@@ -11607,6 +11607,18 @@ aarch64_if_then_else_costs (rtx op0, rtx op1, rtx op2, int *cost, bool speed)
/* CSINV/NEG with zero extend + const 0 (*csinv3_uxtw_insn3). */
op1 = XEXP (inner, 0);
}
+ else if (op1 == constm1_rtx || op1 == const1_rtx)
+ {
+ /* Use CSINV or CSINC. */
+ *cost += rtx_cost (op2, VOIDmode, IF_THEN_ELSE, 2, speed);
+ return true;
+ }
+ else if (op2 == constm1_rtx || op2 == const1_rtx)
+ {
+ /* Use CSINV or CSINC. */
+ *cost += rtx_cost (op1, VOIDmode, IF_THEN_ELSE, 1, speed);
+ return true;
+ }
*cost += rtx_cost (op1, VOIDmode, IF_THEN_ELSE, 1, speed);
*cost += rtx_cost (op2, VOIDmode, IF_THEN_ELSE, 2, speed);
new file mode 100644
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-tree-vectorize" } */
+
+int f(int *a, int n, int *b, int d)
+{
+ for(int i = 0; i < n; i++)
+ b[i] = a[i] == 100 ? 1 : d;
+ /* { dg-final { scan-assembler "csinc\tw\[0-9\].*wzr" } } */
+ return 0;
+}
While looking into PR 112454, I found the cost for `(if_then_else (cmp) (const_int 1) (reg))` was being recorded as 8 (or `COSTS_N_INSNS (2)`) but it should have been 4 (or `COSTS_N_INSNS (1)`). This improves the cost by not adding the cost of `(const_int 1)` to the total cost. It does not does not fully fix PR 112454 as that requires other changes to forwprop the `(const_int 1)` earlier than combine. Though we do fix the loop case where the constant was only used once. Committed as approved after bootstrapped and tested on aarch64-linux-gnu with no regressions. gcc/ChangeLog: * config/aarch64/aarch64.cc (aarch64_if_then_else_costs): Handle csinv/csinc case of 1/-1. gcc/testsuite/ChangeLog: * gcc.target/aarch64/csinc-3.c: New test. Signed-off-by: Andrew Pinski <quic_apinski@quicinc.com> --- gcc/config/aarch64/aarch64.cc | 12 ++++++++++++ gcc/testsuite/gcc.target/aarch64/csinc-3.c | 10 ++++++++++ 2 files changed, 22 insertions(+) create mode 100644 gcc/testsuite/gcc.target/aarch64/csinc-3.c