s390: Add LEN_LOAD/LEN_STORE support.

This patch adds LEN_LOAD/LEN_STORE support for z13 and newer.
It defines a bias value of -1 and implements the LEN_LOAD and LEN_STORE
optabs.

Add vll/vstl testcases adapted from Power.

Also change expectations for SLP testcases with more than one rgroup.

gcc/ChangeLog:

	* config/s390/predicates.md (vll_bias_operand): Add -1 bias.
	* config/s390/s390.cc (s390_option_override_internal): Make
	partial vector usage the default from z13 on.
	* config/s390/vector.md (len_load_v16qi): Add.
	(len_store_v16qi): Add.

gcc/testsuite/ChangeLog:

	* gcc.target/s390/s390.exp: Add partial subdirectory.
	* gcc.target/s390/vector/vec-nopeel-2.c: Change test
	expectation.
	* lib/target-supports.exp: Add s390.
	* gcc.target/s390/vector/partial/s390-vec-length-1.h: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-2.h: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-3.h: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-7.h: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-epil-1.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-epil-2.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-epil-3.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-epil-7.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-epil-run-1.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-epil-run-2.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-epil-run-3.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-epil-run-7.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-full-1.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-full-2.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-full-3.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-full-7.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-full-run-1.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-full-run-2.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-full-run-3.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-full-run-7.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-run-1.h: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-run-2.h: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-run-3.h: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-run-7.h: New test.
	* gcc.target/s390/vector/partial/s390-vec-length-small.c: New test.
	* gcc.target/s390/vector/partial/s390-vec-length.h: New test.

gcc/config/s390/predicates.md

@@ -606,3 +606,11 @@
        (and (match_code "reg")
 	    (match_test "reload_completed || reload_in_progress")
 	    (match_test "register_operand (op, GET_MODE (op))"))))
+
+; Bias value for LEN_LOAD and LEN_STORE.  The bias will be added to the
+; length (in bytes for s390) to be loaded.  vll/vstl expect the lowest byte
+; to load while LEN_LOAD/LEN_STORE use the actual length in bytes.  This implies
+; that we cannot load a length of 0.
+(define_predicate "vll_bias_operand"
+  (and (match_code "const_int")
+       (match_test "op == CONSTM1_RTX (QImode)")))

gcc/config/s390/s390.cc

@@ -15857,6 +15857,14 @@ s390_option_override_internal (struct gcc_options *opts,
 
   /* Use the alternative scheduling-pressure algorithm by default.  */
   SET_OPTION_IF_UNSET (opts, opts_set, param_sched_pressure_algorithm, 2);
+
+  /* Allow simple vector masking using vll/vstl for epilogues.  */
+  if (TARGET_Z13)
+    SET_OPTION_IF_UNSET (opts, opts_set, param_vect_partial_vector_usage, 1);
+  else
+    SET_OPTION_IF_UNSET (opts, opts_set, param_vect_partial_vector_usage, 0);
+
+  /* Do not vectorize loops with a low trip count for now.  */
   SET_OPTION_IF_UNSET (opts, opts_set, param_min_vect_loop_bound, 2);
 
   /* Set the default alignment.  */
@@ -17825,7 +17833,6 @@ s390_vectorize_vec_perm_const (machine_mode vmode, machine_mode op_mode,
 #undef TARGET_VECTORIZE_VEC_PERM_CONST
 #define TARGET_VECTORIZE_VEC_PERM_CONST s390_vectorize_vec_perm_const
 
-
 struct gcc_target targetm = TARGET_INITIALIZER;
 
 #include "gt-s390.h"

gcc/config/s390/vector.md

@@ -2947,6 +2947,41 @@
   ""
   [(set_attr "op_type"      "*,VRX,VRX")])
 
