[PATCH v2 13/37] target/sparc: Implement FCHKSM16

[Richard Henderson <richard.henderson@linaro.org>]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/sparc/helper.h     |  1 +
 target/sparc/insns.decode |  1 +
 target/sparc/translate.c  | 32 ++++++++++++++++++++++++++++++++
 target/sparc/vis_helper.c | 23 +++++++++++++++++++++++
 4 files changed, 57 insertions(+)

diff --git a/target/sparc/helper.h b/target/sparc/helper.h
index 84435b0932..e59307efc2 100644
--- a/target/sparc/helper.h
+++ b/target/sparc/helper.h
@@ -110,6 +110,7 @@ DEF_HELPER_FLAGS_3(bshuffle, TCG_CALL_NO_RWG_SE, i64, i64, i64, i64)
 DEF_HELPER_FLAGS_2(cmask8, TCG_CALL_NO_RWG_SE, i64, i64, i64)
 DEF_HELPER_FLAGS_2(cmask16, TCG_CALL_NO_RWG_SE, i64, i64, i64)
 DEF_HELPER_FLAGS_2(cmask32, TCG_CALL_NO_RWG_SE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(fchksm16, TCG_CALL_NO_RWG_SE, i64, i64, i64)
 #define VIS_CMPHELPER(name)                                              \
     DEF_HELPER_FLAGS_2(f##name##16, TCG_CALL_NO_RWG_SE,      \
                        i64, i64, i64)                                    \
diff --git a/target/sparc/insns.decode b/target/sparc/insns.decode
index 8be808d065..18d068d2af 100644
--- a/target/sparc/insns.decode
+++ b/target/sparc/insns.decode
@@ -410,6 +410,7 @@ FCMPEq      10 000 cc:2 110101 .....  0 0101 0111 .....    \
     PDIST       10 ..... 110110 ..... 0 0011 1110 .....    \
                 &r_r_r_r rd=%dfp_rd rs1=%dfp_rd rs2=%dfp_rs1 rs3=%dfp_rs2
 
+    FCHKSM16    10 ..... 110110 ..... 0 0100 0100 .....    @d_d_d
     FALIGNDATAg 10 ..... 110110 ..... 0 0100 1000 .....    @d_d_d
     FPMERGE     10 ..... 110110 ..... 0 0100 1011 .....    @d_r_r
     BSHUFFLE    10 ..... 110110 ..... 0 0100 1100 .....    @d_d_d
diff --git a/target/sparc/translate.c b/target/sparc/translate.c
index 66c6fb6e41..48ee1abd68 100644
--- a/target/sparc/translate.c
+++ b/target/sparc/translate.c
@@ -788,6 +788,37 @@ static void gen_op_fmuld8sux16(TCGv_i64 dst, TCGv_i32 src1, TCGv_i32 src2)
     tcg_gen_concat_i32_i64(dst, t0, t1);
 }
 
+#ifdef TARGET_SPARC64
+static void gen_vec_fchksm16(unsigned vece, TCGv_vec dst,
+                             TCGv_vec src1, TCGv_vec src2)
+{
+    TCGv_vec a = tcg_temp_new_vec_matching(dst);
+    TCGv_vec c = tcg_temp_new_vec_matching(dst);
+
+    tcg_gen_add_vec(vece, a, src1, src2);
+    tcg_gen_cmp_vec(TCG_COND_LTU, vece, c, a, src1);
+    /* Vector cmp produces -1 for true, so subtract to add carry. */
+    tcg_gen_sub_vec(vece, dst, a, c);
+}
+
+static void gen_op_fchksm16(unsigned vece, uint32_t dofs, uint32_t aofs,
+                            uint32_t bofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_cmp_vec, INDEX_op_add_vec, INDEX_op_sub_vec,
+    };
+    static const GVecGen3 op = {
+        .fni8 = gen_helper_fchksm16,
+        .fniv = gen_vec_fchksm16,
+        .opt_opc = vecop_list,
+        .vece = MO_16,
+    };
+    tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &op);
+}
+#else
+#define gen_op_fchksm16   ({ qemu_build_not_reached(); NULL; })
+#endif
+
 static void finishing_insn(DisasContext *dc)
 {
     /*
@@ -4757,6 +4788,7 @@ TRANS(FPADD16, VIS1, do_gvec_ddd, a, MO_16, tcg_gen_gvec_add)
 TRANS(FPADD32, VIS1, do_gvec_ddd, a, MO_32, tcg_gen_gvec_add)
 TRANS(FPSUB16, VIS1, do_gvec_ddd, a, MO_16, tcg_gen_gvec_sub)
 TRANS(FPSUB32, VIS1, do_gvec_ddd, a, MO_32, tcg_gen_gvec_sub)
+TRANS(FCHKSM16, VIS3, do_gvec_ddd, a, MO_16, gen_op_fchksm16)
 
 static bool do_ddd(DisasContext *dc, arg_r_r_r *a,
                    void (*func)(TCGv_i64, TCGv_i64, TCGv_i64))
diff --git a/target/sparc/vis_helper.c b/target/sparc/vis_helper.c
index 20baa4ff71..fa607375d2 100644
--- a/target/sparc/vis_helper.c
+++ b/target/sparc/vis_helper.c
@@ -389,3 +389,26 @@ uint64_t helper_cmask32(uint64_t gsr, uint64_t src)
 
     return deposit64(gsr, 32, 32, mask);
 }
+
+static inline uint16_t do_fchksm16(uint16_t src1, uint16_t src2)
+{
+    uint16_t a = src1 + src2;
+    uint16_t c = a < src1;
+    return a + c;
+}
+
+uint64_t helper_fchksm16(uint64_t src1, uint64_t src2)
+{
+    VIS64 r, s1, s2;
+
+    s1.ll = src1;
+    s2.ll = src2;
+    r.ll = 0;
+
+    r.VIS_W64(0) = do_fchksm16(s1.VIS_W64(0), s2.VIS_W64(0));
+    r.VIS_W64(1) = do_fchksm16(s1.VIS_W64(1), s2.VIS_W64(1));
+    r.VIS_W64(2) = do_fchksm16(s1.VIS_W64(2), s2.VIS_W64(2));
+    r.VIS_W64(3) = do_fchksm16(s1.VIS_W64(3), s2.VIS_W64(3));
+
+    return r.ll;
+}
-- 
2.34.1