target/riscv: vector floating-point square-root instruction

Backports d9e4ce72a5a0f7c404156d40d3252d4d6a9d6a36

qemu/header_gen.py

@@ -7091,6 +7091,9 @@ riscv_symbols = (
     'helper_vfwmsac_vf_w',
     'helper_vfwnmsac_vf_h',
     'helper_vfwnmsac_vf_w',
+    'helper_vfsqrt_v_h',
+    'helper_vfsqrt_v_w',
+    'helper_vfsqrt_v_d',
     'pmp_hart_has_privs',
     'pmpaddr_csr_read',
     'pmpaddr_csr_write',

qemu/riscv32.h

@@ -4527,6 +4527,9 @@
 #define helper_vfwmsac_vf_w helper_vfwmsac_vf_w_riscv32
 #define helper_vfwnmsac_vf_h helper_vfwnmsac_vf_h_riscv32
 #define helper_vfwnmsac_vf_w helper_vfwnmsac_vf_w_riscv32
+#define helper_vfsqrt_v_h helper_vfsqrt_v_h_riscv32
+#define helper_vfsqrt_v_w helper_vfsqrt_v_w_riscv32
+#define helper_vfsqrt_v_d helper_vfsqrt_v_d_riscv32
 #define pmp_hart_has_privs pmp_hart_has_privs_riscv32
 #define pmpaddr_csr_read pmpaddr_csr_read_riscv32
 #define pmpaddr_csr_write pmpaddr_csr_write_riscv32

qemu/riscv64.h

@@ -4527,6 +4527,9 @@
 #define helper_vfwmsac_vf_w helper_vfwmsac_vf_w_riscv64
 #define helper_vfwnmsac_vf_h helper_vfwnmsac_vf_h_riscv64
 #define helper_vfwnmsac_vf_w helper_vfwnmsac_vf_w_riscv64
+#define helper_vfsqrt_v_h helper_vfsqrt_v_h_riscv64
+#define helper_vfsqrt_v_w helper_vfsqrt_v_w_riscv64
+#define helper_vfsqrt_v_d helper_vfsqrt_v_d_riscv64
 #define pmp_hart_has_privs pmp_hart_has_privs_riscv64
 #define pmpaddr_csr_read pmpaddr_csr_read_riscv64
 #define pmpaddr_csr_write pmpaddr_csr_write_riscv64

qemu/target/riscv/helper.h

@@ -926,3 +926,7 @@ DEF_HELPER_6(vfwmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
 DEF_HELPER_6(vfwmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
 DEF_HELPER_6(vfwnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
 DEF_HELPER_6(vfwnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_5(vfsqrt_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfsqrt_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfsqrt_v_d, void, ptr, ptr, ptr, env, i32)

qemu/target/riscv/insn32.decode

@@ -45,6 +45,7 @@
 &shift     shamt rs1 rd
 &atomic    aq rl rs2 rs1 rd
 &rmrr      vm rd rs1 rs2
+&rmr       vm rd rs2
 &rwdvm     vm wd rd rs1 rs2
 &r2nfvm    vm rd rs1 nf
 &rnfvm     vm rd rs1 rs2 nf
@@ -68,6 +69,7 @@
 @r2_rm   .......   ..... ..... ... ..... ....... %rs1 %rm %rd
 @r2      .......   ..... ..... ... ..... ....... %rs1 %rd
 @r2_nfvm ... ... vm:1 ..... ..... ... ..... ....... &r2nfvm %nf %rs1 %rd
+@r2_vm   ...... vm:1 ..... ..... ... ..... ....... &rmr %rs2 %rd
 @r_nfvm  ... ... vm:1 ..... ..... ... ..... ....... &rnfvm %nf %rs2 %rs1 %rd
 @r_vm    ...... vm:1 ..... ..... ... ..... ....... &rmrr %rs2 %rs1 %rd
 @r_vm_1  ...... . ..... ..... ... ..... .......    &rmrr vm=1 %rs2 %rs1 %rd
@@ -489,6 +491,7 @@ vfwmsac_vv      111110 . ..... ..... 001 ..... 1010111 @r_vm
 vfwmsac_vf      111110 . ..... ..... 101 ..... 1010111 @r_vm
 vfwnmsac_vv     111111 . ..... ..... 001 ..... 1010111 @r_vm
 vfwnmsac_vf     111111 . ..... ..... 101 ..... 1010111 @r_vm
+vfsqrt_v        100011 . ..... 00000 001 ..... 1010111 @r2_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r