+;
+; Implement len_load/len_store optabs with vll/vstl.
+(define_expand "len_load_v16qi"
+  [(match_operand:V16QI 0 "register_operand")
+   (match_operand:V16QI 1 "memory_operand")
+   (match_operand:QI 2 "register_operand")
+   (match_operand:QI 3 "vll_bias_operand")
+  ]
+  "TARGET_VX && TARGET_64BIT"
+{
+  rtx mem = adjust_address (operands[1], BLKmode, 0);
+
+  rtx len = gen_reg_rtx (SImode);
+  emit_move_insn (len, gen_rtx_ZERO_EXTEND (SImode, operands[2]));
+  emit_insn (gen_vllv16qi (operands[0], len, mem));
+  DONE;
+})
+
+(define_expand "len_store_v16qi"
+  [(match_operand:V16QI 0 "memory_operand")
+   (match_operand:V16QI 1 "register_operand")
+   (match_operand:QI 2 "register_operand")
+   (match_operand:QI 3 "vll_bias_operand")
+  ]
+  "TARGET_VX && TARGET_64BIT"
+{
+  rtx mem = adjust_address (operands[0], BLKmode, 0);
+
+  rtx len = gen_reg_rtx (SImode);
+  emit_move_insn (len, gen_rtx_ZERO_EXTEND (SImode, operands[2]));
+  emit_insn (gen_vstlv16qi (operands[1], len, mem));
+  DONE;
+});;
+
+
 ; reduc_smin
 ; reduc_smax
 ; reduc_umin

gcc/testsuite/gcc.target/s390/s390.exp

@@ -236,6 +236,9 @@ dg-runtest [lsort [prune [glob -nocomplain $srcdir/$subdir/*.{c,S}] \
 dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/*vector*/*.{c,S}]] \
 	"" $DEFAULT_CFLAGS
 
+dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/*vector*/partial/*.{c,S}]] \
+	"" $DEFAULT_CFLAGS
+
 gfortran-dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/*vector*/*.F90]] \
 	"" $DEFAULT_FFLAGS
 

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-1.h

@@ -0,0 +1,18 @@
+#include "s390-vec-length.h"
+
+/* Test the case loop iteration is known.  */
+
+#define N 127
+
+#define test(TYPE)                                                             \
+  extern TYPE a_##TYPE[N];                                                     \
+  extern TYPE b_##TYPE[N];                                                     \
+  extern TYPE c_##TYPE[N];                                                     \
+  void __attribute__ ((noinline, noclone)) test##TYPE ()                       \
+  {                                                                            \
+    unsigned int i = 0;                                                        \
+    for (i = 0; i < N; i++)                                                    \
+      c_##TYPE[i] = a_##TYPE[i] + b_##TYPE[i];                                 \
+  }
+
+TEST_ALL (test)

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-2.h

@@ -0,0 +1,18 @@
+#include "s390-vec-length.h"
+
+/* Test the case loop iteration is unknown.  */
+
+#define N 255
+
+#define test(TYPE)                                                             \
+  extern TYPE a_##TYPE[N];                                                     \
+  extern TYPE b_##TYPE[N];                                                     \
+  extern TYPE c_##TYPE[N];                                                     \
+  void __attribute__ ((noinline, noclone)) test##TYPE (unsigned int n)         \
+  {                                                                            \
+    unsigned int i = 0;                                                        \
+    for (i = 0; i < n; i++)                                                    \
+      c_##TYPE[i] = a_##TYPE[i] + b_##TYPE[i];                                 \
+  }
+
+TEST_ALL (test)

