amdgcn: implement vector div and mod libfuncs

Also divmod, but only for scalar modes, for now (because there are no complex
int vectors yet).

gcc/ChangeLog:

	* config/gcn/gcn.cc (gcn_expand_divmod_libfunc): New function.
	(gcn_init_libfuncs): Add div and mod functions for all modes.
	Add placeholders for divmod functions.
	(TARGET_EXPAND_DIVMOD_LIBFUNC): Define.

libgcc/ChangeLog:

	* config/gcn/lib2-divmod-di.c: Reimplement like lib2-divmod.c.
	* config/gcn/lib2-divmod.c: Likewise.
	* config/gcn/lib2-gcn.h: Add new types and prototypes for all the
	new vector libfuncs.
	* config/gcn/t-amdgcn: Add new files.
	* config/gcn/amdgcn_veclib.h: New file.
	* config/gcn/lib2-vec_divmod-di.c: New file.
	* config/gcn/lib2-vec_divmod-hi.c: New file.
	* config/gcn/lib2-vec_divmod-qi.c: New file.
	* config/gcn/lib2-vec_divmod.c: New file.

gcc/testsuite/ChangeLog:

	* gcc.dg/tree-ssa/predcom-2.c: Avoid vectors on amdgcn.
	* gcc.dg/unroll-8.c: Likewise.
	* gcc.dg/vect/slp-26.c: Change expected results on amdgdn.
	* lib/target-supports.exp
	(check_effective_target_vect_int_mod): Add amdgcn.
	(check_effective_target_divmod): Likewise.
	* gcc.target/gcn/simd-math-3-16.c: New test.
	* gcc.target/gcn/simd-math-3-2.c: New test.
	* gcc.target/gcn/simd-math-3-32.c: New test.
	* gcc.target/gcn/simd-math-3-4.c: New test.
	* gcc.target/gcn/simd-math-3-8.c: New test.
	* gcc.target/gcn/simd-math-3-char-16.c: New test.
	* gcc.target/gcn/simd-math-3-char-2.c: New test.
	* gcc.target/gcn/simd-math-3-char-32.c: New test.
	* gcc.target/gcn/simd-math-3-char-4.c: New test.
	* gcc.target/gcn/simd-math-3-char-8.c: New test.
	* gcc.target/gcn/simd-math-3-char-run-16.c: New test.
	* gcc.target/gcn/simd-math-3-char-run-2.c: New test.
	* gcc.target/gcn/simd-math-3-char-run-32.c: New test.
	* gcc.target/gcn/simd-math-3-char-run-4.c: New test.
	* gcc.target/gcn/simd-math-3-char-run-8.c: New test.
	* gcc.target/gcn/simd-math-3-char-run.c: New test.
	* gcc.target/gcn/simd-math-3-char.c: New test.
	* gcc.target/gcn/simd-math-3-long-16.c: New test.
	* gcc.target/gcn/simd-math-3-long-2.c: New test.
	* gcc.target/gcn/simd-math-3-long-32.c: New test.
	* gcc.target/gcn/simd-math-3-long-4.c: New test.
	* gcc.target/gcn/simd-math-3-long-8.c: New test.
	* gcc.target/gcn/simd-math-3-long-run-16.c: New test.
	* gcc.target/gcn/simd-math-3-long-run-2.c: New test.
	* gcc.target/gcn/simd-math-3-long-run-32.c: New test.
	* gcc.target/gcn/simd-math-3-long-run-4.c: New test.
	* gcc.target/gcn/simd-math-3-long-run-8.c: New test.
	* gcc.target/gcn/simd-math-3-long-run.c: New test.
	* gcc.target/gcn/simd-math-3-long.c: New test.
	* gcc.target/gcn/simd-math-3-run-16.c: New test.
	* gcc.target/gcn/simd-math-3-run-2.c: New test.
	* gcc.target/gcn/simd-math-3-run-32.c: New test.
	* gcc.target/gcn/simd-math-3-run-4.c: New test.
	* gcc.target/gcn/simd-math-3-run-8.c: New test.
	* gcc.target/gcn/simd-math-3-run.c: New test.
	* gcc.target/gcn/simd-math-3-short-16.c: New test.
	* gcc.target/gcn/simd-math-3-short-2.c: New test.
	* gcc.target/gcn/simd-math-3-short-32.c: New test.
	* gcc.target/gcn/simd-math-3-short-4.c: New test.
	* gcc.target/gcn/simd-math-3-short-8.c: New test.
	* gcc.target/gcn/simd-math-3-short-run-16.c: New test.
	* gcc.target/gcn/simd-math-3-short-run-2.c: New test.
	* gcc.target/gcn/simd-math-3-short-run-32.c: New test.
	* gcc.target/gcn/simd-math-3-short-run-4.c: New test.
	* gcc.target/gcn/simd-math-3-short-run-8.c: New test.
	* gcc.target/gcn/simd-math-3-short-run.c: New test.
	* gcc.target/gcn/simd-math-3-short.c: New test.
	* gcc.target/gcn/simd-math-3.c: New test.
	* gcc.target/gcn/simd-math-4-char-run.c: New test.
	* gcc.target/gcn/simd-math-4-char.c: New test.
	* gcc.target/gcn/simd-math-4-long-run.c: New test.
	* gcc.target/gcn/simd-math-4-long.c: New test.
	* gcc.target/gcn/simd-math-4-run.c: New test.
	* gcc.target/gcn/simd-math-4-short-run.c: New test.
	* gcc.target/gcn/simd-math-4-short.c: New test.
	* gcc.target/gcn/simd-math-4.c: New test.
	* gcc.target/gcn/simd-math-5-16.c: New test.
	* gcc.target/gcn/simd-math-5-32.c: New test.
	* gcc.target/gcn/simd-math-5-4.c: New test.
	* gcc.target/gcn/simd-math-5-8.c: New test.
	* gcc.target/gcn/simd-math-5-char-16.c: New test.
	* gcc.target/gcn/simd-math-5-char-32.c: New test.
	* gcc.target/gcn/simd-math-5-char-4.c: New test.
	* gcc.target/gcn/simd-math-5-char-8.c: New test.
	* gcc.target/gcn/simd-math-5-char-run-16.c: New test.
	* gcc.target/gcn/simd-math-5-char-run-32.c: New test.
	* gcc.target/gcn/simd-math-5-char-run-4.c: New test.
	* gcc.target/gcn/simd-math-5-char-run-8.c: New test.
	* gcc.target/gcn/simd-math-5-char-run.c: New test.
	* gcc.target/gcn/simd-math-5-char.c: New test.
	* gcc.target/gcn/simd-math-5-long-16.c: New test.
	* gcc.target/gcn/simd-math-5-long-32.c: New test.
	* gcc.target/gcn/simd-math-5-long-4.c: New test.
	* gcc.target/gcn/simd-math-5-long-8.c: New test.
	* gcc.target/gcn/simd-math-5-long-run-16.c: New test.
	* gcc.target/gcn/simd-math-5-long-run-32.c: New test.
	* gcc.target/gcn/simd-math-5-long-run-4.c: New test.
	* gcc.target/gcn/simd-math-5-long-run-8.c: New test.
	* gcc.target/gcn/simd-math-5-long-run.c: New test.
	* gcc.target/gcn/simd-math-5-long.c: New test.
	* gcc.target/gcn/simd-math-5-run-16.c: New test.
	* gcc.target/gcn/simd-math-5-run-32.c: New test.
	* gcc.target/gcn/simd-math-5-run-4.c: New test.
	* gcc.target/gcn/simd-math-5-run-8.c: New test.
	* gcc.target/gcn/simd-math-5-run.c: New test.
	* gcc.target/gcn/simd-math-5-short-16.c: New test.
	* gcc.target/gcn/simd-math-5-short-32.c: New test.
	* gcc.target/gcn/simd-math-5-short-4.c: New test.
	* gcc.target/gcn/simd-math-5-short-8.c: New test.
	* gcc.target/gcn/simd-math-5-short-run-16.c: New test.
	* gcc.target/gcn/simd-math-5-short-run-32.c: New test.
	* gcc.target/gcn/simd-math-5-short-run-4.c: New test.
	* gcc.target/gcn/simd-math-5-short-run-8.c: New test.
	* gcc.target/gcn/simd-math-5-short-run.c: New test.
	* gcc.target/gcn/simd-math-5-short.c: New test.
	* gcc.target/gcn/simd-math-5.c: New test.