qemu/target/riscv/insn_trans/trans_rvv.inc.c

@@ -2121,3 +2121,47 @@ GEN_OPFVF_WIDEN_TRANS(vfwmacc_vf)
 GEN_OPFVF_WIDEN_TRANS(vfwnmacc_vf)
 GEN_OPFVF_WIDEN_TRANS(vfwmsac_vf)
 GEN_OPFVF_WIDEN_TRANS(vfwnmsac_vf)
+
+/* Vector Floating-Point Square-Root Instruction */
+
+/*
+ * If the current SEW does not correspond to a supported IEEE floating-point
+ * type, an illegal instruction exception is raised
+ */
+static bool opfv_check(DisasContext *s, arg_rmr *a)
+{
+   return (vext_check_isa_ill(s) &&
+            vext_check_overlap_mask(s, a->rd, a->vm, false) &&
+            vext_check_reg(s, a->rd, false) &&
+            vext_check_reg(s, a->rs2, false) &&
+            (s->sew != 0));
+}
+
+#define GEN_OPFV_TRANS(NAME, CHECK)                                \
+static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
+{                                                                  \
+    TCGContext *tcg_ctx = s->uc->tcg_ctx;                          \
+    if (CHECK(s, a)) {                                             \
+        uint32_t data = 0;                                         \
+        static gen_helper_gvec_3_ptr * const fns[3] = {            \
+            gen_helper_##NAME##_h,                                 \
+            gen_helper_##NAME##_w,                                 \
+            gen_helper_##NAME##_d,                                 \
+        };                                                         \
+        TCGLabel *over = gen_new_label(tcg_ctx);                   \
+        gen_set_rm(s, 7);                                          \
+        tcg_gen_brcondi_tl(tcg_ctx, TCG_COND_EQ, tcg_ctx->cpu_vl_risc, 0, over); \
+                                                                   \
+        data = FIELD_DP32(data, VDATA, MLEN, s->mlen);             \
+        data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
+        tcg_gen_gvec_3_ptr(tcg_ctx, vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
+                           vreg_ofs(s, a->rs2), tcg_ctx->cpu_env, 0, \
+                           s->vlen / 8, data, fns[s->sew - 1]);    \
+        gen_set_label(tcg_ctx, over);                              \
+        return true;                                               \
+    }                                                              \
+    return false;                                                  \
+}
+
+GEN_OPFV_TRANS(vfsqrt_v, opfv_check)

qemu/target/riscv/vector_helper.c

@@ -3775,3 +3775,46 @@ RVVCALL(OPFVF3, vfwnmsac_vf_h, WOP_UUU_H, H4, H2, fwnmsac16)
 RVVCALL(OPFVF3, vfwnmsac_vf_w, WOP_UUU_W, H8, H4, fwnmsac32)
 GEN_VEXT_VF(vfwnmsac_vf_h, 2, 4, clearl)
 GEN_VEXT_VF(vfwnmsac_vf_w, 4, 8, clearq)
+
+/* Vector Floating-Point Square-Root Instruction */
+/* (TD, T2, TX2) */
+#define OP_UU_H uint16_t, uint16_t, uint16_t
+#define OP_UU_W uint32_t, uint32_t, uint32_t
+#define OP_UU_D uint64_t, uint64_t, uint64_t
+
+#define OPFVV1(NAME, TD, T2, TX2, HD, HS2, OP)        \
+static void do_##NAME(void *vd, void *vs2, int i,      \
+        CPURISCVState *env)                            \
+{                                                      \
+    TX2 s2 = *((T2 *)vs2 + HS2(i));                    \
+    *((TD *)vd + HD(i)) = OP(s2, &env->fp_status);     \
+}
+
+#define GEN_VEXT_V_ENV(NAME, ESZ, DSZ, CLEAR_FN)       \
+void HELPER(NAME)(void *vd, void *v0, void *vs2,       \
+        CPURISCVState *env, uint32_t desc)             \
+{                                                      \
+    uint32_t vlmax = vext_maxsz(desc) / ESZ;           \
+    uint32_t mlen = vext_mlen(desc);                   \
+    uint32_t vm = vext_vm(desc);                       \
+    uint32_t vl = env->vl;                             \
+    uint32_t i;                                        \
+                                                       \
+    if (vl == 0) {                                     \
+        return;                                        \
+    }                                                  \
+    for (i = 0; i < vl; i++) {                         \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {     \
+            continue;                                  \
+        }                                              \
+        do_##NAME(vd, vs2, i, env);                    \
+    }                                                  \
+    CLEAR_FN(vd, vl, vl * DSZ,  vlmax * DSZ);          \
+}
+
+RVVCALL(OPFVV1, vfsqrt_v_h, OP_UU_H, H2, H2, float16_sqrt)
+RVVCALL(OPFVV1, vfsqrt_v_w, OP_UU_W, H4, H4, float32_sqrt)
+RVVCALL(OPFVV1, vfsqrt_v_d, OP_UU_D, H8, H8, float64_sqrt)
+GEN_VEXT_V_ENV(vfsqrt_v_h, 2, 2, clearh)
+GEN_VEXT_V_ENV(vfsqrt_v_w, 4, 4, clearl)
+GEN_VEXT_V_ENV(vfsqrt_v_d, 8, 8, clearq)