@@ -747,3 +747,80 @@
riscv_vector::BINARY_OP, operands);
DONE;
})
+
+;; Combine sign_extend/zero_extend(vf2) and vcond_mask
+(define_insn_and_split "*cond_<optab><v_double_trunc><mode>"
+ [(set (match_operand:VWEXTI 0 "register_operand")
+ (if_then_else:VWEXTI
+ (match_operand:<VM> 1 "register_operand")
+ (any_extend:VWEXTI (match_operand:<V_DOUBLE_TRUNC> 2 "register_operand"))
+ (match_operand:VWEXTI 3 "register_operand")))]
+ "TARGET_VECTOR && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(const_int 0)]
+{
+ insn_code icode = code_for_pred_vf2 (<CODE>, <MODE>mode);
+ rtx ops[] = {operands[0], operands[1], operands[2], operands[3],
+ gen_int_mode (GET_MODE_NUNITS (<MODE>mode), Pmode)};
+ riscv_vector::expand_cond_len_unop (icode, ops);
+ DONE;
+})
+
+;; Combine sign_extend/zero_extend(vf4) and vcond_mask
+(define_insn_and_split "*cond_<optab><v_quad_trunc><mode>"
+ [(set (match_operand:VQEXTI 0 "register_operand")
+ (if_then_else:VQEXTI
+ (match_operand:<VM> 1 "register_operand")
+ (any_extend:VQEXTI (match_operand:<V_QUAD_TRUNC> 2 "register_operand"))
+ (match_operand:VQEXTI 3 "register_operand")))]
+ "TARGET_VECTOR && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(const_int 0)]
+{
+ insn_code icode = code_for_pred_vf4 (<CODE>, <MODE>mode);
+ rtx ops[] = {operands[0], operands[1], operands[2], operands[3],
+ gen_int_mode (GET_MODE_NUNITS (<MODE>mode), Pmode)};
+ riscv_vector::expand_cond_len_unop (icode, ops);
+ DONE;
+})
+
+;; Combine sign_extend/zero_extend(vf8) and vcond_mask
+(define_insn_and_split "*cond_<optab><v_oct_trunc><mode>"
+ [(set (match_operand:VOEXTI 0 "register_operand")
+ (if_then_else:VOEXTI
+ (match_operand:<VM> 1 "register_operand")
+ (any_extend:VOEXTI (match_operand:<V_OCT_TRUNC> 2 "register_operand"))
+ (match_operand:VOEXTI 3 "register_operand")))]
+ "TARGET_VECTOR && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(const_int 0)]
+{
+ insn_code icode = code_for_pred_vf8 (<CODE>, <MODE>mode);
+ rtx ops[] = {operands[0], operands[1], operands[2], operands[3],
+ gen_int_mode (GET_MODE_NUNITS (<MODE>mode), Pmode)};
+ riscv_vector::expand_cond_len_unop (icode, ops);
+ DONE;
+})
+
+;; Combine trunc(vf2) + vcond_mask
+(define_insn_and_split "*cond_trunc<mode><v_double_trunc>"
+ [(set (match_operand:<V_DOUBLE_TRUNC> 0 "register_operand")
+ (if_then_else:<V_DOUBLE_TRUNC>
+ (match_operand:<VM> 1 "register_operand")
+ (truncate:<V_DOUBLE_TRUNC>
+ (match_operand:VWEXTI 2 "register_operand"))
+ (match_operand:<V_DOUBLE_TRUNC> 3 "register_operand")))]
+ "TARGET_VECTOR && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(const_int 0)]
+{
+ insn_code icode = code_for_pred_trunc (<MODE>mode);
+ rtx ops[] = {operands[0], operands[1], operands[2], operands[3],
+ gen_int_mode (GET_MODE_NUNITS (<MODE>mode), Pmode)};
+ riscv_vector::expand_cond_len_unop (icode, ops);
+ DONE;
+})
@@ -633,22 +633,28 @@
[(set_attr "type" "vext")
(set_attr "mode" "<MODE>")])
-(define_expand "<optab><v_quad_trunc><mode>2"
+(define_insn_and_split "<optab><v_quad_trunc><mode>2"
[(set (match_operand:VQEXTI 0 "register_operand")
(any_extend:VQEXTI
(match_operand:<V_QUAD_TRUNC> 1 "register_operand")))]
- "TARGET_VECTOR"
