[CodeGen] add/fix rotate builtins that map to LLVM funnel shift (retry)

This is a retry of rL340135 (reverted at rL340136 because of gcc host compiler crashing)
with 2 changes:
1. Move the code into a helper to reduce code duplication (and hopefully work-around the crash).
2. The original commit had a formatting bug in the docs (missing an underscore).

Original commit message:

This exposes the LLVM funnel shift intrinsics as more familiar bit rotation functions in clang
(when both halves of a funnel shift are the same value, it's a rotate).

We're free to name these as we want because we're not copying gcc, but if there's some other
existing art (eg, the microsoft ops that are modified in this patch) that we want to replicate,
we can change the names.

The funnel shift intrinsics were added here:
https://reviews.llvm.org/D49242

With improved codegen in:
https://reviews.llvm.org/rL337966
https://reviews.llvm.org/rL339359

And basic IR optimization added in:
https://reviews.llvm.org/rL338218
https://reviews.llvm.org/rL340022

...so these are expected to produce asm output that's equal or better to the multi-instruction
alternatives using primitive C/IR ops.

In the motivating loop example from PR37387:
https://bugs.llvm.org/show_bug.cgi?id=37387#c7
...we get the expected 'rolq' x86 instructions if we substitute the rotate builtin into the source.

Differential Revision: https://reviews.llvm.org/D50924

llvm-svn: 340137

1 files changed, 66 insertions, 0 deletions

diff --git a/clang/test/CodeGen/builtin-rotate.c b/clang/test/CodeGen/builtin-rotate.c
new file mode 100644
index 00000000000..8fc1701c6c9
--- /dev/null
+++ b/clang/test/CodeGen/builtin-rotate.c
@@ -0,0 +1,66 @@
+// RUN: %clang_cc1 %s -emit-llvm -o - | FileCheck %s
+
+unsigned char rotl8(unsigned char x, unsigned char y) {
+// CHECK-LABEL: rotl8
+// CHECK: [[F:%.*]] = call i8 @llvm.fshl.i8(i8 [[X:%.*]], i8 [[X]], i8 [[Y:%.*]])
+// CHECK-NEXT: ret i8 [[F]]
+
+  return __builtin_rotateleft8(x, y);
+}
+
+short rotl16(short x, short y) {
+// CHECK-LABEL: rotl16
+// CHECK: [[F:%.*]] = call i16 @llvm.fshl.i16(i16 [[X:%.*]], i16 [[X]], i16 [[Y:%.*]])
+// CHECK-NEXT: ret i16 [[F]]
+
+  return __builtin_rotateleft16(x, y);
+}
+
+int rotl32(int x, unsigned int y) {
+// CHECK-LABEL: rotl32
+// CHECK: [[F:%.*]] = call i32 @llvm.fshl.i32(i32 [[X:%.*]], i32 [[X]], i32 [[Y:%.*]])
+// CHECK-NEXT: ret i32 [[F]]
+
+  return __builtin_rotateleft32(x, y);
+}
+
+unsigned long long rotl64(unsigned long long x, long long y) {
+// CHECK-LABEL: rotl64
+// CHECK: [[F:%.*]] = call i64 @llvm.fshl.i64(i64 [[X:%.*]], i64 [[X]], i64 [[Y:%.*]])
+// CHECK-NEXT: ret i64 [[F]]
+
+  return __builtin_rotateleft64(x, y);
+}
+
+char rotr8(char x, char y) {
+// CHECK-LABEL: rotr8
+// CHECK: [[F:%.*]] = call i8 @llvm.fshr.i8(i8 [[X:%.*]], i8 [[X]], i8 [[Y:%.*]])
+// CHECK-NEXT: ret i8 [[F]]
+
+  return __builtin_rotateright8(x, y);
+}
+
+unsigned short rotr16(unsigned short x, unsigned short y) {
+// CHECK-LABEL: rotr16
+// CHECK: [[F:%.*]] = call i16 @llvm.fshr.i16(i16 [[X:%.*]], i16 [[X]], i16 [[Y:%.*]])
+// CHECK-NEXT: ret i16 [[F]]
+
+  return __builtin_rotateright16(x, y);
+}
+
+unsigned int rotr32(unsigned int x, int y) {
+// CHECK-LABEL: rotr32
+// CHECK: [[F:%.*]] = call i32 @llvm.fshr.i32(i32 [[X:%.*]], i32 [[X]], i32 [[Y:%.*]])
+// CHECK-NEXT: ret i32 [[F]]
+
+  return __builtin_rotateright32(x, y);
+}
+
+long long rotr64(long long x, unsigned long long y) {
+// CHECK-LABEL: rotr64
+// CHECK: [[F:%.*]] = call i64 @llvm.fshr.i64(i64 [[X:%.*]], i64 [[X]], i64 [[Y:%.*]])
+// CHECK-NEXT: ret i64 [[F]]
+
+  return __builtin_rotateright64(x, y);
+}
+