diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h
index 4f3b677f4f9abe60e44e9264918fc7c360048c12..21f6dadf11338fcb93a7648e3dc3894caa83d734 100644
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -255,6 +255,8 @@ struct regmove_vector_cost
{
const int GR2VR;
const int FR2VR;
+ const int VR2GR;
+ const int VR2FR;
};
/* Cost for vector insn classes. */
diff --git a/gcc/config/riscv/riscv-vector-costs.cc b/gcc/config/riscv/riscv-vector-costs.cc
index 90ab93b7506a119994067929f1612f6fbea753ba..7c9840df4e95dee3c75251ffef1da7a88f40d47f 100644
--- a/gcc/config/riscv/riscv-vector-costs.cc
+++ b/gcc/config/riscv/riscv-vector-costs.cc
@@ -1056,6 +1056,9 @@ adjust_stmt_cost (enum vect_cost_for_stmt kind, tree vectype, int stmt_cost)
case scalar_to_vec:
return stmt_cost += (FLOAT_TYPE_P (vectype) ? costs->regmove->FR2VR
: costs->regmove->GR2VR);
+ case vec_to_scalar:
+ return stmt_cost += (FLOAT_TYPE_P (vectype) ? costs->regmove->VR2FR
+ : costs->regmove->VR2GR);
default:
break;
}
diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index ee1a57b321d372092120524420f16e1d63ac6283..568db90a27d0c1776dd95dfe425d8c0e0e9f60e4 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -395,6 +395,8 @@ static const scalable_vector_cost rvv_vla_vector_cost = {
static const regmove_vector_cost rvv_regmove_vector_cost = {
2, /* GR2VR */
2, /* FR2VR */
+ 2, /* VR2GR */
+ 2, /* VR2FR */
};
/* Generic costs for vector insn classes. It is supposed to be the vector cost
@@ -10522,7 +10524,7 @@ riscv_builtin_vectorization_cost (enum vect_cost_for_stmt type_of_cost,
return fp ? common_costs->fp_stmt_cost : common_costs->int_stmt_cost;
case vec_construct:
- return estimated_poly_value (TYPE_VECTOR_SUBPARTS (vectype)) - 1;
+ return estimated_poly_value (TYPE_VECTOR_SUBPARTS (vectype));
default:
gcc_unreachable ();
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-1.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-1.c
new file mode 100644
index 0000000000000000000000000000000000000000..0d09a624a005348733b6f5d69bc11b3210b25811
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-1.c
@@ -0,0 +1,195 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize --param=riscv-autovec-lmul=dynamic" } */
+
+#include <stdint-gcc.h>
+
+#define Ch(x,y,z) (z ^ (x & (y ^ z)))
+#define Maj(x,y,z) ((x & y) | (z & (x | y)))
+
+#define SHR(x, n) (x >> n)
+#define ROTR(x,n) (SHR(x,n) | (x << (32 - n)))
+#define S1(x) (ROTR(x, 6) ^ ROTR(x,11) ^ ROTR(x,25))
+#define S0(x) (ROTR(x, 2) ^ ROTR(x,13) ^ ROTR(x,22))
+
+#define s1(x) (ROTR(x,17) ^ ROTR(x,19) ^ SHR(x,10))
+#define s0(x) (ROTR(x, 7) ^ ROTR(x,18) ^ SHR(x, 3))
+
+#define SHA256_STEP(a,b,c,d,e,f,g,h,x,K) \
+{ \
+ tmp1 = h + S1(e) + Ch(e,f,g) + K + x; \
+ tmp2 = S0(a) + Maj(a,b,c); \
+ h = tmp1 + tmp2; \
+ d += tmp1; \
+}
+
+#define BE_LOAD32(n,b,i) (n) = byteswap(*(uint32_t *)(b + i))
+
+static uint32_t byteswap(uint32_t x)
+{
+ x = (x & 0x0000FFFF) << 16 | (x & 0xFFFF0000) >> 16;
+ x = (x & 0x00FF00FF) << 8 | (x & 0xFF00FF00) >> 8;
+
+ return x;
+}
+
+void sha256 (const uint8_t *in, uint32_t out[8])
+{
+ uint32_t tmp1, tmp2, a, b, c, d, e, f, g, h;
+ uint32_t w0, w1, w2, w3, w4, w5, w6, w7, w8, w9, w10, w11, w12, w13, w14, w15;