+ "TARGET_VECTOR && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(const_int 0)]
{
insn_code icode = code_for_pred_vf4 (<CODE>, <MODE>mode);
riscv_vector::emit_vlmax_insn (icode, riscv_vector::UNARY_OP, operands);
DONE;
})
-(define_expand "<optab><v_oct_trunc><mode>2"
+(define_insn_and_split "<optab><v_oct_trunc><mode>2"
[(set (match_operand:VOEXTI 0 "register_operand")
(any_extend:VOEXTI
(match_operand:<V_OCT_TRUNC> 1 "register_operand")))]
- "TARGET_VECTOR"
+ "TARGET_VECTOR && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(const_int 0)]
{
insn_code icode = code_for_pred_vf8 (<CODE>, <MODE>mode);
riscv_vector::emit_vlmax_insn (icode, riscv_vector::UNARY_OP, operands);
@@ -687,13 +693,8 @@
"TARGET_VECTOR"
{
rtx half = gen_reg_rtx (<V_DOUBLE_TRUNC>mode);
- rtx opshalf[] = {half, operands[1]};
- insn_code icode = code_for_pred_trunc (<MODE>mode);
- riscv_vector::emit_vlmax_insn (icode, riscv_vector::UNARY_OP, opshalf);
-
- rtx ops[] = {operands[0], half};
- icode = code_for_pred_trunc (<V_DOUBLE_TRUNC>mode);
- riscv_vector::emit_vlmax_insn (icode, riscv_vector::UNARY_OP, ops);
+ emit_insn (gen_trunc<mode><v_double_trunc>2 (half, operands[1]));
+ emit_insn (gen_trunc<v_double_trunc><v_quad_trunc>2 (operands[0], half));
DONE;
})
@@ -707,19 +708,9 @@
(match_operand:VOEXTI 1 "register_operand")))]
"TARGET_VECTOR"
{
- rtx half = gen_reg_rtx (<V_DOUBLE_TRUNC>mode);
- rtx opshalf[] = {half, operands[1]};
- insn_code icode = code_for_pred_trunc (<MODE>mode);
- riscv_vector::emit_vlmax_insn (icode, riscv_vector::UNARY_OP, opshalf);
-
rtx quarter = gen_reg_rtx (<V_QUAD_TRUNC>mode);
- rtx opsquarter[] = {quarter, half};
- icode = code_for_pred_trunc (<V_DOUBLE_TRUNC>mode);
- riscv_vector::emit_vlmax_insn (icode, riscv_vector::UNARY_OP, opsquarter);
-
- rtx ops[] = {operands[0], quarter};
- icode = code_for_pred_trunc (<V_QUAD_TRUNC>mode);
- riscv_vector::emit_vlmax_insn (icode, riscv_vector::UNARY_OP, ops);
+ emit_insn (gen_trunc<mode><v_quad_trunc>2 (quarter, operands[1]));
+ emit_insn (gen_trunc<v_quad_trunc><v_oct_trunc>2 (operands[0], quarter));
DONE;
})
@@ -27,5 +27,5 @@
TEST_ALL ()
-/* { dg-final { scan-assembler-times {\tvnsra\.wx} 4 } } */
+/* { dg-final { scan-assembler-times {\tvnsra\.wx} 8 } } */
/* { dg-final { scan-assembler-times {\tvnsrl\.wx} 4 } } */
new file mode 100644
@@ -0,0 +1,47 @@
+#include <stdint.h>
+
+#define DEF_LOOP(OLD_TYPE, NEW_TYPE) \
+ void __attribute__ ((noipa)) \
+ test_##OLD_TYPE##_2_##NEW_TYPE (NEW_TYPE *__restrict r, \
+ OLD_TYPE *__restrict a, \
+ NEW_TYPE *__restrict b, \
+ OLD_TYPE *__restrict pred, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ { \
+ r[i] = pred[i] ? (NEW_TYPE) a[i] : b[i]; \
+ } \
+ }
+
+/* INT -> wider-INT */
+#define TEST_ALL_X2X_WIDER(T) \
+ T (uint8_t, uint16_t) \
+ T (uint8_t, uint32_t) \
+ T (uint8_t, uint64_t) \
+ T (int8_t, int16_t) \
+ T (int8_t, int32_t) \
+ T (int8_t, int64_t) \
+ T (uint16_t, uint32_t) \
+ T (uint16_t, uint64_t) \
+ T (int16_t, int32_t) \
+ T (int16_t, int64_t) \
+ T (uint32_t, uint64_t) \
+ T (int32_t, int64_t)
+
+/* INT -> narrower-INT */
+#define TEST_ALL_X2X_NARROWER(T) \
+ T (uint16_t, uint8_t) \
+ T (int16_t, int8_t) \
+ T (uint32_t, uint8_t) \
+ T (int32_t, int8_t) \
+ T (uint64_t, uint8_t) \
