* accurately according to BASE && STEP. */
return 1;
}
- /* Constants from -16 to 15 can be loaded with vmv.v.i.
- The Wc0, Wc1 constraints are already covered by the
- vi constraint so we do not need to check them here
- separately. */
- if (satisfies_constraint_vi (x))
- return 1;
+
+ rtx elt;
+ if (const_vec_duplicate_p (x, &elt))
+ {
+ /* Constants from -16 to 15 can be loaded with vmv.v.i.
+ The Wc0, Wc1 constraints are already covered by the
+ vi constraint so we do not need to check them here
+ separately. */
+ if (satisfies_constraint_vi (x))
+ return 1;
+
+ /* A const duplicate vector can always be broadcast from
+ a general-purpose register. This means we need as many
+ insns as it takes to load the constant into the GPR
+ and one vmv.v.x. */
+ return 1 + riscv_integer_cost (INTVAL (elt));
+ }
}
/* TODO: We may support more const vector in the future. */
#include "vmv-imm-template.h"
-/* { dg-final { scan-assembler-times "vmv.v.i" 32 } } */
+/* { dg-final { scan-assembler-times {vmv.v.i} 32 } } */
+/* { dg-final { scan-assembler-times {vmv.v.x} 8 } } */
#include "vmv-imm-template.h"
-/* { dg-final { scan-assembler-times "vmv.v.i" 32 } } */
+/* { dg-final { scan-assembler-times {vmv.v.i} 32 } } */
+/* { dg-final { scan-assembler-times {vmv.v.x} 8 } } */
TEST_POS(uint64_t, 13)
TEST_POS(uint64_t, 14)
TEST_POS(uint64_t, 15)
+ TEST_POS(uint32_t, 16)
+ TEST_POS(uint32_t, 123)
+ TEST_POS(uint32_t, 255)
+ TEST_POS(uint32_t, 999)
+ TEST_POS(uint32_t, 32701)
+ TEST_POS(uint32_t, 65535)
+ TEST_POS(uint32_t, 65536)
+ TEST_POS(uint32_t, 923423)
}
#include "vmv-imm-template.h"
-/* { dg-final { scan-assembler-times "vmv.v.i" 32 } } */
+/* { dg-final { scan-assembler-times {vmv.v.i} 32 } } */
+/* { dg-final { scan-assembler-times {vmv.v.x} 8 } } */
#include "vmv-imm-template.h"
-/* { dg-final { scan-assembler-times "vmv.v.i" 32 } } */
+/* { dg-final { scan-assembler-times {vmv.v.i} 32 } } */
+/* { dg-final { scan-assembler-times {vmv.v.x} 8 } } */
dst[i] = -VAL; \
}
-#define TEST_ALL() \
-VMV_NEG(int8_t,16) \
-VMV_NEG(int8_t,15) \
-VMV_NEG(int8_t,14) \
-VMV_NEG(int8_t,13) \
-VMV_NEG(int16_t,12) \
-VMV_NEG(int16_t,11) \
-VMV_NEG(int16_t,10) \
-VMV_NEG(int16_t,9) \
-VMV_NEG(int32_t,8) \
-VMV_NEG(int32_t,7) \
-VMV_NEG(int32_t,6) \
-VMV_NEG(int32_t,5) \
-VMV_NEG(int64_t,4) \
-VMV_NEG(int64_t,3) \
-VMV_NEG(int64_t,2) \
-VMV_NEG(int64_t,1) \
-VMV_POS(uint8_t,0) \
-VMV_POS(uint8_t,1) \
-VMV_POS(uint8_t,2) \
-VMV_POS(uint8_t,3) \
-VMV_POS(uint16_t,4) \
-VMV_POS(uint16_t,5) \
-VMV_POS(uint16_t,6) \
-VMV_POS(uint16_t,7) \
-VMV_POS(uint32_t,8) \
-VMV_POS(uint32_t,9) \
-VMV_POS(uint32_t,10) \
-VMV_POS(uint32_t,11) \
-VMV_POS(uint64_t,12) \
-VMV_POS(uint64_t,13) \
-VMV_POS(uint64_t,14) \
-VMV_POS(uint64_t,15)
+#define TEST_ALL() \
+VMV_NEG(int8_t,16) \
+VMV_NEG(int8_t,15) \
+VMV_NEG(int8_t,14) \
+VMV_NEG(int8_t,13) \
+VMV_NEG(int16_t,12) \
+VMV_NEG(int16_t,11) \
+VMV_NEG(int16_t,10) \
+VMV_NEG(int16_t,9) \
+VMV_NEG(int32_t,8) \
+VMV_NEG(int32_t,7) \
+VMV_NEG(int32_t,6) \
+VMV_NEG(int32_t,5) \
+VMV_NEG(int64_t,4) \
+VMV_NEG(int64_t,3) \
+VMV_NEG(int64_t,2) \
+VMV_NEG(int64_t,1) \
+VMV_POS(uint8_t,0) \
+VMV_POS(uint8_t,1) \
+VMV_POS(uint8_t,2) \
+VMV_POS(uint8_t,3) \
+VMV_POS(uint16_t,4) \
+VMV_POS(uint16_t,5) \
+VMV_POS(uint16_t,6) \
+VMV_POS(uint16_t,7) \
+VMV_POS(uint32_t,8) \
+VMV_POS(uint32_t,9) \
+VMV_POS(uint32_t,10) \
+VMV_POS(uint32_t,11) \
+VMV_POS(uint64_t,12) \
+VMV_POS(uint64_t,13) \
+VMV_POS(uint64_t,14) \
+VMV_POS(uint64_t,15) \
+VMV_POS(uint32_t,16) \
+VMV_POS(uint32_t,123) \
+VMV_POS(uint32_t,255) \
+VMV_POS(uint32_t,999) \
+VMV_POS(uint32_t,32701) \
+VMV_POS(uint32_t,65535) \
+VMV_POS(uint32_t,65536) \
+VMV_POS(uint32_t,923423) \
TEST_ALL()