[llvm-branch-commits] [clang] [llvm] [LV][LAA] Vectorize math lib calls with mem write-only attribute (PR #78432)

[Paschalis Mpeis via llvm-branch-commits]

================
@@ -0,0 +1,52 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --filter "call.*(frexp|modf)" --version 4
+// RUN: %clang --target=aarch64-linux-gnu -march=armv8-a+sve -O3 -isystem %S/../Headers/Inputs/include -mllvm -vector-library=ArmPL -mllvm -force-vector-interleave=1 -mllvm -prefer-predicate-over-epilogue=predicate-dont-vectorize -emit-llvm -S -o - %s | FileCheck %s
+
+// REQUIRES: aarch64-registered-target
+
+/*
+Testing vectorization of math functions that have the attribute write-only to
+memory set. Given they have vectorized counterparts, they should be able to
+vectorize.
+*/
+
+// The following define is required to access some math functions.
+#define _GNU_SOURCE
+#include <math.h>
+
+// frexp/frexpf have no TLI mappings yet.
+
+// CHECK-LABEL: define dso_local void @frexp_f64(
+// CHECK-SAME: ptr nocapture noundef readonly [[IN:%.*]], ptr nocapture noundef writeonly [[OUT1:%.*]], ptr nocapture noundef writeonly [[OUT2:%.*]], i32 noundef [[N:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
+// CHECK:    [[CALL:%.*]] = tail call double @frexp(double noundef [[TMP0:%.*]], ptr noundef [[ADD_PTR:%.*]]) #[[ATTR2:[0-9]+]]
+//
+void frexp_f64(double *in, double *out1, int *out2, int N) {
+  for (int i = 0; i < N; ++i)
+    *out1 = frexp(in[i], out2+i);
+}
+
+// CHECK-LABEL: define dso_local void @frexp_f32(
+// CHECK-SAME: ptr nocapture noundef readonly [[IN:%.*]], ptr nocapture noundef writeonly [[OUT1:%.*]], ptr nocapture noundef writeonly [[OUT2:%.*]], i32 noundef [[N:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK:    [[CALL:%.*]] = tail call float @frexpf(float noundef [[TMP0:%.*]], ptr noundef [[ADD_PTR:%.*]]) #[[ATTR2]]
+//
+void frexp_f32(float *in, float *out1, int *out2, int N) {
+  for (int i = 0; i < N; ++i)
+    *out1 = frexpf(in[i], out2+i);
+}
+
+// CHECK-LABEL: define dso_local void @modf_f64(
+// CHECK-SAME: ptr nocapture noundef readonly [[IN:%.*]], ptr nocapture noundef writeonly [[OUT1:%.*]], ptr nocapture noundef writeonly [[OUT2:%.*]], i32 noundef [[N:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK:    [[CALL:%.*]] = tail call double @modf(double noundef [[TMP0:%.*]], ptr noundef [[ADD_PTR:%.*]]) #[[ATTR3:[0-9]+]]
+//
+void modf_f64(double *in, double *out1, double *out2, int N) {
+  for (int i = 0; i < N; ++i)
+      out1[i] = modf(in[i], out2+i);
+}
+
+// CHECK-LABEL: define dso_local void @modf_f32(
+// CHECK-SAME: ptr nocapture noundef readonly [[IN:%.*]], ptr nocapture noundef writeonly [[OUT1:%.*]], ptr nocapture noundef writeonly [[OUT2:%.*]], i32 noundef [[N:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK:    [[CALL:%.*]] = tail call float @modff(float noundef [[TMP0:%.*]], ptr noundef [[ADD_PTR:%.*]]) #[[ATTR4:[0-9]+]]
+//
+void modf_f32(float *in, float *out1, float *out2, int N) {
+  for (int i = 0; i < N; ++i)
+      out1[i] = modff(in[i], out2+i);
+}
----------------
paschalis-mpeis wrote:

This was converted to LLVM tests for LoopVectorizer, and also added LoopAccessAnalysis tests.

Finally, the PR is stacked on top of #83143, which will re-introduce at least the modf/modff mappings

https://github.com/llvm/llvm-project/pull/78432