target/riscv: vector compress instruction

Backports 31bf42a26cf8b1e02f27acd302ee0ef14e877682

qemu/header_gen.py

@@ -7295,6 +7295,10 @@ riscv_symbols = (
     'helper_vrgather_vx_h',
     'helper_vrgather_vx_w',
     'helper_vrgather_vx_d',
+    'helper_vcompress_vm_b',
+    'helper_vcompress_vm_h',
+    'helper_vcompress_vm_w',
+    'helper_vcompress_vm_d',
     'pmp_hart_has_privs',
     'pmpaddr_csr_read',
     'pmpaddr_csr_write',

qemu/riscv32.h

@@ -4731,6 +4731,10 @@
 #define helper_vrgather_vx_h helper_vrgather_vx_h_riscv32
 #define helper_vrgather_vx_w helper_vrgather_vx_w_riscv32
 #define helper_vrgather_vx_d helper_vrgather_vx_d_riscv32
+#define helper_vcompress_vm_b helper_vcompress_vm_b_riscv32
+#define helper_vcompress_vm_h helper_vcompress_vm_h_riscv32
+#define helper_vcompress_vm_w helper_vcompress_vm_w_riscv32
+#define helper_vcompress_vm_d helper_vcompress_vm_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

@@ -4731,6 +4731,10 @@
 #define helper_vrgather_vx_h helper_vrgather_vx_h_riscv64
 #define helper_vrgather_vx_w helper_vrgather_vx_w_riscv64
 #define helper_vrgather_vx_d helper_vrgather_vx_d_riscv64
+#define helper_vcompress_vm_b helper_vcompress_vm_b_riscv64
+#define helper_vcompress_vm_h helper_vcompress_vm_h_riscv64
+#define helper_vcompress_vm_w helper_vcompress_vm_w_riscv64
+#define helper_vcompress_vm_d helper_vcompress_vm_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

@@ -1148,3 +1148,8 @@ DEF_HELPER_6(vrgather_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vrgather_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vrgather_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vrgather_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vcompress_vm_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vcompress_vm_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vcompress_vm_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vcompress_vm_d, void, ptr, ptr, ptr, ptr, env, i32)

qemu/target/riscv/insn32.decode

@@ -577,6 +577,7 @@ vslide1down_vx  001111 . ..... ..... 110 ..... 1010111 @r_vm
 vrgather_vv     001100 . ..... ..... 000 ..... 1010111 @r_vm
 vrgather_vx     001100 . ..... ..... 100 ..... 1010111 @r_vm
 vrgather_vi     001100 . ..... ..... 011 ..... 1010111 @r_vm
+vcompress_vm    010111 - ..... ..... 010 ..... 1010111 @r
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r

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

@@ -2915,3 +2915,37 @@ static bool trans_vrgather_vi(DisasContext *s, arg_rmrr *a)
     }
     return true;
 }
+
+/* Vector Compress Instruction */
+static bool vcompress_vm_check(DisasContext *s, arg_r *a)
+{
+    return (vext_check_isa_ill(s) &&
+            vext_check_reg(s, a->rd, false) &&
+            vext_check_reg(s, a->rs2, false) &&
+            vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs1, 1) &&
+            (a->rd != a->rs2));
+}
+
+static bool trans_vcompress_vm(DisasContext *s, arg_r *a)
+{
+    TCGContext *tcg_ctx = s->uc->tcg_ctx;
+
+    if (vcompress_vm_check(s, a)) {
+        uint32_t data = 0;
+        static gen_helper_gvec_4_ptr * const fns[4] = {
+            gen_helper_vcompress_vm_b, gen_helper_vcompress_vm_h,
+            gen_helper_vcompress_vm_w, gen_helper_vcompress_vm_d,
+        };
+        TCGLabel *over = gen_new_label(tcg_ctx);
+        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, LMUL, s->lmul);
+        tcg_gen_gvec_4_ptr(tcg_ctx, vreg_ofs(s, a->rd), vreg_ofs(s, 0),
+                           vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),
+                           tcg_ctx->cpu_env, 0, s->vlen / 8, data, fns[s->sew]);
+        gen_set_label(tcg_ctx, over);
+        return true;
+    }
+    return false;
+}

qemu/target/riscv/vector_helper.c

@@ -4847,3 +4847,29 @@ GEN_VEXT_VRGATHER_VX(vrgather_vx_b, uint8_t, H1, clearb)
 GEN_VEXT_VRGATHER_VX(vrgather_vx_h, uint16_t, H2, clearh)
 GEN_VEXT_VRGATHER_VX(vrgather_vx_w, uint32_t, H4, clearl)
 GEN_VEXT_VRGATHER_VX(vrgather_vx_d, uint64_t, H8, clearq)
+
+/* Vector Compress Instruction */
+#define GEN_VEXT_VCOMPRESS_VM(NAME, ETYPE, H, CLEAR_FN)                   \
+void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,               \
+                  CPURISCVState *env, uint32_t desc)                      \
+{                                                                         \
+    uint32_t mlen = vext_mlen(desc);                                      \
+    uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen;                   \
+    uint32_t vl = env->vl;                                                \
+    uint32_t num = 0, i;                                                  \
+                                                                          \
+    for (i = 0; i < vl; i++) {                                            \
+        if (!vext_elem_mask(vs1, mlen, i)) {                              \
+            continue;                                                     \
+        }                                                                 \
+        *((ETYPE *)vd + H(num)) = *((ETYPE *)vs2 + H(i));                 \
+        num++;                                                            \
+    }                                                                     \
+    CLEAR_FN(vd, num, num * sizeof(ETYPE), vlmax * sizeof(ETYPE));        \
+}
+
+/* Compress into vd elements of vs2 where vs1 is enabled */
+GEN_VEXT_VCOMPRESS_VM(vcompress_vm_b, uint8_t, H1, clearb)
+GEN_VEXT_VCOMPRESS_VM(vcompress_vm_h, uint16_t, H2, clearh)
+GEN_VEXT_VCOMPRESS_VM(vcompress_vm_w, uint32_t, H4, clearl)
+GEN_VEXT_VCOMPRESS_VM(vcompress_vm_d, uint64_t, H8, clearq)