Re: [pushed][PATCH] LoongArch: Split vec_selects of bottom elements into simple move

[chenglulu]

Pushed to r14-8447.

在 2024/1/16 上午10:23, Jiahao Xu 写道:

For below pattern, can be treated as a simple move because floating point
and vector share a common register on loongarch64.

(set (reg/v:SF 32 $f0 [orig:93 res ] [93])
       (vec_select:SF (reg:V8SF 32 $f0 [115])
           (parallel [
                   (const_int 0 [0])
               ])))

gcc/ChangeLog:

        * config/loongarch/lasx.md (vec_extract<mode>_0):
        New define_insn_and_split patten.

gcc/testsuite/ChangeLog:

        * gcc.target/loongarch/vect-extract.c: New test.

diff --git a/gcc/config/loongarch/lasx.md b/gcc/config/loongarch/lasx.md
index 72f7161311c..90f66ee4d24 100644
--- a/gcc/config/loongarch/lasx.md
+++ b/gcc/config/loongarch/lasx.md
@@ -761,6 +761,21 @@ (define_expand "vec_extract<mode><unitmode>"
    DONE;
  })

+(define_insn_and_split "vec_extract<mode>_0"

+  [(set (match_operand:<UNITMODE> 0 "register_operand" "=f")
+        (vec_select:<UNITMODE>
+          (match_operand:FLASX 1 "register_operand" "f")
+          (parallel [(const_int 0)])))]
+  "ISA_HAS_LSX"
+  "#"
+  "&& reload_completed"
+  [(set (match_dup 0) (match_dup 1))]
+{
+  operands[1] = gen_rtx_REG (<UNITMODE>mode, REGNO (operands[1]));
+}
+  [(set_attr "move_type" "fmove")
+   (set_attr "mode" "<UNITMODE>")])
+
  (define_expand "vec_perm<mode>"
   [(match_operand:LASX 0 "register_operand")
    (match_operand:LASX 1 "register_operand")
diff --git a/gcc/testsuite/gcc.target/loongarch/vect-extract.c 
b/gcc/testsuite/gcc.target/loongarch/vect-extract.c
new file mode 100644
index 00000000000..ce126e3a4f1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/vect-extract.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ffast-math -mlasx -fno-vect-cost-model 
-fno-unroll-loops" } */
+/* { dg-final { scan-assembler-not "xvpickve.w" } } */
+/* { dg-final { scan-assembler-not "xvpickve.d" } } */
+
+float
+sum_float (float *a, int n) {
+  float res = 0.0;
+  for (int i = 0; i < n; i++)
+    res += a[i];
+  return res;
+}
+
+double
+sum_double (double *a, int n) {
+  double res = 0.0;
+  for (int i = 0; i < n; i++)
+    res += a[i];
+  return res;
+}