9 files changed, 1052 insertions, 47 deletions

diff --git a/libgcc/config/gcn/amdgcn_veclib.h b/libgcc/config/gcn/amdgcn_veclib.h
new file mode 100644
index 0000000..15ea20b
--- /dev/null
+++ b/libgcc/config/gcn/amdgcn_veclib.h
@@ -0,0 +1,322 @@
+/* Macro library used to help during conversion of scalar math functions to
+   vectorized SIMD equivalents on AMD GCN.
+
+   Copyright (C) 2023 Free Software Foundation, Inc.
+   Contributed by Siemens.
+  
+   This file is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published by the
+   Free Software Foundation; either version 3, or (at your option) any
+   later version.
+
+   This file is distributed in the hope that it will be useful, but
+   WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   General Public License for more details.
+
+   Under Section 7 of GPL version 3, you are granted additional
+   permissions described in the GCC Runtime Library Exception, version
+   3.1, as published by the Free Software Foundation.
+
+   You should have received a copy of the GNU General Public License and
+   a copy of the GCC Runtime Library Exception along with this program;
+   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+   <http://www.gnu.org/licenses/>.  */
+
+typedef union {
+  v2sf t_v2sf;
+  v4sf t_v4sf;
+  v8sf t_v8sf;
+  v16sf t_v16sf;
+  v32sf t_v32sf;
+  v64sf t_v64sf;
+
+  v2df t_v2df;
+  v4df t_v4df;
+  v8df t_v8df;
+  v16df t_v16df;
+  v32df t_v32df;
+  v64df t_v64df;
+
+  v64qi t_v64qi;
+  v64hi t_v64hi;
+
+  v2si t_v2si;
+  v4si t_v4si;
+  v8si t_v8si;
+  v16si t_v16si;
+  v32si t_v32si;
+  v64si t_v64si;
+
+  v64usi t_v64usi;
+
+  v2di t_v2di;
+  v4di t_v4di;
+  v8di t_v8di;
+  v16di t_v16di;
+  v32di t_v32di;
+  v64di t_v64di;
+} vector_union;
+
+/* Cast between vectors with a different number of elements, or type.  */
+
+#define VGPR_CAST(to_t, from) \
+({ \
+  to_t __res; \
+  __asm__ ("" : "=v"(__res) : "0"(from)); \
+  __res; \
+})
+
+#define PACK_SI_PAIR(low, high) \
+({ \
+  v64udi __res; \
+  asm ("v_mov_b32\t%L0, %1\n\t" \
+       "v_mov_b32\t%H0, %2" \
+       : "=&v"(__res) : "v0"(low), "v"(high), "e"(-1L)); \
+  __res; \
+ })
+
+#define UNPACK_SI_LOW(to_t, pair) VGPR_CAST(to_t, pair)
+#define UNPACK_SI_HIGH(to_t, pair) \
+({ \
+  to_t __res; \
+  asm ("v_mov_b32\t%0, %H1" : "=v"(__res) : "v"(pair), "e"(-1L)); \
+  __res; \
+ })
+
+#define PACK_DI_PAIR(low, high) \
+({ \
+  v64uti __res; \
+  asm ("v_mov_b32\t%L0, %L1\n\t" \
+       "v_mov_b32\t%H0, %H1\n\t" \
+       "v_mov_b32\t%J0, %L2\n\t" \
+       "v_mov_b32\t%K0, %H2" \
+       : "=&v"(__res) : "v0"(low), "v"(high), "e"(-1L)); \
+  __res; \
+ })
+
+#define UNPACK_DI_LOW(to_t, pair) VGPR_CAST(to_t, pair)
+#define UNPACK_DI_HIGH(to_t, pair) \
+({ \
+  to_t __res; \
+  asm ("v_mov_b32\t%L0, %J1\n\t" \
+       "v_mov_b32\t%H0, %K1" : "=v"(__res) : "v"(pair), "e"(-1L)); \
+  __res; \
+ })
+
+#define NO_COND __mask
+
+/* Note - __mask is _not_ accounted for in VECTOR_MERGE!  */
+#define VECTOR_MERGE(vec1, vec2, cond) \
+({ \
+  _Static_assert (__builtin_types_compatible_p (typeof (vec1), typeof (vec2))); \
+  union { \
+    typeof (vec1) val; \
+    v64qi t_v64qi; \
+    v64hi t_v64hi; \
+    v64si t_v64si; \
+    v64di t_v64di; \
+  } __vec1, __vec2, __res; \
+  __vec1.val = (vec1); \
+  __vec2.val = (vec2); \
+  __builtin_choose_expr ( \
+        sizeof (vec1) == sizeof (v64si), \
+        ({ \
+          v64si __bitmask = __builtin_convertvector ((cond), v64si); \
+          __res.t_v64si = (__vec1.t_v64si & __bitmask) \
+                          | (__vec2.t_v64si & ~__bitmask); \
+        }), \
+	__builtin_choose_expr ( \
+	  sizeof (vec1) == sizeof (v64hi), \
+	  ({ \
+	    v64hi __bitmask = __builtin_convertvector ((cond), v64hi); \
+	    __res.t_v64hi = (__vec1.t_v64hi & __bitmask) \
+			    | (__vec2.t_v64hi & ~__bitmask); \
+	   }), \
+	   __builtin_choose_expr ( \
+	     sizeof (vec1) == sizeof (v64qi), \
+	     ({ \
+	     v64qi __bitmask = __builtin_convertvector ((cond), v64qi); \
+	     __res.t_v64qi = (__vec1.t_v64qi & __bitmask) \
+			      | (__vec2.t_v64qi & ~__bitmask); \
+	     }), \
+	     ({ \
+	      v64di __bitmask = __builtin_convertvector ((cond), v64di); \
+	      __res.t_v64di = (__vec1.t_v64di & __bitmask) \
+			      | (__vec2.t_v64di & ~__bitmask); \
+	      })))); \
+  __res.val; \
+})
+
+#define VECTOR_COND_MOVE(var, val, cond) \
+do { \
+  _Static_assert (__builtin_types_compatible_p (typeof (var), typeof (val))); \
+  __auto_type __cond = __builtin_convertvector ((cond), typeof (__mask)); \
+  var = VECTOR_MERGE ((val), var, __cond & __mask); \
+} while (0)
+
+#define VECTOR_IF(cond, cond_var) \
+{ \
+  __auto_type cond_var = (cond); \
+  __auto_type __inv_cond __attribute__((unused)) = ~cond_var; \
+  if (!ALL_ZEROES_P (cond_var)) \
+  {
+
+#define VECTOR_ELSEIF(cond, cond_var) \
+  } \
+  cond_var = __inv_cond & (cond); \
+  __inv_cond &= ~(cond); \
+  if (!ALL_ZEROES_P (cond_var)) \
+  {
+
+#define VECTOR_ELSE(cond_var) \
+  } \
+  cond_var = __inv_cond; \
+  if (!ALL_ZEROES_P (cond_var)) \
+  {
+
+#define VECTOR_IF2(cond, cond_var, prev_cond_var) \
