[Clang] New loop pragma vectorize_predicate

This adds a new vectorize predication loop hint:

  #pragma clang loop vectorize_predicate(enable)

that can be used to indicate to the vectoriser that all (load/store)
instructions should be predicated (masked). This allows, for example, folding
of the remainder loop into the main loop.

This patch will be followed up with D64916 and D65197. The former is a
refactoring in the loopvectorizer and the groundwork to make tail loop folding
a more general concept, and in the latter the actual tail loop folding
transformation will be implemented.

Differential Revision: https://reviews.llvm.org/D64744

llvm-svn: 366989

4 files changed, 53 insertions, 3 deletions

diff --git a/clang/test/AST/ast-print-pragmas.cpp b/clang/test/AST/ast-print-pragmas.cpp
index a87be2a3403..7bd0b48d6e7 100644
--- a/clang/test/AST/ast-print-pragmas.cpp
+++ b/clang/test/AST/ast-print-pragmas.cpp
@@ -17,10 +17,12 @@ void test(int *List, int Length) {
 // CHECK: #pragma clang loop distribute(disable)
 // CHECK-NEXT: #pragma clang loop vectorize(enable)
 // CHECK-NEXT: #pragma clang loop interleave(disable)
+// CHECK-NEXT: #pragma clang loop vectorize_predicate(disable)
 
 #pragma clang loop distribute(disable)
 #pragma clang loop vectorize(enable)
 #pragma clang loop interleave(disable)
+#pragma clang loop vectorize_predicate(disable)
 // CHECK-NEXT: while (i - 1 < Length)
   while (i - 1 < Length) {
     List[i] = i * 2;
@@ -30,10 +32,12 @@ void test(int *List, int Length) {
 // CHECK: #pragma clang loop distribute(enable)
 // CHECK-NEXT: #pragma clang loop vectorize(disable)
 // CHECK-NEXT: #pragma clang loop interleave(enable)
+// CHECK-NEXT: #pragma clang loop vectorize_predicate(enable)
 
 #pragma clang loop distribute(enable)
 #pragma clang loop vectorize(disable)
 #pragma clang loop interleave(enable)
+#pragma clang loop vectorize_predicate(enable)
 // CHECK-NEXT: while (i - 2 < Length)
   while (i - 2 < Length) {
     List[i] = i * 2;
diff --git a/clang/test/CodeGenCXX/pragma-loop-predicate.cpp b/clang/test/CodeGenCXX/pragma-loop-predicate.cpp
new file mode 100644
index 00000000000..74aed5d17e6
--- /dev/null
+++ b/clang/test/CodeGenCXX/pragma-loop-predicate.cpp
@@ -0,0 +1,35 @@
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++11 -emit-llvm -o - %s | FileCheck %s
+
+void test0(int *List, int Length) {
+// CHECK-LABEL: @{{.*}}test0{{.*}}(
+// CHECK: br label {{.*}}, !llvm.loop ![[LOOP0:.*]]
+
+  #pragma clang loop vectorize(enable)
+  for (int i = 0; i < Length; i++)
+    List[i] = i * 2;
+}
+
+void test1(int *List, int Length) {
+// CHECK-LABEL: @{{.*}}test1{{.*}}(
+// CHECK: br label {{.*}}, !llvm.loop ![[LOOP1:.*]]
+
+  #pragma clang loop vectorize(enable) vectorize_predicate(enable)
+  for (int i = 0; i < Length; i++)
+    List[i] = i * 2;
+}
+
+void test2(int *List, int Length) {
+// CHECK-LABEL: @{{.*}}test2{{.*}}(
+// CHECK:       br label {{.*}}, !llvm.loop ![[LOOP2:.*]]
+
+  #pragma clang loop vectorize(enable) vectorize_predicate(disable)
+  for (int i = 0; i < Length; i++)
+    List[i] = i * 2;
+}
+
+// CHECK:      ![[LOOP0]] = distinct !{![[LOOP0]], !3}
+// CHECK-NEXT: !3 = !{!"llvm.loop.vectorize.enable", i1 true}
+// CHECK-NEXT: ![[LOOP1]] = distinct !{![[LOOP1]], !5, !3}
+// CHECK-NEXT: !5 = !{!"llvm.loop.vectorize.predicate.enable", i1 true}
+// CHECK-NEXT: ![[LOOP2]] = distinct !{![[LOOP2]], !7, !3}
+// CHECK-NEXT: !7 = !{!"llvm.loop.vectorize.predicate.enable", i1 false}
diff --git a/clang/test/Parser/pragma-loop.cpp b/clang/test/Parser/pragma-loop.cpp
index be765170f85..650d21c1482 100644
--- a/clang/test/Parser/pragma-loop.cpp
+++ b/clang/test/Parser/pragma-loop.cpp
@@ -81,6 +81,7 @@ void test(int *List, int Length) {
 
 #pragma clang loop vectorize(enable)
 #pragma clang loop interleave(enable)
+#pragma clang loop vectorize_predicate(enable)
 #pragma clang loop unroll(full)
   while (i + 1 < Length) {
     List[i] = i;
@@ -95,6 +96,7 @@ void test(int *List, int Length) {
 