+
+ tmp1 = tmp2 = 0;
+ w0 = w1 = w2 = w3 = w4 = w5 = w6 = w7 = w8 = w9 = w10 = w11 = w12 = w13 = w14 = w15 = 0;
+
+ BE_LOAD32 ( w0, in, 0 );
+ BE_LOAD32 ( w1, in, 4 );
+ BE_LOAD32 ( w2, in, 8 );
+ BE_LOAD32 ( w3, in, 12 );
+ BE_LOAD32 ( w4, in, 16 );
+ BE_LOAD32 ( w5, in, 20 );
+ BE_LOAD32 ( w6, in, 24 );
+ BE_LOAD32 ( w7, in, 28 );
+ BE_LOAD32 ( w8, in, 32 );
+ BE_LOAD32 ( w9, in, 36 );
+ BE_LOAD32 ( w10, in, 40 );
+ BE_LOAD32 ( w11, in, 44 );
+ BE_LOAD32 ( w12, in, 48 );
+ BE_LOAD32 ( w13, in, 52 );
+ BE_LOAD32 ( w14, in, 56 );
+ BE_LOAD32 ( w15, in, 60 );
+
+ a = out[0];
+ b = out[1];
+ c = out[2];
+ d = out[3];
+ e = out[4];
+ f = out[5];
+ g = out[6];
+ h = out[7];
+
+ SHA256_STEP(a, b, c, d, e, f, g, h, w0, 0x428a2f98);
+ SHA256_STEP(h, a, b, c, d, e, f, g, w1, 0x71374491);
+ SHA256_STEP(g, h, a, b, c, d, e, f, w2, 0xb5c0fbcf);
+ SHA256_STEP(f, g, h, a, b, c, d, e, w3, 0xe9b5dba5);
+ SHA256_STEP(e, f, g, h, a, b, c, d, w4, 0x3956c25b);
+ SHA256_STEP(d, e, f, g, h, a, b, c, w5, 0x59f111f1);
+ SHA256_STEP(c, d, e, f, g, h, a, b, w6, 0x923f82a4);
+ SHA256_STEP(b, c, d, e, f, g, h, a, w7, 0xab1c5ed5);
+ SHA256_STEP(a, b, c, d, e, f, g, h, w8, 0xd807aa98);
+ SHA256_STEP(h, a, b, c, d, e, f, g, w9, 0x12835b01);
+ SHA256_STEP(g, h, a, b, c, d, e, f, w10, 0x243185be);
+ SHA256_STEP(f, g, h, a, b, c, d, e, w11, 0x550c7dc3);
+ SHA256_STEP(e, f, g, h, a, b, c, d, w12, 0x72be5d74);
+ SHA256_STEP(d, e, f, g, h, a, b, c, w13, 0x80deb1fe);
+ SHA256_STEP(c, d, e, f, g, h, a, b, w14, 0x9bdc06a7);
+ SHA256_STEP(b, c, d, e, f, g, h, a, w15, 0xc19bf174);
+
+ w0 = s1(w14) + w9 + s0(w1) + w0;
+ SHA256_STEP(a, b, c, d, e, f, g, h, w0, 0xe49b69c1);
+ w1 = s1(w15) + w10 + s0(w2) + w1;
+ SHA256_STEP(h, a, b, c, d, e, f, g, w1, 0xefbe4786);
+ w2 = s1(w0) + w11 + s0(w3) + w2;
+ SHA256_STEP(g, h, a, b, c, d, e, f, w2, 0x0fc19dc6);
+ w3 = s1(w1) + w12 + s0(w4) + w3;
+ SHA256_STEP(f, g, h, a, b, c, d, e, w3, 0x240ca1cc);
+ w4 = s1(w2) + w13 + s0(w5) + w4;
+ SHA256_STEP(e, f, g, h, a, b, c, d, w4, 0x2de92c6f);
+ w5 = s1(w3) + w14 + s0(w6) + w5;
+ SHA256_STEP(d, e, f, g, h, a, b, c, w5, 0x4a7484aa);
+ w6 = s1(w4) + w15 + s0(w7) + w6;
+ SHA256_STEP(c, d, e, f, g, h, a, b, w6, 0x5cb0a9dc);
+ w7 = s1(w5) + w0 + s0(w8) + w7;
+ SHA256_STEP(b, c, d, e, f, g, h, a, w7, 0x76f988da);
+ w8 = s1(w6) + w1 + s0(w9) + w8;
+ SHA256_STEP(a, b, c, d, e, f, g, h, w8, 0x983e5152);
+ w9 = s1(w7) + w2 + s0(w10) + w9;
+ SHA256_STEP(h, a, b, c, d, e, f, g, w9, 0xa831c66d);
+ w10 = s1(w8) + w3 + s0(w11) + w10;
+ SHA256_STEP(g, h, a, b, c, d, e, f, w10, 0xb00327c8);
+ w11 = s1(w9) + w4 + s0(w12) + w11;
+ SHA256_STEP(f, g, h, a, b, c, d, e, w11, 0xbf597fc7);
+ w12 = s1(w10) + w5 + s0(w13) + w12;
+ SHA256_STEP(e, f, g, h, a, b, c, d, w12, 0xc6e00bf3);
+ w13 = s1(w11) + w6 + s0(w14) + w13;
+ SHA256_STEP(d, e, f, g, h, a, b, c, w13, 0xd5a79147);
+ w14 = s1(w12) + w7 + s0(w15) + w14;
+ SHA256_STEP(c, d, e, f, g, h, a, b, w14, 0x06ca6351);
+ w15 = s1(w13) + w8 + s0(w0) + w15;
+ SHA256_STEP(b, c, d, e, f, g, h, a, w15, 0x14292967);
+
+ w0 = s1(w14) + w9 + s0(w1) + w0;
+ SHA256_STEP(a, b, c, d, e, f, g, h, w0, 0x27b70a85);
+ w1 = s1(w15) + w10 + s0(w2) + w1;
+ SHA256_STEP(h, a, b, c, d, e, f, g, w1, 0x2e1b2138);
