> Do you really need a copy of the address register? Couldn't you just do a
> src = adjust_address (operands[1], BLKmode, 0);
> You create a paradoxical subreg of the QImode input but vll actually
> uses the whole 32 bit value. Couldn't we end up with uninitialized
> bytes being used as part of the length then? Do we need a zero-extend
> here?
v2 attached with these problems addressed.
Testsuite and bootstrap as before.
Regards
Robin
From 27cc2fa49a0f3fbc2c629028b51e862346392636 Mon Sep 17 00:00:00 2001
From: Robin Dapp <rd...@linux.ibm.com>
Date: Mon, 22 Aug 2022 11:05:39 +0200
Subject: [PATCH v2] 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 | 8 +++++
gcc/config/s390/s390.cc | 9 ++++-
gcc/config/s390/vector.md | 35 ++++++++++++++++++
gcc/testsuite/gcc.target/s390/s390.exp | 3 ++
.../s390/vector/partial/s390-vec-length-1.h | 18 ++++++++++
.../s390/vector/partial/s390-vec-length-2.h | 18 ++++++++++
.../s390/vector/partial/s390-vec-length-3.h | 31 ++++++++++++++++
.../s390/vector/partial/s390-vec-length-7.h | 17 +++++++++
.../vector/partial/s390-vec-length-epil-1.c | 13 +++++++
.../vector/partial/s390-vec-length-epil-2.c | 13 +++++++
.../vector/partial/s390-vec-length-epil-3.c | 16 +++++++++
.../vector/partial/s390-vec-length-epil-7.c | 11 ++++++
.../partial/s390-vec-length-epil-run-1.c | 7 ++++
.../partial/s390-vec-length-epil-run-2.c | 7 ++++
.../partial/s390-vec-length-epil-run-3.c | 7 ++++
.../partial/s390-vec-length-epil-run-7.c | 7 ++++
.../vector/partial/s390-vec-length-full-1.c | 12 +++++++
.../vector/partial/s390-vec-length-full-2.c | 12 +++++++
.../vector/partial/s390-vec-length-full-3.c | 13 +++++++
.../vector/partial/s390-vec-length-full-7.c | 14 ++++++++
.../partial/s390-vec-length-full-run-1.c | 7 ++++
.../partial/s390-vec-length-full-run-2.c | 7 ++++
.../partial/s390-vec-length-full-run-3.c | 7 ++++
.../partial/s390-vec-length-full-run-7.c | 7 ++++
.../vector/partial/s390-vec-length-run-1.h | 34 ++++++++++++++++++
.../vector/partial/s390-vec-length-run-2.h | 36 +++++++++++++++++++
.../vector/partial/s390-vec-length-run-3.h | 34 ++++++++++++++++++
.../vector/partial/s390-vec-length-run-7.h | 16 +++++++++
.../vector/partial/s390-vec-length-small.c | 15 ++++++++
.../s390/vector/partial/s390-vec-length.h | 14 ++++++++
.../gcc.target/s390/vector/vec-nopeel-2.c | 2 +-
gcc/testsuite/lib/target-supports.exp | 3 +-
32 files changed, 450 insertions(+), 3 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-1.h
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-2.h
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-3.h
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-7.h
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-1.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-2.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-3.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-7.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-1.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-2.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-3.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-7.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-1.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-2.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-3.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-7.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-1.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-2.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-3.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-7.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-1.h
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-2.h
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-3.h
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-7.h
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-small.c
create mode 100644 gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length.h
diff --git a/gcc/config/s390/predicates.md b/gcc/config/s390/predicates.md
index d5d5a7cc0d35..0c369197fd93 100644
--- a/gcc/config/s390/predicates.md
+++ b/gcc/config/s390/predicates.md
@@ -606,3 +606,11 @@ (define_predicate "subreg_register_operand"
(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)")))
diff --git a/gcc/config/s390/s390.cc b/gcc/config/s390/s390.cc
index b66edf03f473..505de995da87 100644
--- a/gcc/config/s390/s390.cc
+++ b/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"
diff --git a/gcc/config/s390/vector.md b/gcc/config/s390/vector.md
index 08e0b68fbc5f..21bec729efa7 100644
--- a/gcc/config/s390/vector.md
+++ b/gcc/config/s390/vector.md
@@ -2947,6 +2947,41 @@ (define_insn_and_split "*bswap<mode>"
""
[(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