+{ \
+  __auto_type cond_var = (cond) & __builtin_convertvector (prev_cond_var, typeof (cond)); \
+  __auto_type __inv_cond __attribute__((unused)) = ~cond_var; \
+  if (!ALL_ZEROES_P (cond_var)) \
+  {
+
+#define VECTOR_ELSEIF2(cond, cond_var, prev_cond_var) \
+  } \
+  cond_var = (cond) & __inv_cond & __builtin_convertvector (prev_cond_var, typeof (cond)); \
+  __inv_cond &= ~(cond); \
+  if (!ALL_ZEROES_P (cond_var)) \
+  {
+
+#define VECTOR_ELSE2(cond_var, prev_cond_var) \
+  } \
+  cond_var = __inv_cond & __builtin_convertvector (prev_cond_var, typeof (__inv_cond)); \
+  if (!ALL_ZEROES_P (cond_var)) \
+  {
+
+
+#define VECTOR_ENDIF \
+  } \
+}
+
+#define VECTOR_INIT_AUX(x, type) \
+({ \
+  typeof (x) __e = (x); \
+  type __tmp = { \
+    __e, __e, __e, __e, __e, __e, __e, __e, \
+    __e, __e, __e, __e, __e, __e, __e, __e, \
+    __e, __e, __e, __e, __e, __e, __e, __e, \
+    __e, __e, __e, __e, __e, __e, __e, __e, \
+    __e, __e, __e, __e, __e, __e, __e, __e, \
+    __e, __e, __e, __e, __e, __e, __e, __e, \
+    __e, __e, __e, __e, __e, __e, __e, __e, \
+    __e, __e, __e, __e, __e, __e, __e, __e }; \
+  __tmp; \
+})
+
+#define VECTOR_INIT(x) \
+  (_Generic ((x), int: VECTOR_INIT_AUX ((x), v64si), \
+                  unsigned: VECTOR_INIT_AUX ((x), v64usi), \
+                  char: VECTOR_INIT_AUX ((x), v64qi), \
+                  unsigned char: VECTOR_INIT_AUX ((x), v64uqi), \
+                  short: VECTOR_INIT_AUX ((x), v64hi), \
+                  unsigned short: VECTOR_INIT_AUX ((x), v64uhi), \
+                  long: VECTOR_INIT_AUX ((x), v64di), \
+                  unsigned long: VECTOR_INIT_AUX ((x), v64udi), \
+                  float: VECTOR_INIT_AUX ((x), v64sf), \
+                  double: VECTOR_INIT_AUX ((x), v64df)))
+
+
+#if defined (__GCN3__) || defined (__GCN5__) \
+    || defined (__CDNA1__) || defined (__CDNA2__)
+#define CDNA3_PLUS 0
+#else
+#define CDNA3_PLUS 1
+#endif
+
+#define VECTOR_INIT_MASK(COUNT) \
+({ \
+  MASKMODE __mask; \
+  int count = (COUNT); \
+  if (count == 64) \
+    { \
+      if (sizeof (MASKMODE) < 512 || CDNA3_PLUS) \
+	asm ("v_mov%B0\t%0, -1" : "=v"(__mask) : "e"(-1L)); \
+      else \
+	asm ("v_mov_b32\t%L0, -1\n\t" \
+	     "v_mov_b32\t%H0, -1" : "=v"(__mask) : "e"(-1L)); \
+    } \
+  else \
+    { \
+      long bitmask = (count == 64 ? -1 : (1<<count)-1); \
+      if (sizeof (MASKMODE) < 512 || CDNA3_PLUS) \
+        { \
+	  asm ("v_mov%B0\t%0, 0" : "=v"(__mask) : "e"(-1L)); \
+	  asm ("v_mov%B0\t%0, -1" : "+v"(__mask) : "e"(bitmask)); \
+	} \
+      else \
+        { \
+	  asm ("v_mov_b32\t%L0, 0\n\t" \
+	       "v_mov_b32\t%H0, 0" : "=v"(__mask) : "e"(-1L)); \
+	  asm ("v_mov_b32\t%L0, -1\n\t" \
+	       "v_mov_b32\t%H0, -1" : "+v"(__mask) : "e"(bitmask)); \
+	} \
+    } \
+  __mask; \
+})
+
+#define ALL_ZEROES_P(x) (COND_TO_BITMASK(x) == 0)
+
+#define COND_TO_BITMASK(x) \
+({ \
+  long __tmp = 0; \
+  __auto_type __x = __builtin_convertvector((x), typeof (__mask)) & __mask; \
+  __builtin_choose_expr (sizeof (__mask) != 512, \
+                         ({ asm ("v_cmp_ne_u32_e64 %0, %1, 0" \
+                                 : "=Sg" (__tmp) \
+                                 : "v" (__x)); }), \
+                         ({ asm ("v_cmp_ne_u64_e64 %0, %1, 0" \
+                                 : "=Sg" (__tmp) \
+                                 : "v" (__x)); })); \
+  __tmp; \
+})
+
+#define VECTOR_WHILE(cond, cond_var, prev_cond_var) \
+{ \
+  __auto_type cond_var = prev_cond_var; \
+  for (;;) { \
+    cond_var &= (cond); \
+    if (ALL_ZEROES_P (cond_var)) \
+      break;
+
+#define VECTOR_ENDWHILE \
+  } \
+}
+
+#define DEF_VARIANT(FUN, SUFFIX, OTYPE, TYPE, COUNT) \
+v##COUNT##OTYPE \
+FUN##v##COUNT##SUFFIX (v##COUNT##TYPE __arg1, v##COUNT##TYPE __arg2) \
+{ \
+  __auto_type __upsized_arg1 = VGPR_CAST (v64##TYPE, __arg1); \
+  __auto_type __upsized_arg2 = VGPR_CAST (v64##TYPE, __arg2); \
+  __auto_type __mask = VECTOR_INIT_MASK (COUNT); \
+  __auto_type __result = FUN##v64##SUFFIX##_aux (__upsized_arg1, __upsized_arg2, __mask); \
+  return VGPR_CAST (v##COUNT##OTYPE, __result); \
+}
+
+#define DEF_VARIANTS(FUN, SUFFIX, TYPE) \
+  DEF_VARIANT (FUN, SUFFIX, TYPE, TYPE, 2) \
+  DEF_VARIANT (FUN, SUFFIX, TYPE, TYPE, 4) \
+  DEF_VARIANT (FUN, SUFFIX, TYPE, TYPE, 8) \
+  DEF_VARIANT (FUN, SUFFIX, TYPE, TYPE, 16) \
+  DEF_VARIANT (FUN, SUFFIX, TYPE, TYPE, 32) \
+  DEF_VARIANT (FUN, SUFFIX, TYPE, TYPE, 64)
+
+#define DEF_VARIANTS_B(FUN, SUFFIX, OTYPE, TYPE) \
+  DEF_VARIANT (FUN, SUFFIX, OTYPE, TYPE, 2) \
+  DEF_VARIANT (FUN, SUFFIX, OTYPE, TYPE, 4) \
+  DEF_VARIANT (FUN, SUFFIX, OTYPE, TYPE, 8) \
+  DEF_VARIANT (FUN, SUFFIX, OTYPE, TYPE, 16) \
+  DEF_VARIANT (FUN, SUFFIX, OTYPE, TYPE, 32) \
+  DEF_VARIANT (FUN, SUFFIX, OTYPE, TYPE, 64)
diff --git a/libgcc/config/gcn/lib2-divmod-di.c b/libgcc/config/gcn/lib2-divmod-di.c
index a902377..d0385f3 100644
--- a/libgcc/config/gcn/lib2-divmod-di.c
+++ b/libgcc/config/gcn/lib2-divmod-di.c
@@ -22,14 +22,101 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 
 #include "lib2-gcn.h"
 
