From: Frank Chang <frank.ch...@sifive.com>
Add the following instructions:
* vl<nf>re<eew>.v
* vs<nf>r.v
Signed-off-by: Frank Chang <frank.ch...@sifive.com>
---
target/riscv/helper.h | 21 ++++++++
target/riscv/insn32.decode | 22 ++++++++
target/riscv/insn_trans/trans_rvv.inc.c | 72 +++++++++++++++++++++++++
target/riscv/vector_helper.c | 65 ++++++++++++++++++++++
4 files changed, 180 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 9200178d25c..25d076d71a8 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -145,6 +145,27 @@ DEF_HELPER_5(vle16ff_v, void, ptr, ptr, tl, env, i32)
DEF_HELPER_5(vle32ff_v, void, ptr, ptr, tl, env, i32)
DEF_HELPER_5(vle64ff_v, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_4(vl1re8_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl1re16_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl1re32_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl1re64_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl2re8_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl2re16_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl2re32_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl2re64_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl4re8_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl4re16_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl4re32_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl4re64_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl8re8_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl8re16_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl8re32_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vl8re64_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vs1r_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vs2r_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vs4r_v, void, ptr, tl, env, i32)
+DEF_HELPER_4(vs8r_v, void, ptr, tl, env, i32)
+
DEF_HELPER_6(vamoswapei8_32_v, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vamoswapei8_64_v, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vamoswapei16_32_v, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 6a9cf6ad534..c99575d1360 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -267,6 +267,28 @@ vle16ff_v ... 000 . 10000 ..... 101 ..... 0000111
@r2_nfvm
vle32ff_v ... 000 . 10000 ..... 110 ..... 0000111 @r2_nfvm
vle64ff_v ... 000 . 10000 ..... 111 ..... 0000111 @r2_nfvm
+# Vector whole register insns
+vl1re8_v 000 000 1 01000 ..... 000 ..... 0000111 @r2
+vl1re16_v 000 000 1 01000 ..... 101 ..... 0000111 @r2
+vl1re32_v 000 000 1 01000 ..... 110 ..... 0000111 @r2
+vl1re64_v 000 000 1 01000 ..... 111 ..... 0000111 @r2
+vl2re8_v 001 000 1 01000 ..... 000 ..... 0000111 @r2
+vl2re16_v 001 000 1 01000 ..... 101 ..... 0000111 @r2
+vl2re32_v 001 000 1 01000 ..... 110 ..... 0000111 @r2
+vl2re64_v 001 000 1 01000 ..... 111 ..... 0000111 @r2
+vl4re8_v 011 000 1 01000 ..... 000 ..... 0000111 @r2
+vl4re16_v 011 000 1 01000 ..... 101 ..... 0000111 @r2