+ T (int64_t, int8_t) \
+ T (uint32_t, uint16_t) \
+ T (int32_t, int16_t) \
+ T (uint64_t, uint16_t) \
+ T (int64_t, int16_t) \
+ T (uint64_t, uint32_t) \
+ T (int64_t, int32_t)
+
+TEST_ALL_X2X_WIDER (DEF_LOOP)
+TEST_ALL_X2X_NARROWER (DEF_LOOP)
new file mode 100644
@@ -0,0 +1,46 @@
+#include <stdint.h>
+
+#define DEF_LOOP(OLD_TYPE, NEW_TYPE) \
+ void __attribute__ ((noipa)) \
+ test_##OLD_TYPE##_2_##NEW_TYPE (NEW_TYPE *__restrict r, \
+ OLD_TYPE *__restrict a, NEW_TYPE b, \
+ OLD_TYPE *__restrict pred, int n) \
+ { \
+ for (int i = 0; i < n; ++i) \
+ { \
+ r[i] = pred[i] ? (NEW_TYPE) a[i] : b; \
+ } \
+ }
+
+/* INT -> wider-INT */
+#define TEST_ALL_X2X_WIDER(T) \
+ T (uint8_t, uint16_t) \
+ T (uint8_t, uint32_t) \
+ T (uint8_t, uint64_t) \
+ T (int8_t, int16_t) \
+ T (int8_t, int32_t) \
+ T (int8_t, int64_t) \
+ T (uint16_t, uint32_t) \
+ T (uint16_t, uint64_t) \
+ T (int16_t, int32_t) \
+ T (int16_t, int64_t) \
+ T (uint32_t, uint64_t) \
+ T (int32_t, int64_t)
+
+/* INT -> narrower-INT */
+#define TEST_ALL_X2X_NARROWER(T) \
+ T (uint16_t, uint8_t) \
+ T (int16_t, int8_t) \
+ T (uint32_t, uint8_t) \
+ T (int32_t, int8_t) \
+ T (uint64_t, uint8_t) \
+ T (int64_t, int8_t) \
+ T (uint32_t, uint16_t) \
+ T (int32_t, int16_t) \
+ T (uint64_t, uint16_t) \
+ T (int64_t, int16_t) \
+ T (uint64_t, uint32_t) \
+ T (int64_t, int32_t)
+
+TEST_ALL_X2X_WIDER (DEF_LOOP)
+TEST_ALL_X2X_NARROWER (DEF_LOOP)
new file mode 100644
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "cond_convert_int2int-1.h"
+
+/* { dg-final { scan-assembler-times {\tvzext\.vf2\tv[0-9]+,v[0-9]+,v0\.t} 3 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf2\tv[0-9]+,v[0-9]+,v0\.t} 3 } } */
+/* { dg-final { scan-assembler-times {\tvzext\.vf4\tv[0-9]+,v[0-9]+,v0\.t} 2 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf4\tv[0-9]+,v[0-9]+,v0\.t} 2 } } */
+/* { dg-final { scan-assembler-times {\tvzext\.vf8\tv[0-9]+,v[0-9]+,v0\.t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf8\tv[0-9]+,v[0-9]+,v0\.t} 1 } } */
+
+/* { dg-final { scan-assembler-times {\tvncvt\.x\.x\.w\tv[0-9]+,v[0-9]+,v0\.t} 12 } } */
+/* { dg-final { scan-assembler-times {\tvncvt\.x\.x\.w\tv[0-9]+,v[0-9]+\n} 8 } } */
+
+/* { dg-final { scan-assembler {\tvsetvli\t[a-z0-9]+,[a-z0-9]+,e[0-9]+,m[f0-9]+,t[au],mu} } } */
+
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "cond_convert_int2int-2.h"
+
+/* { dg-final { scan-assembler-times {\tvzext\.vf2\tv[0-9]+,v[0-9]+,v0\.t} 3 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf2\tv[0-9]+,v[0-9]+,v0\.t} 3 } } */
+/* { dg-final { scan-assembler-times {\tvzext\.vf4\tv[0-9]+,v[0-9]+,v0\.t} 2 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf4\tv[0-9]+,v[0-9]+,v0\.t} 2 } } */
+/* { dg-final { scan-assembler-times {\tvzext\.vf8\tv[0-9]+,v[0-9]+,v0\.t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf8\tv[0-9]+,v[0-9]+,v0\.t} 1 } } */
+
+/* { dg-final { scan-assembler-times {\tvncvt\.x\.x\.w\tv[0-9]+,v[0-9]+,v0\.t} 12 } } */
+/* { dg-final { scan-assembler-times {\tvncvt\.x\.x\.w\tv[0-9]+,v[0-9]+\n} 8 } } */
+
+/* { dg-final { scan-assembler {\tvsetvli\t[a-z0-9]+,[a-z0-9]+,e[0-9]+,m[f0-9]+,t[au],mu} } } */
