@@ -676,6 +676,190 @@
[(set_attr "type" "vimuladd")
(set_attr "mode" "<MODE>")])
+;; -------------------------------------------------------------------------
+;; ---- [FP] VFMACC and VFMADD
+;; -------------------------------------------------------------------------
+;; Includes:
+;; - vfmacc
+;; - vfmadd
+;; -------------------------------------------------------------------------
+
+(define_expand "fma<mode>4"
+ [(parallel
+ [(set (match_operand:VF_AUTO 0 "register_operand")
+ (fma:VF_AUTO
+ (match_operand:VF_AUTO 1 "register_operand")
+ (match_operand:VF_AUTO 2 "register_operand")
+ (match_operand:VF_AUTO 3 "register_operand")))
+ (clobber (match_dup 4))])]
+ "TARGET_VECTOR"
+ {
+ operands[4] = gen_reg_rtx (Pmode);
+ })
+
+(define_insn_and_split "*fma<VF_AUTO:mode><P:mode>"
+ [(set (match_operand:VF_AUTO 0 "register_operand" "=vr, vr, ?&vr")
+ (fma:VF_AUTO
+ (match_operand:VF_AUTO 1 "register_operand" " %0, vr, vr")
+ (match_operand:VF_AUTO 2 "register_operand" " vr, vr, vr")
+ (match_operand:VF_AUTO 3 "register_operand" " vr, 0, vr")))
+ (clobber (match_operand:P 4 "register_operand" "=r,r,r"))]
+ "TARGET_VECTOR"
+ "#"
+ "&& reload_completed"
+ [(const_int 0)]
+ {
+ riscv_vector::emit_vlmax_vsetvl (<VF_AUTO:MODE>mode, operands[4]);
+ if (which_alternative == 2)
+ emit_insn (gen_rtx_SET (operands[0], operands[3]));
+ rtx ops[] = {operands[0], operands[1], operands[2], operands[3], operands[0]};
+ riscv_vector::emit_vlmax_fp_ternary_insn (code_for_pred_mul (PLUS, <VF_AUTO:MODE>mode),
+ riscv_vector::RVV_TERNOP, ops, operands[4]);
+ DONE;
+ }
+ [(set_attr "type" "vfmuladd")
+ (set_attr "mode" "<VF_AUTO:MODE>")])
+
+;; -------------------------------------------------------------------------
+;; ---- [FP] VFNMSAC and VFNMSUB
+;; -------------------------------------------------------------------------
+;; Includes:
+;; - vfnmsac
+;; - vfnmsub
+;; -------------------------------------------------------------------------
+
+(define_expand "fnma<mode>4"
+ [(parallel
+ [(set (match_operand:VF_AUTO 0 "register_operand")
+ (fma:VF_AUTO
+ (neg:VF_AUTO
+ (match_operand:VF_AUTO 1 "register_operand"))
+ (match_operand:VF_AUTO 2 "register_operand")
+ (match_operand:VF_AUTO 3 "register_operand")))
+ (clobber (match_dup 4))])]
+ "TARGET_VECTOR"
+ {
+ operands[4] = gen_reg_rtx (Pmode);
+ })
+
+(define_insn_and_split "*fnma<VF_AUTO:mode><P:mode>"
+ [(set (match_operand:VF_AUTO 0 "register_operand" "=vr, vr, ?&vr")
+ (fma:VF_AUTO
+ (neg:VF_AUTO
+ (match_operand:VF_AUTO 1 "register_operand" " %0, vr, vr"))
+ (match_operand:VF_AUTO 2 "register_operand" " vr, vr, vr")
+ (match_operand:VF_AUTO 3 "register_operand" " vr, 0, vr")))
+ (clobber (match_operand:P 4 "register_operand" "=r,r,r"))]
+ "TARGET_VECTOR"
+ "#"
+ "&& reload_completed"
+ [(const_int 0)]
+ {
+ riscv_vector::emit_vlmax_vsetvl (<VF_AUTO:MODE>mode, operands[4]);
+ if (which_alternative == 2)
+ emit_insn (gen_rtx_SET (operands[0], operands[3]));
+ rtx ops[] = {operands[0], operands[1], operands[2], operands[3], operands[0]};
+ riscv_vector::emit_vlmax_fp_ternary_insn (code_for_pred_mul_neg (PLUS, <VF_AUTO:MODE>mode),
+ riscv_vector::RVV_TERNOP, ops, operands[4]);
+ DONE;
+ }
+ [(set_attr "type" "vfmuladd")
+ (set_attr "mode" "<VF_AUTO:MODE>")])
+
+;; -------------------------------------------------------------------------
+;; ---- [FP] VFMSAC and VFMSUB
+;; -------------------------------------------------------------------------
+;; Includes:
+;; - vfmsac
+;; - vfmsub
+;; -------------------------------------------------------------------------
+
+(define_expand "fms<mode>4"
+ [(parallel
+ [(set (match_operand:VF_AUTO 0 "register_operand")
+ (fma:VF_AUTO
+ (match_operand:VF_AUTO 1 "register_operand")
+ (match_operand:VF_AUTO 2 "register_operand")
+ (neg:VF_AUTO
+ (match_operand:VF_AUTO 3 "register_operand"))))
+ (clobber (match_dup 4))])]
+ "TARGET_VECTOR"
+ {
+ operands[4] = gen_reg_rtx (Pmode);
