gcc-toolset-13-gcc/gcc13-vector-merge-2.patch

commit ffdd377fc07cdc7b62669d354e23f30940eaaffe
Author: Kewen Lin <linkw@linux.ibm.com>
Date:   Wed Jun 26 02:16:17 2024 -0500

    rs6000: Fix wrong RTL patterns for vector merge high/low char on LE
    
    Commit r12-4496 changes some define_expands and define_insns
    for vector merge high/low char, which are altivec_vmrg[hl]b.
    These defines are mainly for built-in function vec_merge{h,l}
    and some internal gen function needs.  These functions should
    consider endianness, taking vec_mergeh as example, as PVIPR
    defines, vec_mergeh "Merges the first halves (in element order)
    of two vectors", it does note it's in element order.  So it's
    mapped into vmrghb on BE while vmrglb on LE respectively.
    Although the mapped insns are different, as the discussion in
    PR106069, the RTL pattern should be still the same, it is
    conformed before commit r12-4496, but gets changed into
    different patterns on BE and LE starting from commit r12-4496.
    Similar to 32-bit element case in commit log of r15-1504, this
    8-bit element pattern on LE doesn't actually match what the
    underlying insn is intended to represent, once some optimization
    like combine does some changes basing on it, it would cause
    the unexpected consequence.  The newly constructed test case
    pr106069-1.c is a typical example for this issue.
    
    So this patch is to fix the wrong RTL pattern, ensure the
    associated RTL patterns become the same as before which can
    have the same semantic as their mapped insns.  With the
    proposed patch, the expanders like altivec_vmrghb expands
    into altivec_vmrghb_direct_be or altivec_vmrglb_direct_le
    depending on endianness, "direct" can easily show which
    insn would be generated, _be and _le are mainly for the
    different RTL patterns as endianness.
    
    Co-authored-by: Xionghu Luo <xionghuluo@tencent.com>
    
            PR target/106069
            PR target/115355
    
    gcc/ChangeLog:
    
            * config/rs6000/altivec.md (altivec_vmrghb_direct): Rename to ...
            (altivec_vmrghb_direct_be): ... this.  Add condition BYTES_BIG_ENDIAN.
            (altivec_vmrghb_direct_le): New define_insn.
            (altivec_vmrglb_direct): Rename to ...
            (altivec_vmrglb_direct_be): ... this.  Add condition BYTES_BIG_ENDIAN.
            (altivec_vmrglb_direct_le): New define_insn.
            (altivec_vmrghb): Adjust by calling gen_altivec_vmrghb_direct_be
            for BE and gen_altivec_vmrglb_direct_le for LE.
            (altivec_vmrglb): Adjust by calling gen_altivec_vmrglb_direct_be
            for BE and gen_altivec_vmrghb_direct_le for LE.
            * config/rs6000/rs6000.cc (altivec_expand_vec_perm_const): Replace
            CODE_FOR_altivec_vmrghb_direct by
            CODE_FOR_altivec_vmrghb_direct_be for BE and
            CODE_FOR_altivec_vmrghb_direct_le for LE.  And replace
            CODE_FOR_altivec_vmrglb_direct by
            CODE_FOR_altivec_vmrglb_direct_be for BE and
            CODE_FOR_altivec_vmrglb_direct_le for LE.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.target/powerpc/pr106069-1.c: New test.
    
