@@ -243,6 +243,7 @@ struct riscv_tune_param
unsigned short fmv_cost;
bool slow_unaligned_access;
unsigned int fusible_ops;
+ bool overlap_op_by_pieces;
};
/* Information about one micro-arch we know about. */
@@ -331,6 +332,7 @@ static const struct riscv_tune_param rocket_tune_info = {
8, /* fmv_cost */
true, /* slow_unaligned_access */
RISCV_FUSE_NOTHING, /* fusible_ops */
+ false, /* overlap_op_by_pieces */
};
/* Costs to use when optimizing for Sifive 7 Series. */
@@ -346,6 +348,7 @@ static const struct riscv_tune_param sifive_7_tune_info = {
8, /* fmv_cost */
true, /* slow_unaligned_access */
RISCV_FUSE_NOTHING, /* fusible_ops */
+ false, /* overlap_op_by_pieces */
};
/* Costs to use when optimizing for T-HEAD c906. */
@@ -361,6 +364,7 @@ static const struct riscv_tune_param thead_c906_tune_info = {
8, /* fmv_cost */
false, /* slow_unaligned_access */
RISCV_FUSE_NOTHING, /* fusible_ops */
+ false, /* overlap_op_by_pieces */
};
/* Costs to use when optimizing for size. */
@@ -376,6 +380,7 @@ static const struct riscv_tune_param optimize_size_tune_info = {
8, /* fmv_cost */
false, /* slow_unaligned_access */
RISCV_FUSE_NOTHING, /* fusible_ops */
+ false, /* overlap_op_by_pieces */
};
/* Costs to use when optimizing for Ventana Micro VT1. */
@@ -393,7 +398,8 @@ static const struct riscv_tune_param ventana_vt1_tune_info = {
( RISCV_FUSE_ZEXTW | RISCV_FUSE_ZEXTH | /* fusible_ops */
RISCV_FUSE_ZEXTWS | RISCV_FUSE_LDINDEXED |
RISCV_FUSE_LUI_ADDI | RISCV_FUSE_AUIPC_ADDI |
- RISCV_FUSE_LUI_LD | RISCV_FUSE_AUIPC_LD )
+ RISCV_FUSE_LUI_LD | RISCV_FUSE_AUIPC_LD ),
+ true, /* overlap_op_by_pieces */
};
static tree riscv_handle_fndecl_attribute (tree *, tree, tree, int, bool *);
@@ -6444,6 +6450,12 @@ riscv_slow_unaligned_access (machine_mode, unsigned int)
return riscv_slow_unaligned_access_p;
}
+static bool
+riscv_overlap_op_by_pieces (void)
+{
+ return tune_param->overlap_op_by_pieces;
+}
+
/* Implement TARGET_CAN_CHANGE_MODE_CLASS. */
static bool
@@ -6974,6 +6986,9 @@ riscv_dwarf_poly_indeterminate_value (unsigned int i, unsigned int *factor,
#undef TARGET_SLOW_UNALIGNED_ACCESS
#define TARGET_SLOW_UNALIGNED_ACCESS riscv_slow_unaligned_access
+#undef TARGET_OVERLAP_OP_BY_PIECES_P
+#define TARGET_OVERLAP_OP_BY_PIECES_P riscv_overlap_op_by_pieces
+
#undef TARGET_SECONDARY_MEMORY_NEEDED
#define TARGET_SECONDARY_MEMORY_NEEDED riscv_secondary_memory_needed
new file mode 100644
@@ -0,0 +1,54 @@
+/* { dg-do compile } */
+/* { dg-options "-mcpu=sifive-u74 -march=rv64gc -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Os" "-Oz" "-Og" } } */
+
+
+#define COPY_N(N) \
+void copy##N (char *src, char *dst) \
+{ \
+ dst = __builtin_assume_aligned (dst, 4096); \
+ src = __builtin_assume_aligned (src, 4096); \
+ __builtin_memcpy (dst, src, N); \
+}
+
+/* Emits 1x {ld,sd} and 1x {lhu,lbu,sh,sb}. */
+COPY_N(11)
+
+/* Emits 1x {ld,sd} and 1x {lw,lbu,sw,sb}. */
+COPY_N(13)
+
+/* Emits 1x {ld,sd} and 1x {lw,lhu,sw,sh}. */
+COPY_N(14)
+
+/* Emits 1x {ld,sd} and 1x {lw,lhu,lbu,sw,sh,sb}. */
+COPY_N(15)
+
+/* Emits 2x {ld,sd} and 1x {lhu,lbu,sh,sb}. */
+COPY_N(19)
+
+/* Emits 2x {ld,sd} and 1x {lw,lhu,lbu,sw,sh,sb}. */
+COPY_N(23)
+
+/* The by-pieces infrastructure handles up to 24 bytes.