+ })
+
+(define_insn_and_split "*fms<VF_AUTO:mode><P:mode>"
+ [(set (match_operand:VF_AUTO 0 "register_operand" "=vr, vr, ?&vr")
+ (fma:VF_AUTO
+ (match_operand:VF_AUTO 1 "register_operand" " %0, vr, vr")
+ (match_operand:VF_AUTO 2 "register_operand" " vr, vr, vr")
+ (neg:VF_AUTO
+ (match_operand:VF_AUTO 3 "register_operand" " vr, 0, vr"))))
+ (clobber (match_operand:P 4 "register_operand" "=r,r,r"))]
+ "TARGET_VECTOR"
+ "#"
+ "&& reload_completed"
+ [(const_int 0)]
+ {
+ riscv_vector::emit_vlmax_vsetvl (<VF_AUTO:MODE>mode, operands[4]);
+ if (which_alternative == 2)
+ emit_insn (gen_rtx_SET (operands[0], operands[3]));
+ rtx ops[] = {operands[0], operands[1], operands[2], operands[3], operands[0]};
+ riscv_vector::emit_vlmax_fp_ternary_insn (code_for_pred_mul (MINUS, <VF_AUTO:MODE>mode),
+ riscv_vector::RVV_TERNOP, ops, operands[4]);
+ DONE;
+ }
+ [(set_attr "type" "vfmuladd")
+ (set_attr "mode" "<VF_AUTO:MODE>")])
+
+;; -------------------------------------------------------------------------
+;; ---- [FP] VFMSAC and VFMSUB
+;; -------------------------------------------------------------------------
+;; Includes:
+;; - vfmsac
+;; - vfmsub
+;; -------------------------------------------------------------------------
+
+(define_expand "fnms<mode>4"
+ [(parallel
+ [(set (match_operand:VF_AUTO 0 "register_operand")
+ (fma:VF_AUTO
+ (neg:VF_AUTO
+ (match_operand:VF_AUTO 1 "register_operand"))
+ (match_operand:VF_AUTO 2 "register_operand")
+ (neg:VF_AUTO
+ (match_operand:VF_AUTO 3 "register_operand"))))
+ (clobber (match_dup 4))])]
+ "TARGET_VECTOR"
+ {
+ operands[4] = gen_reg_rtx (Pmode);
+ })
+
+(define_insn_and_split "*fnms<VF_AUTO:mode><P:mode>"
+ [(set (match_operand:VF_AUTO 0 "register_operand" "=vr, vr, ?&vr")
+ (fma:VF_AUTO
+ (neg:VF_AUTO
+ (match_operand:VF_AUTO 1 "register_operand" " %0, vr, vr"))
+ (match_operand:VF_AUTO 2 "register_operand" " vr, vr, vr")
+ (neg:VF_AUTO
+ (match_operand:VF_AUTO 3 "register_operand" " vr, 0, vr"))))
+ (clobber (match_operand:P 4 "register_operand" "=r,r,r"))]
+ "TARGET_VECTOR"
+ "#"
+ "&& reload_completed"
+ [(const_int 0)]
+ {
+ riscv_vector::emit_vlmax_vsetvl (<VF_AUTO:MODE>mode, operands[4]);
+ if (which_alternative == 2)
+ emit_insn (gen_rtx_SET (operands[0], operands[3]));
+ rtx ops[] = {operands[0], operands[1], operands[2], operands[3], operands[0]};
+ riscv_vector::emit_vlmax_fp_ternary_insn (code_for_pred_mul_neg (MINUS, <VF_AUTO:MODE>mode),
+ riscv_vector::RVV_TERNOP, ops, operands[4]);
+ DONE;
+ }
+ [(set_attr "type" "vfmuladd")
+ (set_attr "mode" "<VF_AUTO:MODE>")])
+
;; =========================================================================
;; == SELECT_VL
;; =========================================================================
@@ -187,6 +187,7 @@ void emit_hard_vlmax_vsetvl (machine_mode, rtx);
void emit_vlmax_insn (unsigned, int, rtx *, rtx = 0);
void emit_vlmax_fp_insn (unsigned, int, rtx *, rtx = 0);
void emit_vlmax_ternary_insn (unsigned, int, rtx *, rtx = 0);
+void emit_vlmax_fp_ternary_insn (unsigned, int, rtx *, rtx = 0);
void emit_nonvlmax_insn (unsigned, int, rtx *, rtx);
void emit_vlmax_slide_insn (unsigned, rtx *);
void emit_nonvlmax_slide_tu_insn (unsigned, rtx *, rtx);
@@ -705,19 +705,42 @@ emit_vlmax_ternary_insn (unsigned icode, int op_num, rtx *ops, rtx vl)
{
machine_mode dest_mode = GET_MODE (ops[0]);
machine_mode mask_mode = get_mask_mode (dest_mode).require ();
- /* We have a maximum of 11 operands for RVV instruction patterns according to
- * vector.md. */
- insn_expander<11> e (/*OP_NUM*/ op_num, /*HAS_DEST_P*/ true,
- /*FULLY_UNMASKED_P*/ true,
- /*USE_REAL_MERGE_P*/ true, /*HAS_AVL_P*/ true,
- /*VLMAX_P*/ true,
- /*DEST_MODE*/ dest_mode, /*MASK_MODE*/ mask_mode);
+ insn_expander<RVV_INSN_OPERANDS_MAX> e (/*OP_NUM*/ op_num,
+ /*HAS_DEST_P*/ true,
+ /*FULLY_UNMASKED_P*/ true,
+ /*USE_REAL_MERGE_P*/ true,
+ /*HAS_AVL_P*/ true,
+ /*VLMAX_P*/ true,
