summaryrefslogtreecommitdiffstats
path: root/clang/test/CodeGenCXX/attr-target-mv-diff-ns.cpp
diff options
context:
space:
mode:
authorErich Keane <erich.keane@intel.com>2018-10-25 18:57:19 +0000
committerErich Keane <erich.keane@intel.com>2018-10-25 18:57:19 +0000
commit19a8adc9bd2785698c1d5429503fd406d95b6c53 (patch)
tree79e0cbe7c653251b6a98179bbd759bdd3887acc9 /clang/test/CodeGenCXX/attr-target-mv-diff-ns.cpp
parent4a825e7b29f4bc1f3543a8b94106e5006be8e833 (diff)
downloadbcm5719-llvm-19a8adc9bd2785698c1d5429503fd406d95b6c53.tar.gz
bcm5719-llvm-19a8adc9bd2785698c1d5429503fd406d95b6c53.zip
Implement Function Multiversioning for Non-ELF Systems.
Similar to how ICC handles CPU-Dispatch on Windows, this patch uses the resolver function directly to forward the call to the proper function. This is not nearly as efficient as IFuncs of course, but is still quite useful for large functions specifically developed for certain processors. This is unfortunately still limited to x86, since it depends on __builtin_cpu_supports and __builtin_cpu_is, which are x86 builtins. The naming for the resolver/forwarding function for cpu-dispatch was taken from ICC's implementation, which uses the unmodified name for this (no mangling additions). This is possible, since cpu-dispatch uses '.A' for the 'default' version. In 'target' multiversioning, this function keeps the '.resolver' extension in order to keep the default function keeping the default mangling. Change-Id: I4731555a39be26c7ad59a2d8fda6fa1a50f73284 Differential Revision: https://reviews.llvm.org/D53586 llvm-svn: 345298
Diffstat (limited to 'clang/test/CodeGenCXX/attr-target-mv-diff-ns.cpp')
-rw-r--r--clang/test/CodeGenCXX/attr-target-mv-diff-ns.cpp108
1 files changed, 71 insertions, 37 deletions
diff --git a/clang/test/CodeGenCXX/attr-target-mv-diff-ns.cpp b/clang/test/CodeGenCXX/attr-target-mv-diff-ns.cpp
index 4dc2b67b464..77e1ad771ec 100644
--- a/clang/test/CodeGenCXX/attr-target-mv-diff-ns.cpp
+++ b/clang/test/CodeGenCXX/attr-target-mv-diff-ns.cpp
@@ -1,5 +1,6 @@
-// RUN: %clang_cc1 -std=c++11 -triple x86_64-linux-gnu -emit-llvm %s -o - | FileCheck %s
-// Test ensures that this properly differentiates between types in different
+// RUN: %clang_cc1 -std=c++11 -triple x86_64-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix=LINUX
+// RUN: %clang_cc1 -std=c++11 -triple x86_64-windows-pc -emit-llvm %s -o - | FileCheck %s --check-prefix=WINDOWS
+// Test ensures that this properly differentiates between types in different
// namespaces.
int __attribute__((target("sse4.2"))) foo(int) { return 0; }
int __attribute__((target("arch=sandybridge"))) foo(int);
@@ -17,38 +18,71 @@ int bar() {
return foo(1) + ns::foo(2);
}
-// CHECK: @_Z3fooi.ifunc = ifunc i32 (i32), i32 (i32)* ()* @_Z3fooi.resolver
-// CHECK: @_ZN2ns3fooEi.ifunc = ifunc i32 (i32), i32 (i32)* ()* @_ZN2ns3fooEi.resolver
-
-// CHECK: define i32 @_Z3fooi.sse4.2(i32)
-// CHECK: ret i32 0
-// CHECK: define i32 @_Z3fooi.arch_ivybridge(i32)
-// CHECK: ret i32 1
-// CHECK: define i32 @_Z3fooi(i32)
-// CHECK: ret i32 2
-
-// CHECK: define i32 @_ZN2ns3fooEi.sse4.2(i32)
-// CHECK: ret i32 0
-// CHECK: define i32 @_ZN2ns3fooEi.arch_ivybridge(i32)
-// CHECK: ret i32 1
-// CHECK: define i32 @_ZN2ns3fooEi(i32)
-// CHECK: ret i32 2
-
-// CHECK: define i32 @_Z3barv()
-// CHECK: call i32 @_Z3fooi.ifunc(i32 1)
-// CHECK: call i32 @_ZN2ns3fooEi.ifunc(i32 2)