+vl4re32_v 011 000 1 01000 ..... 110 ..... 0000111 @r2
+vl4re64_v 011 000 1 01000 ..... 111 ..... 0000111 @r2
+vl8re8_v 111 000 1 01000 ..... 000 ..... 0000111 @r2
+vl8re16_v 111 000 1 01000 ..... 101 ..... 0000111 @r2
+vl8re32_v 111 000 1 01000 ..... 110 ..... 0000111 @r2
+vl8re64_v 111 000 1 01000 ..... 111 ..... 0000111 @r2
+vs1r_v 000 000 1 01000 ..... 000 ..... 0100111 @r2
+vs2r_v 001 000 1 01000 ..... 000 ..... 0100111 @r2
+vs4r_v 011 000 1 01000 ..... 000 ..... 0100111 @r2
+vs8r_v 111 000 1 01000 ..... 000 ..... 0100111 @r2
+
#*** Vector AMO operations are encoded under the standard AMO major opcode ***
vamoswapei8_v 00001 . . ..... ..... 000 ..... 0101111 @r_wdvm
vamoswapei16_v 00001 . . ..... ..... 101 ..... 0101111 @r_wdvm
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 1377604d599..6a2f175b50a 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1016,6 +1016,78 @@ GEN_VEXT_TRANS(vle16ff_v, 16, 1, r2nfvm, ldff_op,
ld_us_check)
GEN_VEXT_TRANS(vle32ff_v, 32, 2, r2nfvm, ldff_op, ld_us_check)
GEN_VEXT_TRANS(vle64ff_v, 64, 3, r2nfvm, ldff_op, ld_us_check)
+/*
+ * load and store whole register instructions
+ */
+typedef void gen_helper_ldst_whole(TCGv_ptr, TCGv, TCGv_env, TCGv_i32);
+
+static bool ldst_whole_trans(uint32_t vd, uint32_t rs1, uint32_t data,
+ gen_helper_ldst_whole *fn, DisasContext *s,
+ bool is_store)
+{
+ TCGv_ptr dest;
+ TCGv base;
+ TCGv_i32 desc;
+
+ dest = tcg_temp_new_ptr();
+ base = tcg_temp_new();
+ desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
+
+ gen_get_gpr(base, rs1);
+ tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd));
+
+ fn(dest, base, cpu_env, desc);
+
+ tcg_temp_free_ptr(dest);
+ tcg_temp_free(base);
+ tcg_temp_free_i32(desc);
+ if (!is_store) {
+ mark_vs_dirty(s);
+ }
+ return true;
+}
+
+/*
+ * load and store whole register instructions ignore vtype and vl setting.
+ * Thus, we don't need to check vill bit. (Section 7.9)
+ */
+#define GEN_LDST_WHOLE_TRANS(NAME, EEW, ARGTYPE, ARG_NF, IS_STORE) \
+static bool trans_##NAME(DisasContext *s, arg_##ARGTYPE * a) \
+{ \
+ if (require_rvv(s) && \
+ QEMU_IS_ALIGNED(a->rd, ARG_NF)) { \
+ uint32_t data = 0; \
+ bool ret; \
+ data = FIELD_DP32(data, VDATA, NF, ARG_NF); \
+ ret = ldst_whole_trans(a->rd, a->rs1, data, gen_helper_##NAME, \
+ s, IS_STORE); \
+ return ret; \
+ } \
+ return false; \
+}
+
+GEN_LDST_WHOLE_TRANS(vl1re8_v, 8, vl1re8_v, 1, false)
+GEN_LDST_WHOLE_TRANS(vl1re16_v, 16, vl1re16_v, 1, false)
+GEN_LDST_WHOLE_TRANS(vl1re32_v, 32, vl1re32_v, 1, false)
+GEN_LDST_WHOLE_TRANS(vl1re64_v, 64, vl1re64_v, 1, false)
+GEN_LDST_WHOLE_TRANS(vl2re8_v, 8, vl2re8_v, 2, false)
+GEN_LDST_WHOLE_TRANS(vl2re16_v, 16, vl2re16_v, 2, false)
+GEN_LDST_WHOLE_TRANS(vl2re32_v, 32, vl2re32_v, 2, false)
+GEN_LDST_WHOLE_TRANS(vl2re64_v, 64, vl2re64_v, 2, false)
+GEN_LDST_WHOLE_TRANS(vl4re8_v, 8, vl4re8_v, 4, false)
+GEN_LDST_WHOLE_TRANS(vl4re16_v, 16, vl4re16_v, 4, false)
+GEN_LDST_WHOLE_TRANS(vl4re32_v, 32, vl4re32_v, 4, false)