+ /*DEST_MODE*/ dest_mode,
+ /*MASK_MODE*/ mask_mode);
e.set_policy (TAIL_ANY);
e.set_policy (MASK_ANY);
e.set_vl (vl);
e.emit_insn ((enum insn_code) icode, ops);
}
+/* This function emits a {VLMAX, TAIL_ANY, MASK_ANY} vsetvli followed by the
+ * ternary operation which always has a real merge operand. */
+void
+emit_vlmax_fp_ternary_insn (unsigned icode, int op_num, rtx *ops, rtx vl)
+{
+ machine_mode dest_mode = GET_MODE (ops[0]);
+ machine_mode mask_mode = get_mask_mode (dest_mode).require ();
+ insn_expander<RVV_INSN_OPERANDS_MAX> e (/*OP_NUM*/ op_num,
+ /*HAS_DEST_P*/ true,
+ /*FULLY_UNMASKED_P*/ true,
+ /*USE_REAL_MERGE_P*/ true,
+ /*HAS_AVL_P*/ true,
+ /*VLMAX_P*/ true,
+ /*DEST_MODE*/ dest_mode,
+ /*MASK_MODE*/ mask_mode);
+ e.set_policy (TAIL_ANY);
+ e.set_policy (MASK_ANY);
+ e.set_rounding_mode (FRM_DYN);
+ e.set_vl (vl);
+ e.emit_insn ((enum insn_code) icode, ops);
+}
+
/* This function emits a {NONVLMAX, TAIL_ANY, MASK_ANY} vsetvli followed by the
* actual operation. */
void
@@ -847,11 +870,13 @@ emit_vlmax_masked_mu_insn (unsigned icode, int op_num, rtx *ops)
{
machine_mode dest_mode = GET_MODE (ops[0]);
machine_mode mask_mode = get_mask_mode (dest_mode).require ();
- insn_expander<11> e (/*OP_NUM*/ op_num, /*HAS_DEST_P*/ true,
- /*FULLY_UNMASKED_P*/ false,
- /*USE_REAL_MERGE_P*/ true,
- /*HAS_AVL_P*/ true,
- /*VLMAX_P*/ true, dest_mode, mask_mode);
+ insn_expander<RVV_INSN_OPERANDS_MAX> e (/*OP_NUM*/ op_num,
+ /*HAS_DEST_P*/ true,
+ /*FULLY_UNMASKED_P*/ false,
+ /*USE_REAL_MERGE_P*/ true,
+ /*HAS_AVL_P*/ true,
+ /*VLMAX_P*/ true, dest_mode,
+ mask_mode);
e.set_policy (TAIL_ANY);
e.set_policy (MASK_UNDISTURBED);
e.emit_insn ((enum insn_code) icode, ops);
@@ -425,14 +425,14 @@
(eq_attr "type" "vldux,vldox,vialu,vshift,viminmax,vimul,vidiv,vsalu,\
viwalu,viwmul,vnshift,vaalu,vsmul,vsshift,\
vnclip,vicmp,vfalu,vfmul,vfminmax,vfdiv,vfwalu,vfwmul,\
- vfsgnj,vfcmp,vfmuladd,vslideup,vslidedown,vislide1up,\
+ vfsgnj,vfcmp,vslideup,vslidedown,vislide1up,\
vislide1down,vfslide1up,vfslide1down,vgather,viwmuladd,vfwmuladd,\
vlsegds,vlsegdux,vlsegdox")
(symbol_ref "INTVAL (operands[8])")
(eq_attr "type" "vstux,vstox,vssegts,vssegtux,vssegtox")
(symbol_ref "INTVAL (operands[5])")
- (eq_attr "type" "vimuladd")
+ (eq_attr "type" "vimuladd,vfmuladd")
(symbol_ref "INTVAL (operands[9])")
(eq_attr "type" "vmsfs,vmidx,vcompress")
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable" } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math" } */
#include <stdint-gcc.h>
@@ -20,9 +20,13 @@
TEST_TYPE (int32_t) \
TEST_TYPE (uint32_t) \
TEST_TYPE (int64_t) \
- TEST_TYPE (uint64_t)
+ TEST_TYPE (uint64_t) \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
TEST_ALL ()
/* { dg-final { scan-assembler-times {\tvmadd\.vv} 8 } } */
+/* { dg-final { scan-assembler-times {\tvfmadd\.vv} 3 } } */
/* { dg-final { scan-assembler-not {\tvmv} } } */
new file mode 100644
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_TYPE(TYPE) \
+ __attribute__ ((noipa)) void ternop_##TYPE (TYPE *__restrict dst, \
+ TYPE *__restrict a, \
+ TYPE *__restrict b, int n) \
+ { \
+ for (int i = 0; i < n; i++) \
+ dst[i] = -(a[i] * b[i]) - dst[i]; \
+ }
+
+#define TEST_ALL() \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
+
+TEST_ALL ()
+
+/* { dg-final { scan-assembler-times {\tvfnmadd\.vv} 3 } } */
+/* { dg-final { scan-assembler-not {\tvmv} } } */
new file mode 100644
@@ -0,0 +1,29 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-schedule-insns -ffast-math" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_TYPE(TYPE) \
+ __attribute__ ((noipa)) void ternop_##TYPE (TYPE *__restrict dest1, \
+ TYPE *__restrict dest2, \
+ TYPE *__restrict dest3, \
+ TYPE *__restrict src1, \
+ TYPE *__restrict src2, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ { \
+ dest1[i] = -(src1[i] * src2[i]) - dest1[i]; \
+ dest2[i] = src1[i] * dest1[i] - dest2[i]; \