-/* We really want DImode here: override LIBGCC2_UNITS_PER_WORD.  */
-#define LIBGCC2_UNITS_PER_WORD 4
-#define TARGET_HAS_NO_HW_DIVIDE
+/* 64-bit SI divide and modulo as used in gcn.  */
 
-#define L_divmoddi4
-#define L_divdi3
-#define L_moddi3
-#define L_udivdi3
-#define L_umoddi3
+union pack {
+  UTItype ti;
+  struct {DItype quot, rem;} pair;
+};
+union upack {
+  UTItype ti;
+  struct {UDItype quot, rem;} pair;
+};
+
+UTItype
+__udivmoddi4 (UDItype num, UDItype den)
+{
+  UDItype bit = 1;
+  union upack res = {0};
+
+  while (den < num && bit && !(den & (1L<<63)))
+    {
+      den <<=1;
+      bit <<=1;
+    }
+  while (bit)
+    {
+      if (num >= den)
+	{
+	  num -= den;
+	  res.pair.quot |= bit;
+	}
+      bit >>=1;
+      den >>=1;
+    }
+  res.pair.rem = num;
+  return res.ti;
+}
+
+UTItype
+__divmoddi4 (DItype a, DItype b)
+{
+  word_type nega = 0, negb = 0;
+  union pack res;
+
+  if (a < 0)
+    {
+      a = -a;
+      nega = 1;
+    }
+
+  if (b < 0)
+    {
+      b = -b;
+      negb = 1;
+    }
+
+  res.ti = __udivmoddi4 (a, b);
+
+  if (nega)
+    res.pair.rem = -res.pair.rem;
+  if (nega ^ negb)
+    res.pair.quot = -res.pair.quot;
+
+  return res.ti;
+}
+
+
+DItype
+__divdi3 (DItype a, DItype b)
+{
+  union pack u;
+  u.ti = __divmoddi4 (a, b);
+  return u.pair.quot;
+}
+
+DItype
+__moddi3 (DItype a, DItype b)
+{
+  union pack u;
+  u.ti = __divmoddi4 (a, b);
+  return u.pair.rem;
+}
+
+
+UDItype
+__udivdi3 (UDItype a, UDItype b)
+{
+  union pack u;
+  u.ti = __udivmoddi4 (a, b);
+  return u.pair.quot;
+}
+
+UDItype
+__umoddi3 (UDItype a, UDItype b)
+{
+  union pack u;
+ u.ti = __udivmoddi4 (a, b);
+ return u.pair.rem;
+}
 
-#include "libgcc2.c"
diff --git a/libgcc/config/gcn/lib2-divmod.c b/libgcc/config/gcn/lib2-divmod.c
index c350f78..d701d1a 100644
--- a/libgcc/config/gcn/lib2-divmod.c
+++ b/libgcc/config/gcn/lib2-divmod.c
@@ -24,11 +24,20 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 
 /* 32-bit SI divide and modulo as used in gcn.  */
 
-static USItype
-udivmodsi4 (USItype num, USItype den, word_type modwanted)
+union pack {
+  UDItype di;
+  struct {SItype quot, rem;} pair;
+};
+union upack {
+  UDItype di;
+  struct {USItype quot, rem;} pair;
+};
+
+UDItype
+__udivmodsi4 (USItype num, USItype den)
 {
   USItype bit = 1;
-  USItype res = 0;
+  union upack res = {0};
 
   while (den < num && bit && !(den & (1L<<31)))
     {
@@ -40,78 +49,75 @@ udivmodsi4 (USItype num, USItype den, word_type modwanted)
       if (num >= den)
 	{
 	  num -= den;
-	  res |= bit;
+	  res.pair.quot |= bit;
 	}
       bit >>=1;
       den >>=1;
     }
-  if (modwanted)
-    return num;
-  return res;
+  res.pair.rem = num;
+  return res.di;
 }
 
-
-SItype
-__divsi3 (SItype a, SItype b)
+UDItype
+__divmodsi4 (SItype a, SItype b)
 {
-  word_type neg = 0;
-  SItype res;
+  word_type nega = 0, negb = 0;
+  union pack res;
 
   if (a < 0)
     {
       a = -a;
-      neg = !neg;
+      nega = 1;
     }
 
   if (b < 0)
     {
       b = -b;
-      neg = !neg;
+      negb = 1;
     }
 
-  res = udivmodsi4 (a, b, 0);
+  res.di = __udivmodsi4 (a, b);
 
-  if (neg)
-    res = -res;
+  if (nega)
+    res.pair.rem = -res.pair.rem;
+  if (nega ^ negb)
+    res.pair.quot = -res.pair.quot;
 
-  return res;
+  return res.di;
 }
 
 
 SItype
-__modsi3 (SItype a, SItype b)
+__divsi3 (SItype a, SItype b)
 {
-  word_type neg = 0;
-  SItype res;
-
-  if (a < 0)
-    {
-      a = -a;
-      neg = 1;
-    }
-
-  if (b < 0)
-    b = -b;
-
-  res = udivmodsi4 (a, b, 1);
-
-  if (neg)
-    res = -res;
+  union pack u;
+  u.di = __divmodsi4 (a, b);
+  return u.pair.quot;
+}
 
-  return res;
+SItype
+__modsi3 (SItype a, SItype b)
+{
+  union pack u;
+  u.di = __divmodsi4 (a, b);
+  return u.pair.rem;
 }
 
 
 USItype
 __udivsi3 (USItype a, USItype b)
 {
-  return udivmodsi4 (a, b, 0);
+  union pack u;
+  u.di = __udivmodsi4 (a, b);
+  return u.pair.quot;
 }
 
 
 USItype
 __umodsi3 (USItype a, USItype b)
 {
-  return udivmodsi4 (a, b, 1);
+  union pack u;
+ u.di = __udivmodsi4 (a, b);
+ return u.pair.rem;
 }
 
diff --git a/libgcc/config/gcn/lib2-gcn.h b/libgcc/config/gcn/lib2-gcn.h
index 67ad9ba..dc071c0 100644
--- a/libgcc/config/gcn/lib2-gcn.h
+++ b/libgcc/config/gcn/lib2-gcn.h
@@ -35,15 +35,129 @@ typedef int TItype __attribute__ ((mode (TI)));
 typedef unsigned int UTItype __attribute__ ((mode (TI)));
 typedef int word_type __attribute__ ((mode (__word__)));
 