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -mabi=lp64d --param riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "cond_convert_int2int-1.h"
+
+/* { dg-final { scan-assembler-times {\tvzext\.vf2\tv[0-9]+,v[0-9]+,v0\.t} 3 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf2\tv[0-9]+,v[0-9]+,v0\.t} 3 } } */
+/* { dg-final { scan-assembler-times {\tvzext\.vf4\tv[0-9]+,v[0-9]+,v0\.t} 2 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf4\tv[0-9]+,v[0-9]+,v0\.t} 2 } } */
+/* { dg-final { scan-assembler-times {\tvzext\.vf8\tv[0-9]+,v[0-9]+,v0\.t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf8\tv[0-9]+,v[0-9]+,v0\.t} 1 } } */
+
+/* { dg-final { scan-assembler-times {\tvncvt\.x\.x\.w\tv[0-9]+,v[0-9]+,v0\.t} 12 } } */
+/* { dg-final { scan-assembler-times {\tvncvt\.x\.x\.w\tv[0-9]+,v[0-9]+\n} 8 } } */
+
+/* { dg-final { scan-assembler {\tvsetvli\t[a-z0-9]+,[a-z0-9]+,e[0-9]+,m[f0-9]+,t[au],mu} } } */
new file mode 100644
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -mabi=lp64d --param riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "cond_convert_int2int-2.h"
+
+/* { dg-final { scan-assembler-times {\tvzext\.vf2\tv[0-9]+,v[0-9]+,v0\.t} 3 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf2\tv[0-9]+,v[0-9]+,v0\.t} 3 } } */
+/* { dg-final { scan-assembler-times {\tvzext\.vf4\tv[0-9]+,v[0-9]+,v0\.t} 2 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf4\tv[0-9]+,v[0-9]+,v0\.t} 2 } } */
+/* { dg-final { scan-assembler-times {\tvzext\.vf8\tv[0-9]+,v[0-9]+,v0\.t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvsext\.vf8\tv[0-9]+,v[0-9]+,v0\.t} 1 } } */
+
+/* { dg-final { scan-assembler-times {\tvncvt\.x\.x\.w\tv[0-9]+,v[0-9]+,v0\.t} 12 } } */
+/* { dg-final { scan-assembler-times {\tvncvt\.x\.x\.w\tv[0-9]+,v[0-9]+\n} 8 } } */
+
+/* { dg-final { scan-assembler {\tvsetvli\t[a-z0-9]+,[a-z0-9]+,e[0-9]+,m[f0-9]+,t[au],mu} } } */
new file mode 100644
@@ -0,0 +1,31 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "cond_convert_int2int-1.h"
+
+#define N 99
+
+#define TEST_LOOP(OLD_TYPE, NEW_TYPE) \
+ { \
+ NEW_TYPE r[N], b[N]; \
+ OLD_TYPE a[N], pred[N]; \
+ for (int i = 0; i < N; ++i) \
+ { \
+ a[i] = (i & 1 ? i : 3 * i) * (i % 3 == 0 ? 1 : -1); \
+ b[i] = (i % 9) * (i % 7 + 1); \
+ pred[i] = (i % 7 < 4); \
+ asm volatile("" ::: "memory"); \
+ } \
+ test_##OLD_TYPE##_2_##NEW_TYPE (r, a, b, pred, N); \
+ for (int i = 0; i < N; ++i) \
+ if (r[i] != (pred[i] ? (NEW_TYPE) a[i] : b[i])) \
+ __builtin_abort (); \
+ }
+
+int
+main ()
+{
+ TEST_ALL_X2X_WIDER (TEST_LOOP)
+ TEST_ALL_X2X_NARROWER (TEST_LOOP)
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,30 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "cond_convert_int2int-2.h"
+
+#define N 99
+
+#define TEST_LOOP(OLD_TYPE, NEW_TYPE) \
+ { \
+ NEW_TYPE r[N], b = 189; \
+ OLD_TYPE a[N], pred[N]; \
+ for (int i = 0; i < N; ++i) \
+ { \
+ a[i] = (i & 1 ? i : 3 * i) * (i % 3 == 0 ? 1 : -1); \
+ pred[i] = (i % 7 < 4); \
+ asm volatile("" ::: "memory"); \
+ } \
+ test_##OLD_TYPE##_2_##NEW_TYPE (r, a, b, pred, N); \
+ for (int i = 0; i < N; ++i) \
+ if (r[i] != (pred[i] ? (NEW_TYPE) a[i] : b)) \
+ __builtin_abort (); \
+ }
+
+int
+main ()
+{
+ TEST_ALL_X2X_WIDER (TEST_LOOP)
+ TEST_ALL_X2X_NARROWER (TEST_LOOP)
+ return 0;
+}