+ dest3[i] = src2[i] * dest2[i] - dest3[i]; \
+ } \
+ }
+
+#define TEST_ALL() \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
+
+TEST_ALL ()
+
+/* { dg-final { scan-assembler-times {\tvfnmacc\.vv} 3 } } */
+/* { dg-final { scan-assembler-not {\tvmv} } } */
new file mode 100644
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_TYPE(TYPE) \
+ __attribute__ ((noipa)) void ternop_##TYPE (TYPE *__restrict dest1, \
+ TYPE *__restrict dest2, \
+ TYPE *__restrict dest3, \
+ TYPE *__restrict src1, \
+ TYPE *__restrict src2, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ { \
+ dest1[i] = -(src1[i] * src2[i]) - dest2[i]; \
+ dest2[i] = src1[i] * dest1[i] - dest2[i]; \
+ dest3[i] = src2[i] * dest2[i] - dest3[i]; \
+ } \
+ }
+
+#define TEST_ALL() \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
+
+TEST_ALL ()
+
+/* { dg-final { scan-assembler-times {\tvmv} 3 } } */
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-schedule-insns" } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-schedule-insns -ffast-math" } */
#include <stdint-gcc.h>
@@ -26,9 +26,13 @@
TEST_TYPE (int32_t) \
TEST_TYPE (uint32_t) \
TEST_TYPE (int64_t) \
- TEST_TYPE (uint64_t)
+ TEST_TYPE (uint64_t) \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
TEST_ALL ()
/* { dg-final { scan-assembler-times {\tvmacc\.vv} 8 } } */
+/* { dg-final { scan-assembler-times {\tvfmacc\.vv} 3 } } */
/* { dg-final { scan-assembler-not {\tvmv} } } */
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable" } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math" } */
#include <stdint-gcc.h>
@@ -26,8 +26,11 @@
TEST_TYPE (int32_t) \
TEST_TYPE (uint32_t) \
TEST_TYPE (int64_t) \
- TEST_TYPE (uint64_t)
+ TEST_TYPE (uint64_t) \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
TEST_ALL ()
-/* { dg-final { scan-assembler-times {\tvmv} 8 } } */
+/* { dg-final { scan-assembler-times {\tvmv} 11 } } */
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable" } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math" } */
#include <stdint-gcc.h>
@@ -20,9 +20,13 @@
TEST_TYPE (int32_t) \
TEST_TYPE (uint32_t) \
TEST_TYPE (int64_t) \
- TEST_TYPE (uint64_t)
+ TEST_TYPE (uint64_t) \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
TEST_ALL ()
/* { dg-final { scan-assembler-times {\tvnmsub\.vv} 8 } } */
+/* { dg-final { scan-assembler-times {\tvfnmsub\.vv} 3 } } */
/* { dg-final { scan-assembler-not {\tvmv} } } */
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-schedule-insns" } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-schedule-insns -ffast-math" } */
#include <stdint-gcc.h>
@@ -26,9 +26,13 @@
TEST_TYPE (int32_t) \
TEST_TYPE (uint32_t) \
TEST_TYPE (int64_t) \
- TEST_TYPE (uint64_t)
+ TEST_TYPE (uint64_t) \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
TEST_ALL ()
/* { dg-final { scan-assembler-times {\tvnmsac\.vv} 8 } } */
+/* { dg-final { scan-assembler-times {\tvfnmsac\.vv} 3 } } */
/* { dg-final { scan-assembler-not {\tvmv} } } */
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable" } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math" } */
#include <stdint-gcc.h>
@@ -26,8 +26,11 @@
TEST_TYPE (int32_t) \
TEST_TYPE (uint32_t) \
TEST_TYPE (int64_t) \
- TEST_TYPE (uint64_t)
+ TEST_TYPE (uint64_t) \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
TEST_ALL ()
-/* { dg-final { scan-assembler-times {\tvmv} 8 } } */
+/* { dg-final { scan-assembler-times {\tvmv} 11 } } */
new file mode 100644
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_TYPE(TYPE) \
+ __attribute__ ((noipa)) void ternop_##TYPE (TYPE *__restrict dst, \
+ TYPE *__restrict a, \
+ TYPE *__restrict b, int n) \
+ { \
+ for (int i = 0; i < n; i++) \
+ dst[i] = a[i] * b[i] - dst[i]; \
+ }
+
+#define TEST_ALL() \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
+
+TEST_ALL ()
+
+/* { dg-final { scan-assembler-times {\tvfmsub\.vv} 3 } } */
+/* { dg-final { scan-assembler-not {\tvmv} } } */