+typedef float v2sf __attribute__ ((vector_size (8)));
+typedef float v4sf __attribute__ ((vector_size (16)));
+typedef float v8sf __attribute__ ((vector_size (32)));
+typedef float v16sf __attribute__ ((vector_size (64)));
+typedef float v32sf __attribute__ ((vector_size (128)));
+typedef float v64sf __attribute__ ((vector_size (256)));
+
+typedef double v2df __attribute__ ((vector_size (16)));
+typedef double v4df __attribute__ ((vector_size (32)));
+typedef double v8df __attribute__ ((vector_size (64)));
+typedef double v16df __attribute__ ((vector_size (128)));
+typedef double v32df __attribute__ ((vector_size (256)));
+typedef double v64df __attribute__ ((vector_size (512)));
+
+typedef signed char v2qi __attribute__ ((vector_size (2)));
+typedef signed char v4qi __attribute__ ((vector_size (4)));
+typedef signed char v8qi __attribute__ ((vector_size (8)));
+typedef signed char v16qi __attribute__ ((vector_size (16)));
+typedef signed char v32qi __attribute__ ((vector_size (32)));
+typedef signed char v64qi __attribute__ ((vector_size (64)));
+
+typedef unsigned char v2uqi __attribute__ ((vector_size (2)));
+typedef unsigned char v4uqi __attribute__ ((vector_size (4)));
+typedef unsigned char v8uqi __attribute__ ((vector_size (8)));
+typedef unsigned char v16uqi __attribute__ ((vector_size (16)));
+typedef unsigned char v32uqi __attribute__ ((vector_size (32)));
+typedef unsigned char v64uqi __attribute__ ((vector_size (64)));
+
+typedef short v2hi __attribute__ ((vector_size (4)));
+typedef short v4hi __attribute__ ((vector_size (8)));
+typedef short v8hi __attribute__ ((vector_size (16)));
+typedef short v16hi __attribute__ ((vector_size (32)));
+typedef short v32hi __attribute__ ((vector_size (64)));
+typedef short v64hi __attribute__ ((vector_size (128)));
+
+typedef unsigned short v2uhi __attribute__ ((vector_size (4)));
+typedef unsigned short v4uhi __attribute__ ((vector_size (8)));
+typedef unsigned short v8uhi __attribute__ ((vector_size (16)));
+typedef unsigned short v16uhi __attribute__ ((vector_size (32)));
+typedef unsigned short v32uhi __attribute__ ((vector_size (64)));
+typedef unsigned short v64uhi __attribute__ ((vector_size (128)));
+
+typedef int v2si __attribute__ ((vector_size (8)));
+typedef int v4si __attribute__ ((vector_size (16)));
+typedef int v8si __attribute__ ((vector_size (32)));
+typedef int v16si __attribute__ ((vector_size (64)));
+typedef int v32si __attribute__ ((vector_size (128)));
+typedef int v64si __attribute__ ((vector_size (256)));
+
+typedef unsigned int v2usi __attribute__ ((vector_size (8)));
+typedef unsigned int v4usi __attribute__ ((vector_size (16)));
+typedef unsigned int v8usi __attribute__ ((vector_size (32)));
+typedef unsigned int v16usi __attribute__ ((vector_size (64)));
+typedef unsigned int v32usi __attribute__ ((vector_size (128)));
+typedef unsigned int v64usi __attribute__ ((vector_size (256)));
+
+typedef long v2di __attribute__ ((vector_size (16)));
+typedef long v4di __attribute__ ((vector_size (32)));
+typedef long v8di __attribute__ ((vector_size (64)));
+typedef long v16di __attribute__ ((vector_size (128)));
+typedef long v32di __attribute__ ((vector_size (256)));
+typedef long v64di __attribute__ ((vector_size (512)));
+
+typedef unsigned long v2udi __attribute__ ((vector_size (16)));
+typedef unsigned long v4udi __attribute__ ((vector_size (32)));
+typedef unsigned long v8udi __attribute__ ((vector_size (64)));
+typedef unsigned long v16udi __attribute__ ((vector_size (128)));
+typedef unsigned long v32udi __attribute__ ((vector_size (256)));
+typedef unsigned long v64udi __attribute__ ((vector_size (512)));
+
+typedef UTItype v2uti __attribute__ ((vector_size (32)));
+typedef UTItype v4uti __attribute__ ((vector_size (64)));
+typedef UTItype v8uti __attribute__ ((vector_size (128)));
+typedef UTItype v16uti __attribute__ ((vector_size (256)));
+typedef UTItype v32uti __attribute__ ((vector_size (512)));
+typedef UTItype v64uti __attribute__ ((vector_size (1024)));
+
 /* Exported functions.  */
 extern DItype __divdi3 (DItype, DItype);
 extern DItype __moddi3 (DItype, DItype);
+extern UTItype __divmoddi4 (DItype, DItype);
 extern UDItype __udivdi3 (UDItype, UDItype);
 extern UDItype __umoddi3 (UDItype, UDItype);
+extern UTItype __udivmoddi4 (UDItype, UDItype);
 extern SItype __divsi3 (SItype, SItype);
 extern SItype __modsi3 (SItype, SItype);
+extern UDItype __divmodsi4 (SItype, SItype);
 extern USItype __udivsi3 (USItype, USItype);
 extern USItype __umodsi3 (USItype, USItype);
+extern UDItype __udivmodsi4 (USItype, USItype);
 extern SItype __mulsi3 (SItype, SItype);
 