+ So the code below is emitted via cpymemsi/block_move_straight. */
+
+/* Emits 3x {ld,sd} and 1x {lhu,lbu,sh,sb}. */
+COPY_N(27)
+
+/* Emits 3x {ld,sd} and 1x {lw,lbu,sw,sb}. */
+COPY_N(29)
+
+/* Emits 3x {ld,sd} and 1x {lw,lhu,lbu,sw,sh,sb}. */
+COPY_N(31)
+
+/* { dg-final { scan-assembler-times "ld\t" 17 } } */
+/* { dg-final { scan-assembler-times "sd\t" 17 } } */
+
+/* { dg-final { scan-assembler-times "lw\t" 6 } } */
+/* { dg-final { scan-assembler-times "sw\t" 6 } } */
+
+/* { dg-final { scan-assembler-times "lhu\t" 7 } } */
+/* { dg-final { scan-assembler-times "sh\t" 7 } } */
+
+/* { dg-final { scan-assembler-times "lbu\t" 8 } } */
+/* { dg-final { scan-assembler-times "sb\t" 8 } } */
new file mode 100644
@@ -0,0 +1,50 @@
+/* { dg-do compile } */
+/* { dg-options "-mcpu=ventana-vt1 -march=rv64gc -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Os" "-Oz" "-Og" } } */
+
+#define COPY_N(N) \
+void copy##N (char *src, char *dst) \
+{ \
+ dst = __builtin_assume_aligned (dst, 4096); \
+ src = __builtin_assume_aligned (src, 4096); \
+ __builtin_memcpy (dst, src, N); \
+}
+
+/* Emits 1x {ld,sd} and 1x {lw,sw}. */
+COPY_N(11)
+
+/* Emits 2x {ld,sd}. */
+COPY_N(13)
+
+/* Emits 2x {ld,sd}. */
+COPY_N(14)
+
+/* Emits 2x {ld,sd}. */
+COPY_N(15)
+
+/* Emits 2x {ld,sd} and 1x {lw,sw}. */
+COPY_N(19)
+
+/* Emits 3x ld and 3x sd. */
+COPY_N(23)
+
+/* The by-pieces infrastructure handles up to 24 bytes.
+ So the code below is emitted via cpymemsi/block_move_straight. */
+
+/* Emits 3x {ld,sd} and 1x {lhu,lbu,sh,sb}. */
+COPY_N(27)
+
+/* Emits 3x {ld,sd} and 1x {lw,lbu,sw,sb}. */
+COPY_N(29)
+
+/* Emits 3x {ld,sd} and 2x {lw,sw}. */
+COPY_N(31)
+
+/* { dg-final { scan-assembler-times "ld\t" 21 } } */
+/* { dg-final { scan-assembler-times "sd\t" 21 } } */
+
+/* { dg-final { scan-assembler-times "lw\t" 5 } } */
+/* { dg-final { scan-assembler-times "sw\t" 5 } } */
+
+/* { dg-final { scan-assembler-times "lbu\t" 2 } } */
+/* { dg-final { scan-assembler-times "sb\t" 2 } } */
new file mode 100644
@@ -0,0 +1,45 @@
+/* { dg-do compile } */
+/* { dg-options "-mcpu=sifive-u74 -march=rv64gc -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Os" "-Oz" "-Og" } } */
+
+#define ZERO_N(N) \
+void zero##N (char *dst) \
+{ \
+ dst = __builtin_assume_aligned (dst, 4096); \
+ __builtin_memset (dst, 0, N); \
+}
+
+/* Emits 1x sd and 1x {sh,sb}. */
+ZERO_N(11)
+
+/* Emits 1x sd and 1x {sw,sb}. */
+ZERO_N(13)
+
+/* Emits 1x sd and 1x {sw,sh}. */
+ZERO_N(14)
+
+/* Emits 1x sd and 1x {sw,sh,sb}. */
+ZERO_N(15)
+
+/* Emits 2x sd and 1x {sh,sb}. */
+ZERO_N(19)
+
+/* Emits 2x sd and 1x {sw,sh,sb}. */
+ZERO_N(23)
+
+/* The by-pieces infrastructure handles up to 24 bytes.
+ So the code below is emitted via cpymemsi/block_move_straight. */
+
+/* Emits 3x sd and 1x {sh,sb}. */
+ZERO_N(27)
+
+/* Emits 3x sd and 1x {sw,sb}. */
+ZERO_N(29)
+
+/* Emits 3x sd and 1x {sw,sh,sb}. */
+ZERO_N(31)
+
+/* { dg-final { scan-assembler-times "sd\t" 17 } } */
+/* { dg-final { scan-assembler-times "sw\t" 6 } } */
+/* { dg-final { scan-assembler-times "sh\t" 7 } } */
+/* { dg-final { scan-assembler-times "sb\t" 8 } } */
new file mode 100644
@@ -0,0 +1,43 @@
+/* { dg-do compile } */
+/* { dg-options "-mcpu=ventana-vt1 -march=rv64gc -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Os" "-Oz" "-Og" } } */
+
+#define ZERO_N(N) \
+void zero##N (char *dst) \
+{ \
+ dst = __builtin_assume_aligned (dst, 4096); \
+ __builtin_memset (dst, 0, N); \
+}
+
+/* Emits 1x sd and 1x sw. */
+ZERO_N(11)
+
+/* Emits 2x sd. */
+ZERO_N(13)
+
+/* Emits 2x sd. */
+ZERO_N(14)
+
+/* Emits 2x sd. */
+ZERO_N(15)
+
+/* Emits 2x sd and 1x sw. */
+ZERO_N(19)
+
+/* Emits 3x sd. */
+ZERO_N(23)
+
+/* The by-pieces infrastructure handles up to 24 bytes.
+ So the code below is emitted via cpymemsi/block_move_straight. */
+
+/* Emits 3x sd and 1x sw. */
+ZERO_N(27)
+
+/* Emits 4x sd. */
+ZERO_N(29)
+
+/* Emits 4x sd. */
+ZERO_N(31)
+
+/* { dg-final { scan-assembler-times "sd\t" 23 } } */
+/* { dg-final { scan-assembler-times "sw\t" 3 } } */