    (cherry picked from commit 62520e4e9f7e2fe8a16ee57a4bd35da2e921ae22)

diff --git a/gcc/config/rs6000/altivec.md b/gcc/config/rs6000/altivec.md
index 92e2e4a4090..47664204bc5 100644
--- a/gcc/config/rs6000/altivec.md
+++ b/gcc/config/rs6000/altivec.md
@@ -1152,15 +1152,16 @@ (define_expand "altivec_vmrghb"
    (use (match_operand:V16QI 2 "register_operand"))]
   "TARGET_ALTIVEC"
 {
-  rtx (*fun) (rtx, rtx, rtx) = BYTES_BIG_ENDIAN ? gen_altivec_vmrghb_direct
-						: gen_altivec_vmrglb_direct;
-  if (!BYTES_BIG_ENDIAN)
-    std::swap (operands[1], operands[2]);
-  emit_insn (fun (operands[0], operands[1], operands[2]));
+  if (BYTES_BIG_ENDIAN)
+    emit_insn (
+      gen_altivec_vmrghb_direct_be (operands[0], operands[1], operands[2]));
+  else
+    emit_insn (
+      gen_altivec_vmrglb_direct_le (operands[0], operands[2], operands[1]));
   DONE;
 })
 
-(define_insn "altivec_vmrghb_direct"
+(define_insn "altivec_vmrghb_direct_be"
   [(set (match_operand:V16QI 0 "register_operand" "=v")
 	(vec_select:V16QI
 	  (vec_concat:V32QI
@@ -1174,7 +1175,25 @@ (define_insn "altivec_vmrghb_direct"
 		     (const_int 5) (const_int 21)
 		     (const_int 6) (const_int 22)
 		     (const_int 7) (const_int 23)])))]
-  "TARGET_ALTIVEC"
+  "TARGET_ALTIVEC && BYTES_BIG_ENDIAN"
+  "vmrghb %0,%1,%2"
+  [(set_attr "type" "vecperm")])
+
+(define_insn "altivec_vmrghb_direct_le"
+  [(set (match_operand:V16QI 0 "register_operand" "=v")
+	(vec_select:V16QI
+	  (vec_concat:V32QI
+	    (match_operand:V16QI 2 "register_operand" "v")
+	    (match_operand:V16QI 1 "register_operand" "v"))
+	  (parallel [(const_int  8) (const_int 24)
+		     (const_int  9) (const_int 25)
+		     (const_int 10) (const_int 26)
+		     (const_int 11) (const_int 27)
+		     (const_int 12) (const_int 28)
+		     (const_int 13) (const_int 29)
+		     (const_int 14) (const_int 30)
+		     (const_int 15) (const_int 31)])))]
+  "TARGET_ALTIVEC && !BYTES_BIG_ENDIAN"
   "vmrghb %0,%1,%2"
   [(set_attr "type" "vecperm")])
 
@@ -1274,15 +1293,16 @@ (define_expand "altivec_vmrglb"
    (use (match_operand:V16QI 2 "register_operand"))]
   "TARGET_ALTIVEC"
 {
-  rtx (*fun) (rtx, rtx, rtx) = BYTES_BIG_ENDIAN ? gen_altivec_vmrglb_direct
-						: gen_altivec_vmrghb_direct;
-  if (!BYTES_BIG_ENDIAN)
-    std::swap (operands[1], operands[2]);
-  emit_insn (fun (operands[0], operands[1], operands[2]));
+  if (BYTES_BIG_ENDIAN)
+    emit_insn (
+      gen_altivec_vmrglb_direct_be (operands[0], operands[1], operands[2]));
+  else
+    emit_insn (
+      gen_altivec_vmrghb_direct_le (operands[0], operands[2], operands[1]));
   DONE;
 })
 
