From: Andre Vieira <andre.simoesdiasvieira@arm.com>
Date: Fri, 3 Nov 2023 19:09:07 +0000 (+0000)
Subject: vect: allow using inbranch simdclones for masked loops
X-Git-Tag: basepoints/gcc-15~5026
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=aed00696a01ac065e9ed327434ec29d1cf50179e;p=thirdparty%2Fgcc.git

vect: allow using inbranch simdclones for masked loops

In a previous patch I did most of the work for this, but forgot to change the
check for number of arguments matching between call and simdclone.  This check
should accept calls without a mask to be matched against simdclones with mask
arguments.  I also added tests to verify this feature actually works.

gcc/ChangeLog:

	* tree-vect-stmts.cc (vectorizable_simd_clone_call): Allow unmasked
	calls to use masked simdclones.

gcc/testsuite/ChangeLog:

	* gcc.dg/vect/vect-simd-clone-20.c: New file.
	* gfortran.dg/simd-builtins-1.h: Adapt.
	* gfortran.dg/simd-builtins-6.f90: Adapt.
---

diff --git a/gcc/testsuite/gcc.dg/vect/vect-simd-clone-20.c b/gcc/testsuite/gcc.dg/vect/vect-simd-clone-20.c
new file mode 100644
index 000000000000..9f51a68f3a0c
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-simd-clone-20.c
@@ -0,0 +1,87 @@
+/* { dg-require-effective-target vect_simd_clones } */
+/* { dg-additional-options "-fopenmp-simd --param vect-epilogues-nomask=0" } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+
+/* Test that simd inbranch clones work correctly.  */
+
+#ifndef TYPE
+#define TYPE int
+#endif
+
+/* A simple function that will be cloned.  */
+#pragma omp declare simd inbranch
+TYPE __attribute__((noinline))
+foo (TYPE a)
+{
+  return a + 1;
+}
+
+/* Check that "inbranch" clones are called correctly.  */
+
+void __attribute__((noipa))
+masked (TYPE * __restrict a, TYPE * __restrict b, int size)
+{
+  #pragma omp simd
+  for (int i = 0; i < size; i++)
+    b[i] = foo(a[i]);
+}
+
+/* Check that "inbranch" works when there might be unrolling.  */
+
+void __attribute__((noipa))
+masked_fixed (TYPE * __restrict a, TYPE * __restrict b)
+{
+  #pragma omp simd
+  for (int i = 0; i < 128; i++)
+    b[i] = foo(a[i]);
+}
+
+/* Validate the outputs.  */
+
+void
+check_masked (TYPE *b, int size)
+{
+  for (int i = 0; i < size; i++)
+    if (b[i] != (TYPE)(i + 1))
+      {
+	__builtin_printf ("error at %d\n", i);
+	__builtin_exit (1);
+      }
+}
+
+int
+main ()
+{
+  TYPE a[1024];
+  TYPE b[1024];
+
+  for (int i = 0; i < 1024; i++)
+    a[i] = i;
+
+  masked_fixed (a, b);
+  check_masked (b, 128);
+
+  /* Test various sizes to cover machines with different vectorization
+     factors.  */
+  for (int size = 8; size <= 1024; size *= 2)
+    {
+      masked (a, b, size);
+      check_masked (b, size);
+    }
+
+  /* Test sizes that might exercise the partial vector code-path.  */
+  for (int size = 8; size <= 1024; size *= 2)
+    {
+      masked (a, b, size-4);
+      check_masked (b, size-4);
+    }
+
+  return 0;
+}
+
+/* Ensure the the in-branch simd clones are used on targets that support them.  */
+/* { dg-final { scan-tree-dump-times {[\n\r] [^\n]* = foo\.simdclone} 2 "vect" { target { aarch64*-*-* } } } } */
+/* { dg-final { scan-tree-dump-times {[\n\r] [^\n]* = foo\.simdclone} 4 "vect" { target { x86_64*-*-* } } } } */
+
+/* The LTO test produces two dump files and we scan the wrong one.  */
+/* { dg-skip-if "" { *-*-* } { "-flto" } { "" } } */
diff --git a/gcc/testsuite/gfortran.dg/simd-builtins-1.h b/gcc/testsuite/gfortran.dg/simd-builtins-1.h
index 88d555cf41ad..08b73514a67d 100644
--- a/gcc/testsuite/gfortran.dg/simd-builtins-1.h
+++ b/gcc/testsuite/gfortran.dg/simd-builtins-1.h
@@ -1,4 +1,3 @@
-!GCC$ builtin (sin) attributes simd (inbranch)
 !GCC$ builtin (sinf) attributes simd (notinbranch)
 !GCC$ builtin (cosf) attributes simd
 !GCC$ builtin (cosf) attributes simd (notinbranch)
diff --git a/gcc/testsuite/gfortran.dg/simd-builtins-6.f90 b/gcc/testsuite/gfortran.dg/simd-builtins-6.f90
index 60bcac78f3e0..2c68f9f1818a 100644
--- a/gcc/testsuite/gfortran.dg/simd-builtins-6.f90
+++ b/gcc/testsuite/gfortran.dg/simd-builtins-6.f90
@@ -2,7 +2,6 @@
 ! { dg-additional-options "-nostdinc -Ofast -fdump-tree-optimized" }
 ! { dg-additional-options "-msse2 -mno-avx" { target i?86-*-linux* x86_64-*-linux* } }
 
-!GCC$ builtin (sin) attributes simd (inbranch)
 !GCC$ builtin (sinf) attributes simd (notinbranch)
 !GCC$ builtin (cosf) attributes simd
 !GCC$ builtin (cosf) attributes simd (notinbranch)
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index d374907095b5..f895aaf3083a 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -4149,10 +4149,19 @@ vectorizable_simd_clone_call (vec_info *vinfo, stmt_vec_info stmt_info,
       {
 	unsigned int this_badness = 0;
 	unsigned int num_calls;
+	/* The number of arguments in the call and the number of parameters in
+	   the simdclone should match.  However, when the simdclone is
+	   'inbranch', it could have one more paramater than nargs when using
+	   an inbranch simdclone to call a non-inbranch call, either in a
+	   non-masked loop using a all true constant mask, or inside a masked
+	   loop using it's mask.  */
+	size_t simd_nargs = n->simdclone->nargs;
+	if (!masked_call_offset && n->simdclone->inbranch)
+	  simd_nargs--;
 	if (!constant_multiple_p (vf * group_size, n->simdclone->simdlen,
 				  &num_calls)
 	    || (!n->simdclone->inbranch && (masked_call_offset > 0))
-	    || nargs != n->simdclone->nargs)
+	    || (nargs != simd_nargs))
 	  continue;
 	if (num_calls != 1)
 	  this_badness += exact_log2 (num_calls) * 4096;