_q32
+// CHECK: call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld1x4.v4i32.p0(ptr {{.*}})
+// CHECK-NOT: neon_ld1m4_q32
+// CHECK: ret
+int32x4x4_t test_vld1q_s32_x4(int32_t const *a) {
+ return vld1q_s32_x4(a);
+}
|
|
@llvm/pr-subscribers-backend-x86 Author: GkvJwa ChangesAdd an MSVC-compatible <arm64_neon.h> resource header that forwards to Fix #195683 Full diff: https://github.com/llvm/llvm-project/pull/196014.diff 4 Files Affected:
diff --git a/clang/lib/Headers/CMakeLists.txt b/clang/lib/Headers/CMakeLists.txt
index d60ae2b5961e0..ce34f8b9410a7 100644
--- a/clang/lib/Headers/CMakeLists.txt
+++ b/clang/lib/Headers/CMakeLists.txt
@@ -55,6 +55,7 @@ set(arm_only_files
)
set(aarch64_only_files
+ arm64_neon.h
arm64intr.h
arm_neon_sve_bridge.h
)
diff --git a/clang/lib/Headers/arm64_neon.h b/clang/lib/Headers/arm64_neon.h
new file mode 100644
index 0000000000000..380e88d545621
--- /dev/null
+++ b/clang/lib/Headers/arm64_neon.h
@@ -0,0 +1,15 @@
+/*===---- arm64_neon.h - ARM64 NEON intrinsics -----------------------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __ARM64_NEON_H
+#define __ARM64_NEON_H
+
+#include <arm_neon.h>
+
+#endif /* __ARM64_NEON_H */
diff --git a/clang/lib/Headers/module.modulemap b/clang/lib/Headers/module.modulemap
index 3fcaa55f1110e..c8f96df1672c1 100644
--- a/clang/lib/Headers/module.modulemap
+++ b/clang/lib/Headers/module.modulemap
@@ -50,6 +50,12 @@ module _Builtin_intrinsics [system] [extern_c] {
header "arm64intr.h"
export *
+
+ explicit module neon {
+ requires neon
+ header "arm64_neon.h"
+ export *
+ }
}
explicit module intel {
diff --git a/clang/test/CodeGen/arm64-neon-header.c b/clang/test/CodeGen/arm64-neon-header.c
new file mode 100644
index 0000000000000..f0aea4093caad
--- /dev/null
+++ b/clang/test/CodeGen/arm64-neon-header.c
@@ -0,0 +1,13 @@
+// RUN: %clang_cc1 -triple arm64-pc-windows-msvc -fms-compatibility \
+// RUN: -emit-llvm -o - %s | FileCheck %s
+
+#include <arm64_neon.h>
+
+// CHECK-LABEL: define{{.*}} @test_vld1q_s32_x4(
+// CHECK-NOT: neon_ld1m4_q32
+// CHECK: call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld1x4.v4i32.p0(ptr {{.*}})
+// CHECK-NOT: neon_ld1m4_q32
+// CHECK: ret
+int32x4x4_t test_vld1q_s32_x4(int32_t const *a) {
+ return vld1q_s32_x4(a);
+}
|
| */ | ||
|
|
||
| #ifndef __ARM64_NEON_H | ||
| #define __ARM64_NEON_H |
Contributor
There was a problem hiding this comment.
Please restrict this so we only do this forwarding on MSVC targets: #ifndef _MSC_VER #include_next "arm64_neon.h" or something like that. (There should be some examples in other headers.)
Contributor
|
Adding some reviewers for the modulemap changes; I'm not really confident to review that. Otherwise LGTM |
GkvJwa
force-pushed
the
add_arm64_neon_wrappert
branch
from
2437a74 to
ae0a8aa
Compare
Contributor
Author
|
Merge it, if any problems with module, leave a comment and I will handle it |
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/51/builds/36917 Here is the relevant piece of the build log for the reference |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add an MSVC-compatible <arm64_neon.h> resource header that forwards to
Clang's generated <arm_neon.h>. This lets ARM64 Windows code using the
MSVC header name lower NEON intrinsics through Clang builtins instead of
eaving external neon_* calls such as neon_ld1m4_q32
Fixes #195683