-(define_insn "altivec_vmrglb_direct"
+(define_insn "altivec_vmrglb_direct_be"
   [(set (match_operand:V16QI 0 "register_operand" "=v")
 	(vec_select:V16QI
 	  (vec_concat:V32QI
@@ -1296,7 +1316,25 @@ (define_insn "altivec_vmrglb_direct"
 		     (const_int 13) (const_int 29)
 		     (const_int 14) (const_int 30)
 		     (const_int 15) (const_int 31)])))]
-  "TARGET_ALTIVEC"
+  "TARGET_ALTIVEC && BYTES_BIG_ENDIAN"
+  "vmrglb %0,%1,%2"
+  [(set_attr "type" "vecperm")])
+
+(define_insn "altivec_vmrglb_direct_le"
+  [(set (match_operand:V16QI 0 "register_operand" "=v")
+	(vec_select:V16QI
+	  (vec_concat:V32QI
+	    (match_operand:V16QI 2 "register_operand" "v")
+	    (match_operand:V16QI 1 "register_operand" "v"))
+	  (parallel [(const_int 0) (const_int 16)
+		     (const_int 1) (const_int 17)
+		     (const_int 2) (const_int 18)
+		     (const_int 3) (const_int 19)
+		     (const_int 4) (const_int 20)
+		     (const_int 5) (const_int 21)
+		     (const_int 6) (const_int 22)
+		     (const_int 7) (const_int 23)])))]
+  "TARGET_ALTIVEC && !BYTES_BIG_ENDIAN"
   "vmrglb %0,%1,%2"
   [(set_attr "type" "vecperm")])
 
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index b3d648312f1..10088033aa1 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -23166,8 +23166,8 @@ altivec_expand_vec_perm_const (rtx target, rtx op0, rtx op1,
      CODE_FOR_altivec_vpkuwum_direct,
      {2, 3, 6, 7, 10, 11, 14, 15, 18, 19, 22, 23, 26, 27, 30, 31}},
     {OPTION_MASK_ALTIVEC,
-     BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrghb_direct
-		      : CODE_FOR_altivec_vmrglb_direct,
+     BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrghb_direct_be
+		      : CODE_FOR_altivec_vmrglb_direct_le,
      {0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23}},
     {OPTION_MASK_ALTIVEC,
      BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrghh_direct
@@ -23178,8 +23178,8 @@ altivec_expand_vec_perm_const (rtx target, rtx op0, rtx op1,
 		      : CODE_FOR_altivec_vmrglw_direct_v4si_le,
      {0, 1, 2, 3, 16, 17, 18, 19, 4, 5, 6, 7, 20, 21, 22, 23}},
     {OPTION_MASK_ALTIVEC,
-     BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrglb_direct
-		      : CODE_FOR_altivec_vmrghb_direct,
+     BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrglb_direct_be
+		      : CODE_FOR_altivec_vmrghb_direct_le,
      {8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31}},
     {OPTION_MASK_ALTIVEC,
      BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrglh_direct
diff --git a/gcc/testsuite/gcc.target/powerpc/pr106069-1.c b/gcc/testsuite/gcc.target/powerpc/pr106069-1.c
new file mode 100644
index 00000000000..4945d8fedfb
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr106069-1.c
@@ -0,0 +1,39 @@
+/* { dg-do run } */
+/* { dg-options "-O2" } */
+/* { dg-require-effective-target vmx_hw } */
+
+/* Test vector merge for 8-bit element size,
+   it will abort if the RTL pattern isn't expected.  */
+
+#include "altivec.h"
+
+__attribute__((noipa))
+signed char elem_6 (vector signed char a, vector signed char b)
+{
+  vector signed char c = vec_mergeh (a,b);
+  return vec_extract (c, 6);
+}
+
+__attribute__((noipa))
+unsigned char elem_15 (vector unsigned char a, vector unsigned char b)
+{
+  vector unsigned char c = vec_mergel (a,b);
+  return vec_extract (c, 15);
+}
+
+int
+main ()
+{
+  vector unsigned char v1
+    = {3, 33, 22, 12, 34, 14, 5, 25, 30, 11, 0, 21, 17, 27, 38, 8};
+  vector unsigned char v2
+    = {81, 82, 83, 84, 68, 67, 66, 65, 99, 100, 101, 102, 250, 125, 0, 6};
+  signed char x1 = elem_6 ((vector signed char) v1, (vector signed char) v2);
+  unsigned char x2 = elem_15 (v1, v2);
+
+  if (x1 != 12 || x2 != 6)
+    __builtin_abort ();
+
+  return 0;
+}
+