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-3.h

@@ -0,0 +1,31 @@
+#include "s390-vec-length.h"
+
+/* Test the case loop iteration less than VF.  */
+
+/* For char.  */
+#define N_uint8_t 15
+#define N_int8_t 15
+/* For short.  */
+#define N_uint16_t 6
+#define N_int16_t 6
+/* For int/float.  */
+#define N_uint32_t 3
+#define N_int32_t 3
+#define N_float 3
+/* For long/double.  */
+#define N_uint64_t 1
+#define N_int64_t 1
+#define N_double 1
+
+#define test(TYPE)                                                             \
+  extern TYPE a_##TYPE[N_##TYPE];                                              \
+  extern TYPE b_##TYPE[N_##TYPE];                                              \
+  extern TYPE c_##TYPE[N_##TYPE];                                              \
+  void __attribute__ ((noinline, noclone)) test##TYPE ()                       \
+  {                                                                            \
+    unsigned int i = 0;                                                        \
+    for (i = 0; i < N_##TYPE; i++)                                             \
+      c_##TYPE[i] = a_##TYPE[i] + b_##TYPE[i];                                 \
+  }
+
+TEST_ALL (test)

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-7.h

@@ -0,0 +1,17 @@
+#include "s390-vec-length.h"
+
+#define N 64
+#define START 1
+#define END 59
+
+#define test(TYPE)                                                             \
+  TYPE x_##TYPE[N] __attribute__((aligned(16)));                                \
+  void __attribute__((noinline, noclone)) test_npeel_##TYPE() {                \
+    TYPE v = 0;                                                                \
+    for (unsigned int i = START; i < END; i++) {                               \
+      x_##TYPE[i] = v;                                                         \
+      v += 1;                                                                  \
+    }                                                                          \
+  }
+
+TEST_ALL (test)

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-1.c

@@ -0,0 +1,13 @@
+/* { dg-do compile { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=1 --param=min-vect-loop-bound=0" } */
+
+/* Test that we only vectorize the epilogue with vector load/store with length,
+   the main body still uses normal vector load/store.  */
+
+#include "s390-vec-length-1.h"
+
+/* { dg-final { scan-assembler-times {\mvll\M} 14 } } */
+/* { dg-final { scan-assembler-times {\mvstl\M} 7 } } */
+

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-2.c

@@ -0,0 +1,13 @@
+/* { dg-do compile { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=1 --param=min-vect-loop-bound=0" } */
+
+/* Test that we only vectorize the epilogue with vector load/store with length,
+   the main body still uses normal vector load/store.  */
+
+#include "s390-vec-length-2.h"
+
+/* { dg-final { scan-assembler-times {\mvll\M} 20 } } */
+/* { dg-final { scan-assembler-times {\mvstl\M} 10 } } */
+

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-3.c

@@ -0,0 +1,16 @@
+/* { dg-do compile { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=1 --param=min-vect-loop-bound=0" } */
+
+/* Test that we only vectorize the epilogue with vector load/store with length,
+   the main body still uses normal vector load/store.  */
+
+#include "s390-vec-length-3.h"
+
+/* { dg-final { scan-assembler-not   {\mvl\M} } } */
+/* { dg-final { scan-assembler-not   {\mvst\M} } } */
+/* 64bit types get completely unrolled, so only check the others.  */
+/* { dg-final { scan-assembler-times {\mvll\M} 14 } } */
+/* { dg-final { scan-assembler-times {\mvstl\M} 7 } } */
+

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-7.c

@@ -0,0 +1,11 @@
+/* { dg-do compile { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -ffast-math -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=1 --param=min-vect-loop-bound=0" } */
+
+/* Test that we only vectorize the epilogue with vector load/store with length,
+   the main body still uses normal vector load/store.  */
+
+#include "s390-vec-length-7.h"
+
+/* { dg-final { scan-assembler-times {\mvstl\M} 4 } } */

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-1.c

@@ -0,0 +1,7 @@
+/* { dg-do run { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=1" } */
+
+#include "s390-vec-length-run-1.h"
+

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-2.c

@@ -0,0 +1,7 @@
+/* { dg-do run { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=1" } */
+
+#include "s390-vec-length-run-2.h"
+

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-3.c

@@ -0,0 +1,7 @@
+/* { dg-do run { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=1" } */
+
+#include "s390-vec-length-run-3.h"
+