 #pragma clang loop vectorize(disable)
 #pragma clang loop interleave(disable)
+#pragma clang loop vectorize_predicate(disable)
 #pragma clang loop unroll(disable)
   while (i - 1 < Length) {
     List[i] = i;
@@ -111,7 +113,7 @@ void test(int *List, int Length) {
   }
 
   int VList[Length];
-#pragma clang loop vectorize(disable) interleave(disable) unroll(disable)
+#pragma clang loop vectorize(disable) interleave(disable) unroll(disable) vectorize_predicate(disable)
   for (int j : VList) {
     VList[j] = List[j];
   }
@@ -130,11 +132,13 @@ void test(int *List, int Length) {
 
 /* expected-error {{expected '('}} */ #pragma clang loop vectorize
 /* expected-error {{expected '('}} */ #pragma clang loop interleave
+/* expected-error {{expected '('}} */ #pragma clang loop vectorize_predicate
 /* expected-error {{expected '('}} */ #pragma clang loop unroll
 /* expected-error {{expected '('}} */ #pragma clang loop distribute
 
 /* expected-error {{expected ')'}} */ #pragma clang loop vectorize(enable
 /* expected-error {{expected ')'}} */ #pragma clang loop interleave(enable
+/* expected-error {{expected ')'}} */ #pragma clang loop vectorize_predicate(enable
 /* expected-error {{expected ')'}} */ #pragma clang loop unroll(full
 /* expected-error {{expected ')'}} */ #pragma clang loop distribute(enable
 
@@ -147,7 +151,7 @@ void test(int *List, int Length) {
 /* expected-error {{missing argument; expected 'enable', 'full' or 'disable'}} */ #pragma clang loop unroll()
 /* expected-error {{missing argument; expected 'enable' or 'disable'}} */ #pragma clang loop distribute()
 
-/* expected-error {{missing option; expected vectorize, vectorize_width, interleave, interleave_count, unroll, unroll_count, pipeline, pipeline_initiation_interval, or distribute}} */ #pragma clang loop
+/* expected-error {{missing option; expected vectorize, vectorize_width, interleave, interleave_count, unroll, unroll_count, pipeline, pipeline_initiation_interval, vectorize_predicate, or distribute}} */ #pragma clang loop
 /* expected-error {{invalid option 'badkeyword'}} */ #pragma clang loop badkeyword
 /* expected-error {{invalid option 'badkeyword'}} */ #pragma clang loop badkeyword(enable)
 /* expected-error {{invalid option 'badkeyword'}} */ #pragma clang loop vectorize(enable) badkeyword(4)
@@ -245,6 +249,9 @@ const int VV = 4;
 /* expected-error {{duplicate directives 'vectorize(enable)' and 'vectorize(disable)'}} */ #pragma clang loop vectorize(disable)
 #pragma clang loop interleave(enable)
 /* expected-error {{duplicate directives 'interleave(enable)' and 'interleave(disable)'}} */ #pragma clang loop interleave(disable)
+#pragma clang loop vectorize_predicate(enable)
+/* expected-error@+1 {{duplicate directives 'vectorize_predicate(enable)' and 'vectorize_predicate(disable)'}} */
+#pragma clang loop vectorize_predicate(disable)
 #pragma clang loop unroll(full)
 /* expected-error {{duplicate directives 'unroll(full)' and 'unroll(disable)'}} */ #pragma clang loop unroll(disable)
 #pragma clang loop distribute(enable)
@@ -281,3 +288,7 @@ const int VV = 4;
 
 #pragma clang loop interleave(enable)
 /* expected-error {{expected statement}} */ }
+
+void foo(void) {
+#pragma clang loop vectorize_predicate(enable)
+/* expected-error {{expected statement}} */ }
diff --git a/clang/test/Parser/pragma-unroll-and-jam.cpp b/clang/test/Parser/pragma-unroll-and-jam.cpp
index ef1867aa195..6ff9f1fe853 100644
--- a/clang/test/Parser/pragma-unroll-and-jam.cpp
+++ b/clang/test/Parser/pragma-unroll-and-jam.cpp
@@ -67,7 +67,7 @@ void test(int *List, int Length, int Value) {
   }
 
 // pragma clang unroll_and_jam is disabled for the moment
-/* expected-error {{invalid option 'unroll_and_jam'; expected vectorize, vectorize_width, interleave, interleave_count, unroll, unroll_count, pipeline, pipeline_initiation_interval, or distribute}} */ #pragma clang loop unroll_and_jam(4)
+/* expected-error {{invalid option 'unroll_and_jam'; expected vectorize, vectorize_width, interleave, interleave_count, unroll, unroll_count, pipeline, pipeline_initiation_interval, vectorize_predicate, or distribute}} */ #pragma clang loop unroll_and_jam(4)
   for (int i = 0; i < Length; i++) {
     for (int j = 0; j < Length; j++) {
       List[i * Length + j] = Value;