From: liuhongt <hongtao.liu@intel.com>
Date: Mon, 5 Jun 2023 04:38:41 +0000 (+0800)
Subject: Explicitly view_convert_expr mask to signed type when folding pblendvb builtins.
X-Git-Tag: basepoints/gcc-15~8498
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=dac73e4c64bf62be18bd5203e4e0f3e6bc64b4dc;p=thirdparty%2Fgcc.git

Explicitly view_convert_expr mask to signed type when folding pblendvb builtins.

Since mask < 0 will be always false for vector char when
-funsigned-char, but vpblendvb needs to check the most significant
bit. The patch explicitly VCE to vector signed char.

gcc/ChangeLog:

	PR target/110108
	* config/i386/i386.cc (ix86_gimple_fold_builtin): Explicitly
	view_convert_expr mask to signed type when folding pblendvb
	builtins.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr110108-2.c: New test.
---

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 660fe15cce19..3a1444db882c 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -18572,8 +18572,10 @@ ix86_gimple_fold_builtin (gimple_stmt_iterator *gsi)
 	      tree itype = GET_MODE_INNER (TYPE_MODE (type)) == E_SFmode
 		? intSI_type_node : intDI_type_node;
 	      type = get_same_sized_vectype (itype, type);
-	      arg2 = gimple_build (&stmts, VIEW_CONVERT_EXPR, type, arg2);
 	    }
+	  else
+	    type = signed_type_for (type);
+	  arg2 = gimple_build (&stmts, VIEW_CONVERT_EXPR, type, arg2);
 	  tree zero_vec = build_zero_cst (type);
 	  tree cmp_type = truth_type_for (type);
 	  tree cmp = gimple_build (&stmts, LT_EXPR, cmp_type, arg2, zero_vec);
diff --git a/gcc/testsuite/gcc.target/i386/pr110108-2.c b/gcc/testsuite/gcc.target/i386/pr110108-2.c
new file mode 100644
index 000000000000..2d1d2fd49915
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr110108-2.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx2 -O2 -funsigned-char" } */
+/* { dg-final { scan-assembler-times "vpblendvb" 2 } } */
+
+#include <immintrin.h>
+__m128i do_stuff_128(__m128i X0, __m128i X1, __m128i X2) {
+  __m128i Result = _mm_blendv_epi8(X0, X1, X2);
+  return Result;
+}
+
+__m256i do_stuff_256(__m256i X0, __m256i X1, __m256i X2) {
+  __m256i Result = _mm256_blendv_epi8(X0, X1, X2);
+  return Result;
+}