Hi,

   The patch optimizes the code generation for vec_xl_sext builtin. Now all the sign extensions are done on VSX registers directly.

   Bootstrapped and tested on powerpc64le-linux with no regressions. Is this okay for trunk? Any recommendations? Thanks a lot.

ChangeLog

2021-11-16 Haochen Gui <guihaoc@linux.ibm.com>

gcc/
        * config/rs6000/rs6000-call.c (altivec_expand_lxvr_builtin): Modify
        the expansion for sign extension. All extensions are done on VSX
        registers.

gcc/testsuite/
        * gcc.target/powerpc/p10_vec_xl_sext.c: New test.

patch.diff

diff --git a/gcc/config/rs6000/rs6000-call.c b/gcc/config/rs6000/rs6000-call.c
index b4e13af4dc6..587e9fa2a2a 100644
--- a/gcc/config/rs6000/rs6000-call.c
+++ b/gcc/config/rs6000/rs6000-call.c
@@ -9779,7 +9779,7 @@ altivec_expand_lxvr_builtin (enum insn_code icode, tree exp, rtx target, bool bl

   if (sign_extend)
     {
-      rtx discratch = gen_reg_rtx (DImode);
+      rtx discratch = gen_reg_rtx (V2DImode);
       rtx tiscratch = gen_reg_rtx (TImode);

       /* Emit the lxvr*x insn.  */
@@ -9788,20 +9788,31 @@ altivec_expand_lxvr_builtin (enum insn_code icode, tree exp, rtx target, bool bl
        return 0;
       emit_insn (pat);

-      /* Emit a sign extension from QI,HI,WI to double (DI).  */
-      rtx scratch = gen_lowpart (smode, tiscratch);
+      /* Emit a sign extension from V16QI,V8HI,V4SI to V2DI.  */
+      rtx temp1, temp2;
       if (icode == CODE_FOR_vsx_lxvrbx)
-       emit_insn (gen_extendqidi2 (discratch, scratch));
+       {
+         temp1  = simplify_gen_subreg (V16QImode, tiscratch, TImode, 0);
+         emit_insn (gen_vsx_sign_extend_qi_v2di (discratch, temp1));
+       }
       else if (icode == CODE_FOR_vsx_lxvrhx)
-       emit_insn (gen_extendhidi2 (discratch, scratch));
+       {
+         temp1  = simplify_gen_subreg (V8HImode, tiscratch, TImode, 0);
+         emit_insn (gen_vsx_sign_extend_hi_v2di (discratch, temp1));
+       }
       else if (icode == CODE_FOR_vsx_lxvrwx)
-       emit_insn (gen_extendsidi2 (discratch, scratch));
-      /*  Assign discratch directly if scratch is already DI.  */
-      if (icode == CODE_FOR_vsx_lxvrdx)
-       discratch = scratch;
+       {
+         temp1  = simplify_gen_subreg (V4SImode, tiscratch, TImode, 0);
+         emit_insn (gen_vsx_sign_extend_si_v2di (discratch, temp1));
+       }
+      else if (icode == CODE_FOR_vsx_lxvrdx)
+       discratch = simplify_gen_subreg (V2DImode, tiscratch, TImode, 0);
+      else
+       gcc_unreachable ();

-      /* Emit the sign extension from DI (double) to TI (quad).  */
-      emit_insn (gen_extendditi2 (target, discratch));
+      /* Emit the sign extension from V2DI (double) to TI (quad).  */
+      temp2 = simplify_gen_subreg (TImode, discratch, V2DImode, 0);
+      emit_insn (gen_extendditi2_vector (target, temp2));

       return target;
     }
diff --git a/gcc/testsuite/gcc.target/powerpc/p10_vec_xl_sext.c b/gcc/testsuite/gcc.target/powerpc/p10_vec_xl_sext.c
new file mode 100644
index 00000000000..78e72ac5425
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/p10_vec_xl_sext.c
@@ -0,0 +1,35 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target int128 } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2" } */
+
+#include <altivec.h>
+
+vector signed __int128
+foo1 (signed long a, signed char *b)
+{
+  return vec_xl_sext (a, b);
+}
+
+vector signed __int128
+foo2 (signed long a, signed short *b)
+{
+  return vec_xl_sext (a, b);
+}
+
+vector signed __int128
+foo3 (signed long a, signed int *b)
+{
+  return vec_xl_sext (a, b);
+}
+
+vector signed __int128
+foo4 (signed long a, signed long *b)
+{
+  return vec_xl_sext (a, b);
+}
+
+/* { dg-final { scan-assembler-times {\mvextsd2q\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mvextsb2d\M} 1 } } */
+/* { dg-final { scan-assembler-times {\mvextsh2d\M} 1 } } */
+/* { dg-final { scan-assembler-times {\mvextsw2d\M} 1 } } */