new file mode 100644
@@ -0,0 +1,29 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-schedule-insns -ffast-math" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_TYPE(TYPE) \
+ __attribute__ ((noipa)) void ternop_##TYPE (TYPE *__restrict dest1, \
+ TYPE *__restrict dest2, \
+ TYPE *__restrict dest3, \
+ TYPE *__restrict src1, \
+ TYPE *__restrict src2, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ { \
+ dest1[i] = src1[i] * src2[i] - dest1[i]; \
+ dest2[i] = src1[i] * dest1[i] - dest2[i]; \
+ dest3[i] = src2[i] * dest2[i] - dest3[i]; \
+ } \
+ }
+
+#define TEST_ALL() \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
+
+TEST_ALL ()
+
+/* { dg-final { scan-assembler-times {\tvfmsac\.vv} 3 } } */
+/* { dg-final { scan-assembler-not {\tvmv} } } */
new file mode 100644
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_TYPE(TYPE) \
+ __attribute__ ((noipa)) void ternop_##TYPE (TYPE *__restrict dest1, \
+ TYPE *__restrict dest2, \
+ TYPE *__restrict dest3, \
+ TYPE *__restrict src1, \
+ TYPE *__restrict src2, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ { \
+ dest1[i] = src1[i] * src2[i] - dest2[i]; \
+ dest2[i] = src1[i] * dest1[i] - dest2[i]; \
+ dest3[i] = src2[i] * dest2[i] - dest3[i]; \
+ } \
+ }
+
+#define TEST_ALL() \
+ TEST_TYPE (_Float16) \
+ TEST_TYPE (float) \
+ TEST_TYPE (double)
+
+TEST_ALL ()
+
+/* { dg-final { scan-assembler-times {\tvmv} 3 } } */
@@ -1,5 +1,5 @@
/* { dg-do run { target { riscv_vector } } } */
-/* { dg-additional-options "--param=riscv-autovec-preference=scalable" } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
#include "ternop-1.c"
@@ -80,5 +80,15 @@ int __attribute__ ((optimize (0))) main ()
TEST_LOOP (int64_t, 795)
TEST_LOOP (uint64_t, 795)
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
return 0;
}
new file mode 100644
@@ -0,0 +1,40 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-10.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 3 - i; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array1_##NUM, array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ if (array3_##NUM[i] \
+ != (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) - array4_##NUM[i])) \
+ __builtin_abort (); \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,60 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-11.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) - array6_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] - array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] - array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,60 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-12.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) - array7_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] - array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] - array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
+ return 0;
+}
@@ -1,5 +1,5 @@
/* { dg-do run { target { riscv_vector } } } */
-/* { dg-additional-options "--param=riscv-autovec-preference=scalable" } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
#include "ternop-2.c"
@@ -100,5 +100,15 @@ int __attribute__ ((optimize (0))) main ()
TEST_LOOP (int64_t, 795)
TEST_LOOP (uint64_t, 795)
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
return 0;
}
@@ -1,5 +1,5 @@
/* { dg-do run { target { riscv_vector } } } */
-/* { dg-additional-options "--param=riscv-autovec-preference=scalable" } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
#include "ternop-3.c"
@@ -100,5 +100,15 @@ int __attribute__ ((optimize (0))) main ()
TEST_LOOP (int64_t, 795)
TEST_LOOP (uint64_t, 795)
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
return 0;
}
@@ -1,5 +1,5 @@
/* { dg-do run { target { riscv_vector } } } */
-/* { dg-additional-options "--param=riscv-autovec-preference=scalable" } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
#include "ternop-4.c"
