===================================================================
@@ -3419,6 +3419,10 @@ dimode_scalar_chain::compute_convert_gain ()
|| GET_CODE (src) == AND)
{
gain += ix86_cost->add;
+ /* Additional gain for andnot for targets without BMI. */
+ if (GET_CODE (XEXP (src, 0)) == NOT
+ && !TARGET_BMI)
+ gain += 2 * ix86_cost->add;
if (CONST_INT_P (XEXP (src, 0)))
gain -= vector_const_cost (XEXP (src, 0));
if (CONST_INT_P (XEXP (src, 1)))
===================================================================
@@ -0,0 +1,32 @@
+/* PR target/pr78794 */
+/* { dg-do compile { target { ia32 } } } */
+/* { dg-options "-O2 -march=slm -mno-bmi -mno-stackrealign" } */
+/* { dg-final { scan-assembler "pandn" } } */
+
+typedef unsigned long long ull;
+
+struct S1
+{
+ float x;
+ ull y;
+};
+
+
+struct S2
+{
+ int a1;
+ struct S1 *node;
+ int *a2;
+};
+
+void
+foo(int c1, int c2, int c3, struct S2 *reg)
+{
+ int i;
+ for(i=0; i<reg->a1; i++)
+ if(reg->node[i].y & ((ull) 1 << c1))
+ {
+ if(reg->node[i].y & ((ull) 1 << c2))
+ reg->node[i].y ^= ((ull) 1 << c3);
+ }
+}
Hello! Attached patch fixes STV cost function to better model gains of pandn insn on non-BMI targets. As explained in the PR, STV converts four scalar arithmetic insns (2 * not and 2 * and) to one (pandn). The patch increases gain for non-BMI targets for 2 * ix86_cost->add to a total of 3 * ix86_cost->add. 2016-12-13 Uros Bizjak <ubizjak@gmail.com> PR target/78794 * config/i386/i386.c (dimode_scalar_chain::compute_convert_gain): Calculate additional gain for andnot for targets without BMI. testsuite/ChangeLog: 2016-12-13 Uros Bizjak <ubizjak@gmail.com> PR target/78794 * gcc.target/i386/pr78794.c: New test. Patch was bootstrapped and regression tested on x86_64-linux-gnu {,-m32}. Committed to mainline SVN. Uros.