diff --git a/gcc/testsuite/gcc.target/s390/s390.exp b/gcc/testsuite/gcc.target/s390/s390.exp
index 5045b48b61a0..58258492f832 100644
--- a/gcc/testsuite/gcc.target/s390/s390.exp
+++ b/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
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-1.h b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-1.h
new file mode 100644
index 000000000000..5a27c32a6d98
--- /dev/null
+++ b/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)
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-2.h b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-2.h
new file mode 100644
index 000000000000..a9a188c4d16f
--- /dev/null
+++ b/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)
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-3.h b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-3.h
new file mode 100644
index 000000000000..30d7c383d727
--- /dev/null
+++ b/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)
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-7.h b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-7.h
new file mode 100644
index 000000000000..e441bf6ed08b
--- /dev/null
+++ b/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)
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-1.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-1.c
new file mode 100644
index 000000000000..ca844f79f617
--- /dev/null
+++ b/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 } } */
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-2.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-2.c
new file mode 100644
index 000000000000..31850f81c809
--- /dev/null
+++ b/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 } } */
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-3.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-3.c
new file mode 100644
index 000000000000..4e342de331c4
--- /dev/null
+++ b/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 } } */
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-7.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-7.c
new file mode 100644
index 000000000000..c85c93e17d87
--- /dev/null
+++ b/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 } } */
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-1.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-1.c
new file mode 100644
index 000000000000..83d986451cb0
--- /dev/null
+++ b/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"
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-2.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-2.c
new file mode 100644
index 000000000000..8b3b19516bfa
--- /dev/null
+++ b/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"
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-3.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-3.c
new file mode 100644
index 000000000000..f2f94efc14bb
--- /dev/null
+++ b/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"
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-7.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-epil-run-7.c
new file mode 100644
index 000000000000..c1f58c3ee427
--- /dev/null
+++ b/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"
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-1.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-1.c
new file mode 100644
index 000000000000..0ff86e70e48e
--- /dev/null
+++ b/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 } } */
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-2.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-2.c
new file mode 100644
index 000000000000..f47fb8949437
--- /dev/null
+++ b/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 } } */
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-3.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-3.c
new file mode 100644
index 000000000000..086185f461b0
--- /dev/null
+++ b/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 } } */
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-7.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-7.c
new file mode 100644
index 000000000000..23856e1c5fa0
--- /dev/null
+++ b/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 } } */
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-1.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-1.c
new file mode 100644
index 000000000000..b064706c63ed
--- /dev/null
+++ b/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"
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-2.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-2.c
new file mode 100644
index 000000000000..c9a4ae8f3a6a
--- /dev/null
+++ b/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"