+#define VECTOR_PROTOTYPES(SIZE) \
+  extern v##SIZE##qi  __divv##SIZE##qi3     (v##SIZE##qi,  v##SIZE##qi);  \
+  extern v##SIZE##qi  __modv##SIZE##qi3     (v##SIZE##qi,  v##SIZE##qi);  \
+  extern v##SIZE##udi __divmodv##SIZE##qi4  (v##SIZE##qi,  v##SIZE##qi);  \
+  extern v##SIZE##uqi __udivv##SIZE##qi3    (v##SIZE##uqi, v##SIZE##uqi); \
+  extern v##SIZE##uqi __umodv##SIZE##qi3    (v##SIZE##uqi, v##SIZE##uqi); \
+  extern v##SIZE##udi __udivmodv##SIZE##qi4 (v##SIZE##uqi, v##SIZE##uqi);  \
+  extern v##SIZE##hi  __divv##SIZE##hi3     (v##SIZE##hi,  v##SIZE##hi);  \
+  extern v##SIZE##hi  __modv##SIZE##hi3     (v##SIZE##hi,  v##SIZE##hi);  \
+  extern v##SIZE##udi __divmodv##SIZE##hi4  (v##SIZE##hi,  v##SIZE##hi);  \
+  extern v##SIZE##uhi __udivv##SIZE##hi3    (v##SIZE##uhi, v##SIZE##uhi); \
+  extern v##SIZE##uhi __umodv##SIZE##hi3    (v##SIZE##uhi, v##SIZE##uhi); \
+  extern v##SIZE##udi __udivmodv##SIZE##hi4 (v##SIZE##uhi, v##SIZE##uhi); \
+  extern v##SIZE##si  __divv##SIZE##si3     (v##SIZE##si,  v##SIZE##si);  \
+  extern v##SIZE##si  __modv##SIZE##si3     (v##SIZE##si,  v##SIZE##si);  \
+  extern v##SIZE##udi __divmodv##SIZE##si4  (v##SIZE##si,  v##SIZE##si);  \
+  extern v##SIZE##usi __udivv##SIZE##si3    (v##SIZE##usi, v##SIZE##usi); \
+  extern v##SIZE##usi __umodv##SIZE##si3    (v##SIZE##usi, v##SIZE##usi); \
+  extern v##SIZE##udi __udivmodv##SIZE##si4 (v##SIZE##usi, v##SIZE##usi); \
+  extern v##SIZE##di  __divv##SIZE##di3     (v##SIZE##di,  v##SIZE##di);  \
+  extern v##SIZE##di  __modv##SIZE##di3     (v##SIZE##di,  v##SIZE##di);  \
+  extern v##SIZE##uti __divmodv##SIZE##di4  (v##SIZE##di,  v##SIZE##di);  \
+  extern v##SIZE##udi __udivv##SIZE##di3    (v##SIZE##udi, v##SIZE##udi); \
+  extern v##SIZE##udi __umodv##SIZE##di3    (v##SIZE##udi, v##SIZE##udi); \
+  extern v##SIZE##uti __udivmodv##SIZE##di4 (v##SIZE##udi, v##SIZE##udi);
+VECTOR_PROTOTYPES (2)
+VECTOR_PROTOTYPES (4)
+VECTOR_PROTOTYPES (8)
+VECTOR_PROTOTYPES (16)
+VECTOR_PROTOTYPES (32)
+VECTOR_PROTOTYPES (64)
+#undef VECTOR_PROTOTYPES
+
 #endif /* LIB2_GCN_H */
diff --git a/libgcc/config/gcn/lib2-vec_divmod-di.c b/libgcc/config/gcn/lib2-vec_divmod-di.c
new file mode 100644
index 0000000..8f4a035
--- /dev/null
+++ b/libgcc/config/gcn/lib2-vec_divmod-di.c
@@ -0,0 +1,118 @@
+/* Copyright (C) 2012-2023 Free Software Foundation, Inc.
+   Contributed by Altera and Mentor Graphics, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 3, or (at your option) any
+later version.
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+Under Section 7 of GPL version 3, you are granted additional
+permissions described in the GCC Runtime Library Exception, version
+3.1, as published by the Free Software Foundation.
+
+You should have received a copy of the GNU General Public License and
+a copy of the GCC Runtime Library Exception along with this program;
+see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+<http://www.gnu.org/licenses/>.  */
+
+#include "lib2-gcn.h"
+
+/* 64-bit V64SI divide and modulo as used in gcn.
+   This is a simple conversion from lib2-divmod.c.  */
+
+#define MASKMODE v64di
+#include "amdgcn_veclib.h"
+
+static v64uti
+__udivmodv64di4_aux (v64udi num, v64udi den, v64di __mask)
+{
+  v64udi bit = VECTOR_INIT (1UL);
+  v64udi res = VECTOR_INIT (0UL);
+
+  VECTOR_WHILE ((den < num) & (bit != 0) & ((den & (1L<<31)) == 0),
+		cond, NO_COND)
+    VECTOR_COND_MOVE (den, den << 1, cond);
+    VECTOR_COND_MOVE (bit, bit << 1, cond);
+  VECTOR_ENDWHILE
+  VECTOR_WHILE (bit != 0, loopcond, NO_COND)
+    VECTOR_IF2 (num >= den, ifcond, loopcond)
+      VECTOR_COND_MOVE (num, num - den, ifcond);
+      VECTOR_COND_MOVE (res, res | bit, ifcond);
+    VECTOR_ENDIF
+    VECTOR_COND_MOVE (bit, bit >> 1, loopcond);
+    VECTOR_COND_MOVE (den, den >> 1, loopcond);
+  VECTOR_ENDWHILE
+
+  return PACK_DI_PAIR (res, num);
+}
+
+static v64uti
+__divmodv64di4_aux (v64di a, v64di b, v64di __mask)
+{
+  v64di nega = VECTOR_INIT (0L);
+  v64di negb = VECTOR_INIT (0L);
+
+  VECTOR_IF (a < 0, cond)
+    VECTOR_COND_MOVE (a, -a, cond);
+    nega = cond;
+  VECTOR_ENDIF
+
+  VECTOR_IF (b < 0, cond)
+    VECTOR_COND_MOVE (b, -b, cond);
+    negb = cond;
+  VECTOR_ENDIF
+
+  v64udi ua = __builtin_convertvector (a, v64udi);
+  v64udi ub = __builtin_convertvector (b, v64udi);
+  v64uti pair = __udivmodv64di4_aux (ua, ub, __mask);
+
+  v64di quot = UNPACK_DI_LOW (v64di, pair);
+  v64di rem = UNPACK_DI_HIGH (v64di, pair);
+  VECTOR_COND_MOVE (quot, -quot, nega ^ negb);
+  VECTOR_COND_MOVE (rem, -rem, nega);
+  pair = PACK_DI_PAIR (quot, rem);
+
+  return pair;
+}
+
+
+static inline v64di
+__divv64di3_aux (v64di a, v64di b, v64di __mask)
+{
+  v64uti pair = __divmodv64di4_aux (a, b, __mask);
+  return UNPACK_DI_LOW (v64di, pair);
+}
+
+static inline v64di
+__modv64di3_aux (v64di a, v64di b, v64di __mask)
+{
+  v64uti pair = __divmodv64di4_aux (a, b, __mask);
+  return UNPACK_DI_HIGH (v64di, pair);
+}
+
+
+static inline v64udi
+__udivv64di3_aux (v64udi a, v64udi b, v64di __mask)
+{
+  v64uti pair = __udivmodv64di4_aux (a, b, __mask);
+  return UNPACK_DI_LOW (v64udi, pair);
+}
+
+static inline v64udi
+__umodv64di3_aux (v64udi a, v64udi b, v64di __mask)
+{
+  v64uti pair = __udivmodv64di4_aux (a, b, __mask);
+  return UNPACK_DI_HIGH (v64udi, pair);
+}
+
+DEF_VARIANTS (__div, di3, di)
+DEF_VARIANTS (__mod, di3, di)
+DEF_VARIANTS_B (__divmod, di4, uti, di)
+DEF_VARIANTS (__udiv, di3, udi)
+DEF_VARIANTS (__umod, di3, udi)
+DEF_VARIANTS_B (__udivmod, di4, uti, udi)