@@ -80,5 +80,15 @@ int __attribute__ ((optimize (0))) main ()
TEST_LOOP (int64_t, 795)
TEST_LOOP (uint64_t, 795)
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
return 0;
}
@@ -1,5 +1,5 @@
/* { dg-do run { target { riscv_vector } } } */
-/* { dg-additional-options "--param=riscv-autovec-preference=scalable" } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
#include "ternop-5.c"
@@ -100,5 +100,15 @@ int __attribute__ ((optimize (0))) main ()
TEST_LOOP (int64_t, 795)
TEST_LOOP (uint64_t, 795)
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
return 0;
}
@@ -1,5 +1,5 @@
/* { dg-do run { target { riscv_vector } } } */
-/* { dg-additional-options "--param=riscv-autovec-preference=scalable" } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
#include "ternop-6.c"
@@ -100,5 +100,15 @@ int __attribute__ ((optimize (0))) main ()
TEST_LOOP (int64_t, 795)
TEST_LOOP (uint64_t, 795)
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
return 0;
}
new file mode 100644
@@ -0,0 +1,40 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-7.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 3 - i; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array1_##NUM, array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ if (array3_##NUM[i] \
+ != (TYPE) (array1_##NUM[i] * array2_##NUM[i] - array4_##NUM[i])) \
+ __builtin_abort (); \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,60 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-8.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array2_##NUM[i] - array6_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] - array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] - array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,60 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-9.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array2_##NUM[i] - array7_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] - array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] - array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (float, 7)
+ TEST_LOOP (double, 7)
+ TEST_LOOP (float, 16)
+ TEST_LOOP (double, 16)
+ TEST_LOOP (float, 77)
+ TEST_LOOP (double, 77)
+ TEST_LOOP (float, 128)
+ TEST_LOOP (double, 128)
+ TEST_LOOP (float, 795)
+ TEST_LOOP (double, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,35 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-1.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 3 - i; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array1_##NUM, array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ if (array3_##NUM[i] \
+ != (TYPE) (array1_##NUM[i] * array2_##NUM[i] + array4_##NUM[i])) \
+ __builtin_abort (); \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,35 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-10.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 3 - i; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array1_##NUM, array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ if (array3_##NUM[i] \
+ != (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) - array4_##NUM[i])) \
+ __builtin_abort (); \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,55 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-11.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) - array6_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] - array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] - array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,55 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-12.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) - array7_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] - array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] - array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,55 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-2.