[Power] Use lwsync for non-seq_cst fences

Summary:
hwsync is only required for seq_cst fences, acquire and release one can use
the cheaper lwsync.

Test Plan: Added some cases to atomics.ll + make check-all

Reviewers: jfb, wschmidt

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D5317

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218995 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/PowerPC/PPCInstrInfo.td b/lib/Target/PowerPC/PPCInstrInfo.td
index fe85e8209f7add2a23f7ba881e7cc9ba4f88beda..a480757a6009bec7478156dc6e848eb8340abb94 100644 (file)
--- a/lib/Target/PowerPC/PPCInstrInfo.td
+++ b/lib/Target/PowerPC/PPCInstrInfo.td
@@ -2549,7 +2549,14 @@ def : Pat<(f64 (extloadf32 xaddr:$src)),
 def : Pat<(f64 (fextend f32:$src)),
           (COPY_TO_REGCLASS $src, F8RC)>;
 
-def : Pat<(atomic_fence (imm), (imm)), (SYNC 0)>, Requires<[HasSYNC]>;
+// Only seq_cst fences require the heavyweight sync (SYNC 0).
+// All others can use the lightweight sync (SYNC 1).
+// source: http://www.cl.cam.ac.uk/~pes20/cpp/cpp0xmappings.html
+// The rule for seq_cst is duplicated to work with both 64 bits and 32 bits
+// versions of Power.
+def : Pat<(atomic_fence (i64 7), (imm)), (SYNC 0)>, Requires<[HasSYNC]>;
+def : Pat<(atomic_fence (i32 7), (imm)), (SYNC 0)>, Requires<[HasSYNC]>;
+def : Pat<(atomic_fence (imm),   (imm)), (SYNC 1)>, Requires<[HasSYNC]>;
 def : Pat<(atomic_fence (imm), (imm)), (MSYNC)>, Requires<[HasOnlyMSYNC]>;
 
 // Additional FNMSUB patterns: -a*c + b == -(a*c - b)

diff --git a/test/CodeGen/PowerPC/atomics-fences.ll b/test/CodeGen/PowerPC/atomics-fences.ll
new file mode 100644 (file)
index 0000000..862bd17
--- /dev/null
+++ b/test/CodeGen/PowerPC/atomics-fences.ll
@@ -0,0 +1,29 @@
+; RUN: llc < %s -mtriple=powerpc-apple-darwin -march=ppc32 -verify-machineinstrs | FileCheck %s --check-prefix=CHECK
+; RUN: llc < %s -mtriple=powerpc-apple-darwin -march=ppc64 -verify-machineinstrs | FileCheck %s --check-prefix=CHECK
+; RUN: llc < %s -mtriple=powerpc-apple-darwin -mcpu=440 | FileCheck %s --check-prefix=PPC440
+
+; Fences
+define void @fence_acquire() {
+; CHECK-LABEL: fence_acquire
+; CHECK: sync 1
+; PPC440-NOT: sync 1
+; PPC440: msync
+  fence acquire
+  ret void
+}
+define void @fence_release() {
+; CHECK-LABEL: fence_release
+; CHECK: sync 1
+; PPC440-NOT: sync 1
+; PPC440: msync
+  fence release
+  ret void
+}
+define void @fence_seq_cst() {
+; CHECK-LABEL: fence_seq_cst
+; CHECK: sync 0
+; PPC440-NOT: sync 0
+; PPC440: msync
+  fence seq_cst
+  ret void
+}