diff --git a/libgcc/config/gcn/lib2-vec_divmod-hi.c b/libgcc/config/gcn/lib2-vec_divmod-hi.c
new file mode 100644
index 0000000..175ddf8
--- /dev/null
+++ b/libgcc/config/gcn/lib2-vec_divmod-hi.c
@@ -0,0 +1,118 @@
+/* Copyright (C) 2012-2023 Free Software Foundation, Inc.
+   Contributed by Altera and Mentor Graphics, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 3, or (at your option) any
+later version.
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+Under Section 7 of GPL version 3, you are granted additional
+permissions described in the GCC Runtime Library Exception, version
+3.1, as published by the Free Software Foundation.
+
+You should have received a copy of the GNU General Public License and
+a copy of the GCC Runtime Library Exception along with this program;
+see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+<http://www.gnu.org/licenses/>.  */
+
+#include "lib2-gcn.h"
+
+/* 16-bit V64HI divide and modulo as used in gcn.
+   This is a simple conversion from lib2-divmod.c.  */
+
+#define MASKMODE v64hi
+#include "amdgcn_veclib.h"
+
+static v64udi
+__udivmodv64hi4_aux (v64uhi num, v64uhi den, v64hi __mask)
+{
+  v64uhi bit = VECTOR_INIT ((unsigned short)1U);
+  v64uhi res = VECTOR_INIT ((unsigned short)0U);
+
+  VECTOR_WHILE ((den < num) & (bit != 0) & ((den & (1L<<15)) == 0),
+		cond, NO_COND)
+    VECTOR_COND_MOVE (den, den << 1, cond);
+    VECTOR_COND_MOVE (bit, bit << 1, cond);
+  VECTOR_ENDWHILE
+  VECTOR_WHILE (bit != 0, loopcond, NO_COND)
+    VECTOR_IF2 (num >= den, ifcond, loopcond)
+      VECTOR_COND_MOVE (num, num - den, ifcond);
+      VECTOR_COND_MOVE (res, res | bit, ifcond);
+    VECTOR_ENDIF
+    VECTOR_COND_MOVE (bit, bit >> 1, loopcond);
+    VECTOR_COND_MOVE (den, den >> 1, loopcond);
+  VECTOR_ENDWHILE
+
+  return PACK_SI_PAIR (res, num);
+}
+
+static v64udi
+__divmodv64hi4_aux (v64hi a, v64hi b,  v64hi __mask)
+{
+  v64hi nega = VECTOR_INIT ((short)0);
+  v64hi negb = VECTOR_INIT ((short)0);
+
+  VECTOR_IF (a < 0, cond)
+    VECTOR_COND_MOVE (a, -a, cond);
+    nega = cond;
+  VECTOR_ENDIF
+
+  VECTOR_IF (b < 0, cond)
+    VECTOR_COND_MOVE (b, -b, cond);
+    negb = cond;
+  VECTOR_ENDIF
+
+  v64uhi ua = __builtin_convertvector (a, v64uhi);
+  v64uhi ub = __builtin_convertvector (b, v64uhi);
+  v64udi pair = __udivmodv64hi4_aux (ua, ub, __mask);
+
+  v64hi quot = UNPACK_SI_LOW (v64hi, pair);
+  v64hi rem = UNPACK_SI_HIGH (v64hi, pair);
+  VECTOR_COND_MOVE (quot, -quot, nega ^ negb);
+  VECTOR_COND_MOVE (rem, -rem, nega);
+  pair = PACK_SI_PAIR (quot, rem);
+
+  return pair;
+}
+
+
+static inline v64hi
+__divv64hi3_aux (v64hi a, v64hi b, v64hi __mask)
+{
+  v64udi pair = __divmodv64hi4_aux (a, b, __mask);
+  return UNPACK_SI_LOW (v64hi, pair);
+}
+
+static inline v64hi
+__modv64hi3_aux (v64hi a, v64hi b, v64hi __mask)
+{
+  v64udi pair = __divmodv64hi4_aux (a, b, __mask);
+  return UNPACK_SI_HIGH (v64hi, pair);
+}
+
+
+static inline v64uhi
+__udivv64hi3_aux (v64uhi a, v64uhi b, v64hi __mask)
+{
+  v64udi pair = __udivmodv64hi4_aux (a, b, __mask);
+  return UNPACK_SI_LOW (v64uhi, pair);
+}
+
+static inline v64uhi
+__umodv64hi3_aux (v64uhi a, v64uhi b, v64hi __mask)
+{
+  v64udi pair = __udivmodv64hi4_aux (a, b, __mask);
+  return UNPACK_SI_HIGH (v64uhi, pair);
+}
+
+DEF_VARIANTS (__div, hi3, hi)
+DEF_VARIANTS (__mod, hi3, hi)
+DEF_VARIANTS_B (__divmod, hi4, udi, hi)
+DEF_VARIANTS (__udiv, hi3, uhi)
+DEF_VARIANTS (__umod, hi3, uhi)
+DEF_VARIANTS_B (__udivmod, hi4, udi, uhi)
diff --git a/libgcc/config/gcn/lib2-vec_divmod-qi.c b/libgcc/config/gcn/lib2-vec_divmod-qi.c
new file mode 100644
index 0000000..ff6b5c2
--- /dev/null
+++ b/libgcc/config/gcn/lib2-vec_divmod-qi.c
@@ -0,0 +1,118 @@
+/* Copyright (C) 2012-2023 Free Software Foundation, Inc.
+   Contributed by Altera and Mentor Graphics, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 3, or (at your option) any
+later version.
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+Under Section 7 of GPL version 3, you are granted additional
+permissions described in the GCC Runtime Library Exception, version
+3.1, as published by the Free Software Foundation.
+
+You should have received a copy of the GNU General Public License and
+a copy of the GCC Runtime Library Exception along with this program;
+see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+<http://www.gnu.org/licenses/>.  */
+
+#include "lib2-gcn.h"
+
+/* 8-bit V64QI divide and modulo as used in gcn.
+   This is a simple conversion from lib2-divmod.c.  */
+
+#define MASKMODE v64qi
+#include "amdgcn_veclib.h"
+
+static v64udi
+__udivmodv64qi4_aux (v64uqi num, v64uqi den, v64qi __mask)
+{
+  v64uqi bit = VECTOR_INIT ((unsigned char)1U);
+  v64uqi res = VECTOR_INIT ((unsigned char)0U);
+
+  VECTOR_WHILE ((den < num) & (bit != 0) & ((den & (1<<7)) == 0),
+		cond, NO_COND)
+    VECTOR_COND_MOVE (den, den << 1, cond);
+    VECTOR_COND_MOVE (bit, bit << 1, cond);
+  VECTOR_ENDWHILE
+  VECTOR_WHILE (bit != 0, loopcond, NO_COND)
+    VECTOR_IF2 (num >= den, ifcond, loopcond)
+      VECTOR_COND_MOVE (num, num - den, ifcond);
+      VECTOR_COND_MOVE (res, res | bit, ifcond);
+    VECTOR_ENDIF
+    VECTOR_COND_MOVE (bit, bit >> 1, loopcond);
+    VECTOR_COND_MOVE (den, den >> 1, loopcond);
+  VECTOR_ENDWHILE
+
+  return PACK_SI_PAIR (res, num);
+}
+
+static v64udi
+__divmodv64qi4_aux (v64qi a, v64qi b, v64qi __mask)
+{
+  v64qi nega = VECTOR_INIT ((char)0);
+  v64qi negb = VECTOR_INIT ((char)0);
+
+  VECTOR_IF (a < 0, cond)