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-7.c

@@ -0,0 +1,7 @@
+/* { dg-do run { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=1" } */
+
+#include "s390-vec-length-run-7.h"
+

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-1.c

@@ -0,0 +1,12 @@
+/* { dg-do compile { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
+
+/* Test that the loop body uses vector load/store with length,
+   there should not be any epilogues.  */
+
+#include "s390-vec-length-1.h"
+
+/* { dg-final { scan-assembler-times {\mvll\M} 20 } } */
+/* { dg-final { scan-assembler-times {\mvstl\M} 10 } } */

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-2.c

@@ -0,0 +1,12 @@
+/* { dg-do compile { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
+
+/* Test that the loop body uses vector load/store with length,
+   there should not be any epilogues.  */
+
+#include "s390-vec-length-2.h"
+
+/* { dg-final { scan-assembler-times {\mvll\M} 20 } } */
+/* { dg-final { scan-assembler-times {\mvstl\M} 10 } } */

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-3.c

@@ -0,0 +1,13 @@
+/* { dg-do compile { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=2 --param=min-vect-loop-bound=0" } */
+
+/* Test that the loop body uses vector load/store with length,
+   there should not be any epilogues.  */
+
+#include "s390-vec-length-3.h"
+
+/* 64bit types get completely unrolled, so only check the others.  */
+/* { dg-final { scan-assembler-times {\mvll\M} 14 } } */
+/* { dg-final { scan-assembler-times {\mvstl\M} 7 } } */

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-7.c

@@ -0,0 +1,14 @@
+/* { dg-do compile { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
+
+/* Test that the loop body uses vector load/store with length,
+   there should not be any epilogues.  */
+
+#include "s390-vec-length-7.h"
+
+/* Each type should have one vstl but we do not currently vectorize the
+   float and double variants and the [u]int64_t ones which do not require
+   partial vectors.  */
+/* { dg-final { scan-assembler-times {\mvstl\M} 6 } } */

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-1.c

@@ -0,0 +1,7 @@
+/* { dg-do run { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
+
+#include "s390-vec-length-run-1.h"
+

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-2.c

@@ -0,0 +1,7 @@
+/* { dg-do run { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
+
+#include "s390-vec-length-run-2.h"
+

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-3.c

@@ -0,0 +1,7 @@
+/* { dg-do run { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
+
+#include "s390-vec-length-run-3.h"
+

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-7.c

@@ -0,0 +1,7 @@
+/* { dg-do run { target { lp64 && s390_vx } } } */
+/* { dg-options "-march=native -O2 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-trapping-math" } */
+
+/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
+
+#include "s390-vec-length-run-7.h"
+

gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-1.h

@@ -0,0 +1,34 @@
+#include "s390-vec-length-1.h"
+
+#define decl(TYPE)                                                             \
+  TYPE a_##TYPE[N];                                                            \
+  TYPE b_##TYPE[N];                                                            \
+  TYPE c_##TYPE[N];
+
+#define run(TYPE)                                                              \
+  {                                                                            \
+    unsigned int i = 0;                                                        \
+    for (i = 0; i < N; i++)                                                    \
+      {                                                                        \
+	a_##TYPE[i] = i * 2 + 1;                                               \
+	b_##TYPE[i] = i % 2 - 2;                                               \
+      }                                                                        \
+    test##TYPE ();                                                             \
+    for (i = 0; i < N; i++)                                                    \
+      {                                                                        \
+	TYPE a1 = i * 2 + 1;                                                   \
+	TYPE b1 = i % 2 - 2;                                                   \
+	TYPE exp_c = a1 + b1;                                                  \
+	if (c_##TYPE[i] != exp_c)                                              \
+	  __builtin_abort ();                                                  \
+      }                                                                        \
+  }
+
+TEST_ALL (decl)
+
+int
+main (void)
+{
+  TEST_ALL (run)
+  return 0;
+}