+ w2 = s1(w0) + w11 + s0(w3) + w2;
+ SHA256_STEP(g, h, a, b, c, d, e, f, w2, 0x4d2c6dfc);
+ w3 = s1(w1) + w12 + s0(w4) + w3;
+ SHA256_STEP(f, g, h, a, b, c, d, e, w3, 0x53380d13);
+ w4 = s1(w2) + w13 + s0(w5) + w4;
+ SHA256_STEP(e, f, g, h, a, b, c, d, w4, 0x650a7354);
+ w5 = s1(w3) + w14 + s0(w6) + w5;
+ SHA256_STEP(d, e, f, g, h, a, b, c, w5, 0x766a0abb);
+ w6 = s1(w4) + w15 + s0(w7) + w6;
+ SHA256_STEP(c, d, e, f, g, h, a, b, w6, 0x81c2c92e);
+ w7 = s1(w5) + w0 + s0(w8) + w7;
+ SHA256_STEP(b, c, d, e, f, g, h, a, w7, 0x92722c85);
+ w8 = s1(w6) + w1 + s0(w9) + w8;
+ SHA256_STEP(a, b, c, d, e, f, g, h, w8, 0xa2bfe8a1);
+ w9 = s1(w7) + w2 + s0(w10) + w9;
+ SHA256_STEP(h, a, b, c, d, e, f, g, w9, 0xa81a664b);
+ w10 = s1(w8) + w3 + s0(w11) + w10;
+ SHA256_STEP(g, h, a, b, c, d, e, f, w10, 0xc24b8b70);
+ w11 = s1(w9) + w4 + s0(w12) + w11;
+ SHA256_STEP(f, g, h, a, b, c, d, e, w11, 0xc76c51a3);
+ w12 = s1(w10) + w5 + s0(w13) + w12;
+ SHA256_STEP(e, f, g, h, a, b, c, d, w12, 0xd192e819);
+ w13 = s1(w11) + w6 + s0(w14) + w13;
+ SHA256_STEP(d, e, f, g, h, a, b, c, w13, 0xd6990624);
+ w14 = s1(w12) + w7 + s0(w15) + w14;
+ SHA256_STEP(c, d, e, f, g, h, a, b, w14, 0xf40e3585);
+ w15 = s1(w13) + w8 + s0(w0) + w15;
+ SHA256_STEP(b, c, d, e, f, g, h, a, w15, 0x106aa070);
+
+ w0 = s1(w14) + w9 + s0(w1) + w0;
+ SHA256_STEP(a, b, c, d, e, f, g, h, w0, 0x19a4c116);
+ w1 = s1(w15) + w10 + s0(w2) + w1;
+ SHA256_STEP(h, a, b, c, d, e, f, g, w1, 0x1e376c08);
+ w2 = s1(w0) + w11 + s0(w3) + w2;
+ SHA256_STEP(g, h, a, b, c, d, e, f, w2, 0x2748774c);
+ w3 = s1(w1) + w12 + s0(w4) + w3;
+ SHA256_STEP(f, g, h, a, b, c, d, e, w3, 0x34b0bcb5);
+ w4 = s1(w2) + w13 + s0(w5) + w4;
+ SHA256_STEP(e, f, g, h, a, b, c, d, w4, 0x391c0cb3);
+ w5 = s1(w3) + w14 + s0(w6) + w5;
+ SHA256_STEP(d, e, f, g, h, a, b, c, w5, 0x4ed8aa4a);
+ w6 = s1(w4) + w15 + s0(w7) + w6;
+ SHA256_STEP(c, d, e, f, g, h, a, b, w6, 0x5b9cca4f);
+ w7 = s1(w5) + w0 + s0(w8) + w7;
+ SHA256_STEP(b, c, d, e, f, g, h, a, w7, 0x682e6ff3);
+ w8 = s1(w6) + w1 + s0(w9) + w8;
+ SHA256_STEP(a, b, c, d, e, f, g, h, w8, 0x748f82ee);
+ w9 = s1(w7) + w2 + s0(w10) + w9;
+ SHA256_STEP(h, a, b, c, d, e, f, g, w9, 0x78a5636f);
+ w10 = s1(w8) + w3 + s0(w11) + w10;
+ SHA256_STEP(g, h, a, b, c, d, e, f, w10, 0x84c87814);
+ w11 = s1(w9) + w4 + s0(w12) + w11;
+ SHA256_STEP(f, g, h, a, b, c, d, e, w11, 0x8cc70208);
+ w12 = s1(w10) + w5 + s0(w13) + w12;
+ SHA256_STEP(e, f, g, h, a, b, c, d, w12, 0x90befffa);
+ w13 = s1(w11) + w6 + s0(w14) + w13;
+ SHA256_STEP(d, e, f, g, h, a, b, c, w13, 0xa4506ceb);
+ w14 = s1(w12) + w7 + s0(w15) + w14;
+ SHA256_STEP(c, d, e, f, g, h, a, b, w14, 0xbef9a3f7);
+ w15 = s1(w13) + w8 + s0(w0) + w15;
+ SHA256_STEP(b, c, d, e, f, g, h, a, w15, 0xc67178f2);
+
+ out[0] += a;
+ out[1] += b;
+ out[2] += c;
+ out[3] += d;
+ out[4] += e;
+ out[5] += f;
+ out[6] += g;
+ out[7] += h;
+}
+
+/* { dg-final { scan-assembler-not {vset} } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-2.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-2.c
new file mode 100644
index 0000000000000000000000000000000000000000..64a53cfca886a814e15ab1b60fe928d0b06f4fb0