+GEN_LDST_WHOLE_TRANS(vl4re64_v, 64, vl4re64_v, 4, false)
+GEN_LDST_WHOLE_TRANS(vl8re8_v, 8, vl8re8_v, 8, false)
+GEN_LDST_WHOLE_TRANS(vl8re16_v, 16, vl8re16_v, 8, false)
+GEN_LDST_WHOLE_TRANS(vl8re32_v, 32, vl8re32_v, 8, false)
+GEN_LDST_WHOLE_TRANS(vl8re64_v, 64, vl8re64_v, 8, false)
+
+GEN_LDST_WHOLE_TRANS(vs1r_v, 8, vs1r_v, 1, true)
+GEN_LDST_WHOLE_TRANS(vs2r_v, 8, vs2r_v, 2, true)
+GEN_LDST_WHOLE_TRANS(vs4r_v, 8, vs4r_v, 4, true)
+GEN_LDST_WHOLE_TRANS(vs8r_v, 8, vs8r_v, 8, true)
+
/*
*** vector atomic operation
*/
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d212fce21c1..f3da2e7fbbd 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -536,6 +536,71 @@ GEN_VEXT_LDFF(vle16ff_v, int16_t, lde_h)
GEN_VEXT_LDFF(vle32ff_v, int32_t, lde_w)
GEN_VEXT_LDFF(vle64ff_v, int64_t, lde_d)
+/*
+ *** load and store whole register instructions
+ */
+static void
+vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
+ vext_ldst_elem_fn *ldst_elem, uint32_t esz, uintptr_t ra,
+ MMUAccessType access_type)
+{
+ uint32_t i, k;
+ uint32_t nf = vext_nf(desc);
+ uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
+ uint32_t max_elems = vlenb >> esz;
+
+ /* probe every access */
+ probe_pages(env, base, vlenb * nf, ra, access_type);
+
+ /* load bytes from guest memory */
+ for (k = 0; k < nf; k++) {
+ for (i = 0; i < max_elems; i++) {
+ target_ulong addr = base + ((i + k * max_elems) << esz);
+ ldst_elem(env, addr, i + k * max_elems, vd, ra);
+ }
+ }
+}
+
+#define GEN_VEXT_LD_WHOLE(NAME, ETYPE, LOAD_FN) \
+void HELPER(NAME)(void *vd, target_ulong base, \
+ CPURISCVState *env, uint32_t desc) \
+{ \
+ vext_ldst_whole(vd, base, env, desc, LOAD_FN, \
+ ctzl(sizeof(ETYPE)), GETPC(), \
+ MMU_DATA_LOAD); \
+}
+
+GEN_VEXT_LD_WHOLE(vl1re8_v, int8_t, lde_b)
+GEN_VEXT_LD_WHOLE(vl1re16_v, int16_t, lde_h)
+GEN_VEXT_LD_WHOLE(vl1re32_v, int32_t, lde_w)
+GEN_VEXT_LD_WHOLE(vl1re64_v, int64_t, lde_d)
+GEN_VEXT_LD_WHOLE(vl2re8_v, int8_t, lde_b)
+GEN_VEXT_LD_WHOLE(vl2re16_v, int16_t, lde_h)
+GEN_VEXT_LD_WHOLE(vl2re32_v, int32_t, lde_w)
+GEN_VEXT_LD_WHOLE(vl2re64_v, int64_t, lde_d)
+GEN_VEXT_LD_WHOLE(vl4re8_v, int8_t, lde_b)
+GEN_VEXT_LD_WHOLE(vl4re16_v, int16_t, lde_h)
+GEN_VEXT_LD_WHOLE(vl4re32_v, int32_t, lde_w)
+GEN_VEXT_LD_WHOLE(vl4re64_v, int64_t, lde_d)
+GEN_VEXT_LD_WHOLE(vl8re8_v, int8_t, lde_b)
+GEN_VEXT_LD_WHOLE(vl8re16_v, int16_t, lde_h)
+GEN_VEXT_LD_WHOLE(vl8re32_v, int32_t, lde_w)
+GEN_VEXT_LD_WHOLE(vl8re64_v, int64_t, lde_d)
+
+#define GEN_VEXT_ST_WHOLE(NAME, ETYPE, STORE_FN) \
+void HELPER(NAME)(void *vd, target_ulong base, \
+ CPURISCVState *env, uint32_t desc) \
+{ \
+ vext_ldst_whole(vd, base, env, desc, STORE_FN, \
+ ctzl(sizeof(ETYPE)), GETPC(), \
+ MMU_DATA_STORE); \
+}
+
+GEN_VEXT_ST_WHOLE(vs1r_v, int8_t, ste_b)
+GEN_VEXT_ST_WHOLE(vs2r_v, int8_t, ste_b)
+GEN_VEXT_ST_WHOLE(vs4r_v, int8_t, ste_b)
+GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b)
+
/*
*** Vector AMO Operations (Zvamo)
*/
--
2.17.1