-
-// CHECK: define i32 (i32)* @_Z3fooi.resolver() comdat
-// CHECK: ret i32 (i32)* @_Z3fooi.arch_sandybridge
-// CHECK: ret i32 (i32)* @_Z3fooi.arch_ivybridge
-// CHECK: ret i32 (i32)* @_Z3fooi.sse4.2
-// CHECK: ret i32 (i32)* @_Z3fooi
-//
-// CHECK: define i32 (i32)* @_ZN2ns3fooEi.resolver() comdat
-// CHECK: ret i32 (i32)* @_ZN2ns3fooEi.arch_sandybridge
-// CHECK: ret i32 (i32)* @_ZN2ns3fooEi.arch_ivybridge
-// CHECK: ret i32 (i32)* @_ZN2ns3fooEi.sse4.2
-// CHECK: ret i32 (i32)* @_ZN2ns3fooEi
-
-// CHECK: declare i32 @_Z3fooi.arch_sandybridge(i32)
-// CHECK: declare i32 @_ZN2ns3fooEi.arch_sandybridge(i32)
+// LINUX: @_Z3fooi.ifunc = ifunc i32 (i32), i32 (i32)* ()* @_Z3fooi.resolver
+// LINUX: @_ZN2ns3fooEi.ifunc = ifunc i32 (i32), i32 (i32)* ()* @_ZN2ns3fooEi.resolver
+
+// LINUX: define i32 @_Z3fooi.sse4.2(i32)
+// LINUX: ret i32 0
+// LINUX: define i32 @_Z3fooi.arch_ivybridge(i32)
+// LINUX: ret i32 1
+// LINUX: define i32 @_Z3fooi(i32)
+// LINUX: ret i32 2
+
+// WINDOWS: define dso_local i32 @"?foo@@YAHH@Z.sse4.2"(i32)
+// WINDOWS: ret i32 0
+// WINDOWS: define dso_local i32 @"?foo@@YAHH@Z.arch_ivybridge"(i32)
+// WINDOWS: ret i32 1
+// WINDOWS: define dso_local i32 @"?foo@@YAHH@Z"(i32)
+// WINDOWS: ret i32 2
+
+// LINUX: define i32 @_ZN2ns3fooEi.sse4.2(i32)
+// LINUX: ret i32 0
+// LINUX: define i32 @_ZN2ns3fooEi.arch_ivybridge(i32)
+// LINUX: ret i32 1
+// LINUX: define i32 @_ZN2ns3fooEi(i32)
+// LINUX: ret i32 2
+
+// WINDOWS: define dso_local i32 @"?foo@ns@@YAHH@Z.sse4.2"(i32)
+// WINDOWS: ret i32 0
+// WINDOWS: define dso_local i32 @"?foo@ns@@YAHH@Z.arch_ivybridge"(i32)
+// WINDOWS: ret i32 1
+// WINDOWS: define dso_local i32 @"?foo@ns@@YAHH@Z"(i32)
+// WINDOWS: ret i32 2
+
+// LINUX: define i32 @_Z3barv()
+// LINUX: call i32 @_Z3fooi.ifunc(i32 1)
+// LINUX: call i32 @_ZN2ns3fooEi.ifunc(i32 2)
+
+// WINDOWS: define dso_local i32 @"?bar@@YAHXZ"()
+// WINDOWS: call i32 @"?foo@@YAHH@Z.resolver"(i32 1)
+// WINDOWS: call i32 @"?foo@ns@@YAHH@Z.resolver"(i32 2)
+
+// LINUX: define i32 (i32)* @_Z3fooi.resolver() comdat
+// LINUX: ret i32 (i32)* @_Z3fooi.arch_sandybridge
+// LINUX: ret i32 (i32)* @_Z3fooi.arch_ivybridge
+// LINUX: ret i32 (i32)* @_Z3fooi.sse4.2
+// LINUX: ret i32 (i32)* @_Z3fooi
+
+// WINDOWS: define dso_local i32 @"?foo@@YAHH@Z.resolver"(i32) comdat
+// WINDOWS: call i32 @"?foo@@YAHH@Z.arch_sandybridge"(i32 %0)
+// WINDOWS: call i32 @"?foo@@YAHH@Z.arch_ivybridge"(i32 %0)
+// WINDOWS: call i32 @"?foo@@YAHH@Z.sse4.2"(i32 %0)
+// WINDOWS: call i32 @"?foo@@YAHH@Z"(i32 %0)
+
+// LINUX: define i32 (i32)* @_ZN2ns3fooEi.resolver() comdat
+// LINUX: ret i32 (i32)* @_ZN2ns3fooEi.arch_sandybridge
+// LINUX: ret i32 (i32)* @_ZN2ns3fooEi.arch_ivybridge
+// LINUX: ret i32 (i32)* @_ZN2ns3fooEi.sse4.2
+// LINUX: ret i32 (i32)* @_ZN2ns3fooEi
+
+// WINDOWS: define dso_local i32 @"?foo@ns@@YAHH@Z.resolver"(i32) comdat
+// WINDOWS: call i32 @"?foo@ns@@YAHH@Z.arch_sandybridge"(i32 %0)
+// WINDOWS: call i32 @"?foo@ns@@YAHH@Z.arch_ivybridge"(i32 %0)
+// WINDOWS: call i32 @"?foo@ns@@YAHH@Z.sse4.2"(i32 %0)
+// WINDOWS: call i32 @"?foo@ns@@YAHH@Z"(i32 %0)
+
+// LINUX: declare i32 @_Z3fooi.arch_sandybridge(i32)
+// LINUX: declare i32 @_ZN2ns3fooEi.arch_sandybridge(i32)
+
+// WINDOWS: declare dso_local i32 @"?foo@@YAHH@Z.arch_sandybridge"(i32)
+// WINDOWS: declare dso_local i32 @"?foo@ns@@YAHH@Z.arch_sandybridge"(i32)
OpenPOWER on IntegriCloud