The .SAT_ADD has 2 operand, when one of the operand may be INTEGER_CST.
For example _1 = .SAT_ADD (_2, 9) comes from below sample code.
Form 3:
#define DEF_VEC_SAT_U_ADD_IMM_FMT_3(T, IMM) \
T __attribute__((noinline)) \
vec_sat_u_add_imm##IMM##_##T##_fmt_3 (T *out, T *in, unsigned limit) \
{ \
unsigned i; \
T ret; \
for (i = 0; i < limit; i++) \
{ \
out[i] = __builtin_add_overflow (in[i], IMM, &ret) ? -1 : ret; \
} \
}
DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint64_t, 9)
It will fail to vectorize as the vectorizable_call will check the
operands is type_compatiable but the imm will be (const_int 9) with
the SImode, which is different from _2 (DImode). Aka:
uint64_t _1;
uint64_t _2;
_1 = .SAT_ADD (_2, 9);
This patch would like to reconcile the imm operand to the operand type
mode of _2 by fold_convert to make the vectorizable_call happy.
The below test suites are passed for this patch:
1. The rv64gcv fully regression tests.
2. The x86 bootstrap tests.
3. The x86 fully regression tests.
gcc/ChangeLog:
* tree-vect-patterns.cc (vect_recog_sat_add_pattern): Add fold
convert for const_int to the type of operand 0.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/vec_sat_arith.h: Add test helper macros.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-1.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-10.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-11.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-12.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-13.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-14.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-15.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-2.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-3.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-4.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-5.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-6.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-7.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-8.c: New test.
* gcc.target/riscv/rvv/autovec/binop/vec_sat_u_add_imm_reconcile-9.c: New test.
Signed-off-by: Pan Li <pan2.li@intel.com>
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint8_t, 9u)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_ADD " 2 "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint32_t, 4294967205u)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_ADD " 2 "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint32_t, 4294967495ll)
+
+/* { dg-final { scan-rtl-dump-not ".SAT_ADD " "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint32_t, 9294967495ull)
+
+/* { dg-final { scan-rtl-dump-not ".SAT_ADD " "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint64_t, 119u)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_ADD " 2 "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint64_t, 18446744073709551615ull)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_ADD " 2 "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint64_t, 9223372036854775807ull)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_ADD " 2 "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint8_t, 219)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_ADD " 2 "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint8_t, 299)
+
+/* { dg-final { scan-rtl-dump-not ".SAT_ADD " "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint8_t, 301u)
+
+/* { dg-final { scan-rtl-dump-not ".SAT_ADD " "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint16_t, 9u)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_ADD " 2 "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint16_t, 65530)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_ADD " 2 "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint16_t, 65559)
+
+/* { dg-final { scan-rtl-dump-not ".SAT_ADD " "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint16_t, 75559u)
+
+/* { dg-final { scan-rtl-dump-not ".SAT_ADD " "expand" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fdump-rtl-expand-details" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../vec_sat_arith.h"
+
+DEF_VEC_SAT_U_ADD_IMM_FMT_3(uint32_t, 911u)
+
+/* { dg-final { scan-rtl-dump-times ".SAT_ADD " 2 "expand" } } */
#define DEF_VEC_SAT_U_ADD_IMM_FMT_2_WRAP(T, IMM) \
DEF_VEC_SAT_U_ADD_IMM_FMT_2(T, IMM)
+#define DEF_VEC_SAT_U_ADD_IMM_FMT_3(T, IMM) \
+T __attribute__((noinline)) \
+vec_sat_u_add_imm##IMM##_##T##_fmt_3 (T *out, T *in, unsigned limit) \
+{ \
+ unsigned i; \
+ T ret; \
+ for (i = 0; i < limit; i++) \
+ { \
+ out[i] = __builtin_add_overflow (in[i], IMM, &ret) ? -1 : ret; \
+ } \
+}
+#define DEF_VEC_SAT_U_ADD_IMM_FMT_3_WRAP(T, IMM) \
+ DEF_VEC_SAT_U_ADD_IMM_FMT_3(T, IMM)
+
#define RUN_VEC_SAT_U_ADD_IMM_FMT_1(T, out, op_1, expect, IMM, N) \
vec_sat_u_add_imm##IMM##_##T##_fmt_1(out, op_1, N); \
VALIDATE_RESULT (out, expect, N)
#define RUN_VEC_SAT_U_ADD_IMM_FMT_2_WRAP(T, out, op_1, expect, IMM, N) \
RUN_VEC_SAT_U_ADD_IMM_FMT_2(T, out, op_1, expect, IMM, N)
+#define RUN_VEC_SAT_U_ADD_IMM_FMT_3(T, out, op_1, expect, IMM, N) \
+ vec_sat_u_add_imm##IMM##_##T##_fmt_3(out, op_1, N); \
+ VALIDATE_RESULT (out, expect, N)
+#define RUN_VEC_SAT_U_ADD_IMM_FMT_3_WRAP(T, out, op_1, expect, IMM, N) \
+ RUN_VEC_SAT_U_ADD_IMM_FMT_3(T, out, op_1, expect, IMM, N)
+
/******************************************************************************/
/* Saturation Sub (Unsigned and Signed) */
/******************************************************************************/
if (gimple_unsigned_integer_sat_add (lhs, ops, NULL))
{
+ if (TREE_CODE (ops[1]) == INTEGER_CST)
+ ops[1] = fold_convert (TREE_TYPE (ops[0]), ops[1]);
+
gimple *stmt = vect_recog_build_binary_gimple_stmt (vinfo, stmt_vinfo,
IFN_SAT_ADD, type_out,
lhs, ops[0], ops[1]);