+    VECTOR_COND_MOVE (a, -a, cond);
+    nega = cond;
+  VECTOR_ENDIF
+
+  VECTOR_IF (b < 0, cond)
+    VECTOR_COND_MOVE (b, -b, cond);
+    negb = cond;
+  VECTOR_ENDIF
+
+  v64uqi ua = __builtin_convertvector (a, v64uqi);
+  v64uqi ub = __builtin_convertvector (b, v64uqi);
+  v64udi pair = __udivmodv64qi4_aux (ua, ub, __mask);
+
+  v64qi quot = UNPACK_SI_LOW (v64qi, pair);
+  v64qi rem = UNPACK_SI_HIGH (v64qi, pair);
+  VECTOR_COND_MOVE (quot, -quot, nega ^ negb);
+  VECTOR_COND_MOVE (rem, -rem, nega);
+  pair = PACK_SI_PAIR (quot, rem);
+
+  return pair;
+}
+
+
+static inline v64qi
+__divv64qi3_aux (v64qi a, v64qi b, v64qi __mask)
+{
+  v64udi pair = __divmodv64qi4_aux (a, b, __mask);
+  return UNPACK_SI_LOW (v64qi, pair);
+}
+
+static inline v64qi
+__modv64qi3_aux (v64qi a, v64qi b, v64qi __mask)
+{
+  v64udi pair = __divmodv64qi4_aux (a, b, __mask);
+  return UNPACK_SI_HIGH (v64qi, pair);
+}
+
+
+static inline v64uqi
+__udivv64qi3_aux (v64uqi a, v64uqi b, v64qi __mask)
+{
+  v64udi pair = __udivmodv64qi4_aux (a, b, __mask);
+  return UNPACK_SI_LOW (v64uqi, pair);
+}
+
+static inline v64uqi
+__umodv64qi3_aux (v64uqi a, v64uqi b, v64qi __mask)
+{
+  v64udi pair = __udivmodv64qi4_aux (a, b, __mask);
+  return UNPACK_SI_HIGH (v64uqi, pair);
+}
+
+DEF_VARIANTS (__div, qi3, qi)
+DEF_VARIANTS (__mod, qi3, qi)
+DEF_VARIANTS_B (__divmod, qi4, udi, qi)
+DEF_VARIANTS (__udiv, qi3, uqi)
+DEF_VARIANTS (__umod, qi3, uqi)
+DEF_VARIANTS_B (__udivmod, qi4, udi, uqi)
diff --git a/libgcc/config/gcn/lib2-vec_divmod.c b/libgcc/config/gcn/lib2-vec_divmod.c
new file mode 100644
index 0000000..e166766
--- /dev/null
+++ b/libgcc/config/gcn/lib2-vec_divmod.c
@@ -0,0 +1,118 @@
+/* Copyright (C) 2012-2023 Free Software Foundation, Inc.
+   Contributed by Altera and Mentor Graphics, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 3, or (at your option) any
+later version.
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+Under Section 7 of GPL version 3, you are granted additional
+permissions described in the GCC Runtime Library Exception, version
+3.1, as published by the Free Software Foundation.
+
+You should have received a copy of the GNU General Public License and
+a copy of the GCC Runtime Library Exception along with this program;
+see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+<http://www.gnu.org/licenses/>.  */
+
+#include "lib2-gcn.h"
+
+/* 32-bit V64SI divide and modulo as used in gcn.
+   This is a simple conversion from lib2-divmod.c.  */
+
+#define MASKMODE v64si
+#include "amdgcn_veclib.h"
+
+static v64udi
+__udivmodv64si4_aux (v64usi num, v64usi den, v64si __mask)
+{
+  v64usi bit = VECTOR_INIT (1U);
+  v64usi res = VECTOR_INIT (0U);
+
+  VECTOR_WHILE ((den < num) & (bit != 0) & ((den & (1L<<31)) == 0),
+		cond, NO_COND)
+    VECTOR_COND_MOVE (den, den << 1, cond);
+    VECTOR_COND_MOVE (bit, bit << 1, cond);
+  VECTOR_ENDWHILE
+  VECTOR_WHILE (bit != 0, loopcond, NO_COND)
+    VECTOR_IF2 (num >= den, ifcond, loopcond)
+      VECTOR_COND_MOVE (num, num - den, ifcond);
+      VECTOR_COND_MOVE (res, res | bit, ifcond);
+    VECTOR_ENDIF
+    VECTOR_COND_MOVE (bit, bit >> 1, loopcond);
+    VECTOR_COND_MOVE (den, den >> 1, loopcond);
+  VECTOR_ENDWHILE
+
+  return PACK_SI_PAIR (res, num);
+}
+
+static v64udi
+__divmodv64si4_aux (v64si a, v64si b, v64si __mask)
+{
+  v64si nega = VECTOR_INIT (0);
+  v64si negb = VECTOR_INIT (0);
+
+  VECTOR_IF (a < 0, cond)
+    VECTOR_COND_MOVE (a, -a, cond);
+    nega = cond;
+  VECTOR_ENDIF
+
+  VECTOR_IF (b < 0, cond)
+    VECTOR_COND_MOVE (b, -b, cond);
+    negb = cond;
+  VECTOR_ENDIF
+
+  v64usi ua = __builtin_convertvector (a, v64usi);
+  v64usi ub = __builtin_convertvector (b, v64usi);
+  v64udi pair = __udivmodv64si4_aux (ua, ub, __mask);
+
+  v64si quot = UNPACK_SI_LOW (v64si, pair);
+  v64si rem = UNPACK_SI_HIGH (v64si, pair);
+  VECTOR_COND_MOVE (quot, -quot, nega ^ negb);
+  VECTOR_COND_MOVE (rem, -rem, nega);
+  pair = PACK_SI_PAIR (quot, rem);
+
+  return pair;
+}
+
+
+static inline v64si
+__divv64si3_aux (v64si a, v64si b, v64si __mask)
+{
+  v64udi pair = __divmodv64si4_aux (a, b, __mask);
+  return UNPACK_SI_LOW (v64si, pair);
+}
+
+static inline v64si
+__modv64si3_aux (v64si a, v64si b, v64si __mask)
+{
+  v64udi pair = __divmodv64si4_aux (a, b, __mask);
+  return UNPACK_SI_HIGH (v64si, pair);
+}
+
+
+static inline v64usi
+__udivv64si3_aux (v64usi a, v64usi b, v64si __mask)
+{
+  v64udi pair = __udivmodv64si4_aux (a, b, __mask);
+  return UNPACK_SI_LOW (v64usi, pair);
+}
+
+static inline v64usi
+__umodv64si3_aux (v64usi a, v64usi b, v64si __mask)
+{
+  v64udi pair = __udivmodv64si4_aux (a, b, __mask);
+  return UNPACK_SI_HIGH (v64usi, pair);
+}
+
+DEF_VARIANTS (__div, si3, si)
+DEF_VARIANTS (__mod, si3, si)
+DEF_VARIANTS_B (__divmod, si4, udi, si)
+DEF_VARIANTS (__udiv, si3, usi)
+DEF_VARIANTS (__umod, si3, usi)
+DEF_VARIANTS_B (__udivmod, si4, udi, usi)
diff --git a/libgcc/config/gcn/t-amdgcn b/libgcc/config/gcn/t-amdgcn
index e64953e..d1d9a4f 100644
--- a/libgcc/config/gcn/t-amdgcn
+++ b/libgcc/config/gcn/t-amdgcn
@@ -1,6 +1,10 @@
 LIB2ADD += $(srcdir)/config/gcn/atomic.c \
 	   $(srcdir)/config/gcn/lib2-divmod.c \
 	   $(srcdir)/config/gcn/lib2-divmod-di.c \
+	   $(srcdir)/config/gcn/lib2-vec_divmod.c \
+	   $(srcdir)/config/gcn/lib2-vec_divmod-qi.c \
+	   $(srcdir)/config/gcn/lib2-vec_divmod-hi.c \
+	   $(srcdir)/config/gcn/lib2-vec_divmod-di.c \
 	   $(srcdir)/config/gcn/lib2-bswapti2.c \
 	   $(srcdir)/config/gcn/unwind-gcn.c