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array2_##NUM[i] + array6_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] + array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] + array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,55 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-3.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array2_##NUM[i] + array7_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] + array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] + array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,35 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-4.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 3 - i; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array1_##NUM, array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ if (array3_##NUM[i] \
+ != (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) + array4_##NUM[i])) \
+ __builtin_abort (); \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,55 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-5.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) + array6_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] + array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] + array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,55 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-6.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) + array7_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] + array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] + array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,35 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-7.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 3 - i; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array1_##NUM, array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ if (array3_##NUM[i] \
+ != (TYPE) (array1_##NUM[i] * array2_##NUM[i] - array4_##NUM[i])) \
+ __builtin_abort (); \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,55 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-8.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array2_##NUM[i] - array6_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] - array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] - array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,55 @@
+/* { dg-do run { target { riscv_vector && riscv_zvfh_hw } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math" } */
+
+#include "ternop-9.c"
+
+#define TEST_LOOP(TYPE, NUM) \
+ { \
+ TYPE array1_##NUM[NUM] = {}; \
+ TYPE array2_##NUM[NUM] = {}; \
+ TYPE array3_##NUM[NUM] = {}; \
+ TYPE array4_##NUM[NUM] = {}; \
+ TYPE array5_##NUM[NUM] = {}; \
+ TYPE array6_##NUM[NUM] = {}; \
+ TYPE array7_##NUM[NUM] = {}; \
+ TYPE array8_##NUM[NUM] = {}; \
+ for (int i = 0; i < NUM; ++i) \
+ { \
+ array1_##NUM[i] = (i & 1) + 5; \
+ array2_##NUM[i] = i - NUM / 3; \
+ array3_##NUM[i] = NUM - NUM / 3 - i; \
+ array6_##NUM[i] = NUM - NUM / 3 - i; \
+ array4_##NUM[i] = NUM - NUM / 2 + i; \
+ array7_##NUM[i] = NUM - NUM / 2 + i; \
+ array5_##NUM[i] = NUM + i * 7; \
+ array8_##NUM[i] = NUM + i * 7; \
+ asm volatile("" ::: "memory"); \
+ } \
+ ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM, \
+ array2_##NUM, NUM); \
+ for (int i = 0; i < NUM; i++) \
+ { \
+ array6_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array2_##NUM[i] - array7_##NUM[i]); \
+ if (array3_##NUM[i] != array6_##NUM[i]) \
+ __builtin_abort (); \
+ array7_##NUM[i] \
+ = (TYPE) (array1_##NUM[i] * array6_##NUM[i] - array7_##NUM[i]); \
+ if (array4_##NUM[i] != array7_##NUM[i]) \
+ __builtin_abort (); \
+ array8_##NUM[i] \
+ = (TYPE) (array2_##NUM[i] * array7_##NUM[i] - array8_##NUM[i]); \
+ if (array5_##NUM[i] != array8_##NUM[i]) \
+ __builtin_abort (); \
+ } \
+ }
+
+int __attribute__ ((optimize (0))) main ()
+{
+ TEST_LOOP (_Float16, 7)
+ TEST_LOOP (_Float16, 16)
+ TEST_LOOP (_Float16, 77)
+ TEST_LOOP (_Float16, 128)
+ TEST_LOOP (_Float16, 795)
+ return 0;
+}