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-3.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-3.c
new file mode 100644
index 000000000000..b422119b7ece
--- /dev/null
+++ b/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"
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-7.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-full-run-7.c
new file mode 100644
index 000000000000..dea7a0acec74
--- /dev/null
+++ b/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"
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-1.h b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-1.h
new file mode 100644
index 000000000000..ba9e113dc640
--- /dev/null
+++ b/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;
+}
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-2.h b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-2.h
new file mode 100644
index 000000000000..87582cefe7de
--- /dev/null
+++ b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-2.h
@@ -0,0 +1,36 @@
+#include "s390-vec-length-2.h"
+
+#define decl(TYPE) \
+ TYPE a_##TYPE[N]; \
+ TYPE b_##TYPE[N]; \
+ TYPE c_##TYPE[N];
+
+#define N1 195
+
+#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 (N1); \
+ for (i = 0; i < N1; 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;
+}
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-3.h b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-3.h
new file mode 100644
index 000000000000..eef57f41dbb1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-3.h
@@ -0,0 +1,34 @@
+#include "s390-vec-length-3.h"
+
+#define decl(TYPE) \
+ TYPE a_##TYPE[N_##TYPE]; \
+ TYPE b_##TYPE[N_##TYPE]; \
+ TYPE c_##TYPE[N_##TYPE];
+
+#define run(TYPE) \
+ { \
+ unsigned int i = 0; \
+ for (i = 0; i < N_##TYPE; i++) \
+ { \
+ a_##TYPE[i] = i * 2 + 1; \
+ b_##TYPE[i] = i % 2 - 2; \
+ } \
+ test##TYPE (); \
+ for (i = 0; i < N_##TYPE; 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;
+}
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-7.h b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-7.h
new file mode 100644
index 000000000000..39af9a64714d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-run-7.h
@@ -0,0 +1,16 @@
+#include "s390-vec-length-7.h"
+
+#define run(TYPE) \
+ { \
+ unsigned int i = 0; \
+ test_npeel_##TYPE(); \
+ for (int i = 0; i < N; ++i) { \
+ if (x_##TYPE[i] != (i < START || i >= END ? 0 : (i - START))) \
+ __builtin_abort(); \
+ } \
+ }
+
+int main() {
+ TEST_ALL(run)
+ return 0;
+}
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-small.c b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-small.c
new file mode 100644
index 000000000000..ed953c876e4b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length-small.c
@@ -0,0 +1,15 @@
+/* { dg-do compile { target { lp64 && s390_vx } } } */
+/* { dg-options "-mzarch -march=native -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+
+/* { dg-additional-options "--param=min-vect-loop-bound=0 --param=vect-partial-vector-usage=2 -fno-trapping-math" } */
+
+#define SZ 333
+
+void foo (char *restrict a, char *restrict b, char *restrict c, int n)
+{
+#pragma gcc unroll 0
+ for (int i = 0; i < 17; i++)
+ c[i] = a[i] + b[i];
+/* { dg-final { scan-assembler-times "lhi\t%r\[0-9\]*,0\n" 1 } } */
+}
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length.h b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length.h
new file mode 100644
index 000000000000..83418b0b6418
--- /dev/null
+++ b/gcc/testsuite/gcc.target/s390/vector/partial/s390-vec-length.h
@@ -0,0 +1,14 @@
+#include <stdint.h>
+
+#define TEST_ALL(T) \
+ T (int8_t) \
+ T (uint8_t) \
+ T (int16_t) \
+ T (uint16_t) \
+ T (int32_t) \
+ T (uint32_t) \
+ T (int64_t) \
+ T (uint64_t) \
+ T (float) \
+ T (double)
+
diff --git a/gcc/testsuite/gcc.target/s390/vector/vec-nopeel-2.c b/gcc/testsuite/gcc.target/s390/vector/vec-nopeel-2.c
index 9b67793e6f4f..03bf5ee60f10 100644
--- a/gcc/testsuite/gcc.target/s390/vector/vec-nopeel-2.c
+++ b/gcc/testsuite/gcc.target/s390/vector/vec-nopeel-2.c
@@ -9,4 +9,4 @@ void foo(int *restrict a, int *restrict b, unsigned int n)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" } } */
+/* { dg-final { scan-tree-dump "Vectorizing an unaligned access" "vect" } } */
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index 59be4fc9dc99..b45bcffbb059 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -7774,7 +7774,8 @@ proc check_effective_target_vect_fully_masked { } {
# @code{len_store} optabs.
proc check_effective_target_vect_len_load_store { } {
- return [check_effective_target_has_arch_pwr9]
+ return [expr { [check_effective_target_has_arch_pwr9]
+ || [check_effective_target_s390_vx] }]
}
# Return the value of parameter vect-partial-vector-usage specified for
--
2.39.1