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-2.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize --param=riscv-autovec-lmul=dynamic --param=riscv-autovec-preference=fixed-vlmax" } */
+
+#include "pr113247-1.c"
+
+/* { dg-final { scan-assembler-not {vset} } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-3.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-3.c
new file mode 100644
index 0000000000000000000000000000000000000000..423c90e41542a1a7bb478c96cb31642c36c18e58
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-3.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize" } */
+
+#include "pr113247-1.c"
+
+/* { dg-final { scan-assembler-not {vset} } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-4.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-4.c
new file mode 100644
index 0000000000000000000000000000000000000000..c2a46d848e576e7c211674f54aa28652a467428b
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113247-4.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax" } */
+
+#include "pr113247-1.c"
+
+/* { dg-final { scan-assembler-not {vset} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-19.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-19.c
index 2048b636910105e9afd7654480a84da55f7f20b6..5130fe5f2e33d386787e2b72712386be80d7f931 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-19.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-19.c
@@ -14,7 +14,7 @@ DEF_REDUC_PLUS (_Float16, 512)
DEF_REDUC_PLUS (_Float16, 1024)
DEF_REDUC_PLUS (_Float16, 2048)
-/* { dg-final { scan-assembler-times {vfredosum\.vs} 10 } } */
+/* { dg-final { scan-assembler-times {vfredosum\.vs} 9 } } */
/* { dg-final { scan-assembler-not {csrr} } } */
/* { dg-final { scan-tree-dump-not "1,1" "optimized" } } */
/* { dg-final { scan-tree-dump-not "2,2" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-20.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-20.c
index bfc328da56839a6a6d0da037e2c95bd3726821fb..819104a8cdf9e4b535df745e2da1b8a4c01ac00c 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-20.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-20.c
@@ -13,7 +13,7 @@ DEF_REDUC_PLUS (float, 256)
DEF_REDUC_PLUS (float, 512)
DEF_REDUC_PLUS (float, 1024)
-/* { dg-final { scan-assembler-times {vfredosum\.vs} 9 } } */
+/* { dg-final { scan-assembler-times {vfredosum\.vs} 8 } } */
/* { dg-final { scan-assembler-not {csrr} } } */
/* { dg-final { scan-tree-dump-not "1,1" "optimized" } } */
/* { dg-final { scan-tree-dump-not "2,2" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-21.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-21.c
index 8228590fa3b755e27b00a70d59fd3dcf927dfe5c..2b61e0ac71a0952e46902e3e685198dbffb3de6d 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-21.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/reduc-21.c
@@ -12,7 +12,7 @@ DEF_REDUC_PLUS (float, 128)
DEF_REDUC_PLUS (float, 256)
DEF_REDUC_PLUS (float, 512)
-/* { dg-final { scan-assembler-times {vfredosum\.vs} 8 } } */
+/* { dg-final { scan-assembler-times {vfredosum\.vs} 7 } } */
/* { dg-final { scan-assembler-not {csrr} } } */
/* { dg-final { scan-tree-dump-not "1,1" "optimized" } } */
/* { dg-final { scan-tree-dump-not "2,2" "optimized" } } */