target/sparc: Implement FHADD, FHSUB, FNHADD, FNADD, FNMUL

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

diff --git a/target/sparc/fop_helper.c b/target/sparc/fop_helper.c
index 1de44d79c11e9e895e21c6947764c4a640c186a1..08b5f96f958fc8bf3db872ff37ed5052678ddfad 100644 (file)
--- a/target/sparc/fop_helper.c
+++ b/target/sparc/fop_helper.c
@@ -359,6 +359,74 @@ float64 helper_fmaddd(CPUSPARCState *env, float64 s1,
     return ret;
 }
 
+float32 helper_fnadds(CPUSPARCState *env, float32 src1, float32 src2)
+{
+    float32 ret = float32_add(src1, src2, &env->fp_status);
+
+    /*
+     * NaN inputs or result do not get a sign change.
+     * Nor, apparently, does zero: on hardware, -(x + -x) yields +0.
+     */
+    if (!float32_is_any_nan(ret) && !float32_is_zero(ret)) {
+        ret = float32_chs(ret);
+    }
+    check_ieee_exceptions(env, GETPC());
+    return ret;
+}
+
+float32 helper_fnmuls(CPUSPARCState *env, float32 src1, float32 src2)
+{
+    float32 ret = float32_mul(src1, src2, &env->fp_status);
+
+    /* NaN inputs or result do not get a sign change. */
+    if (!float32_is_any_nan(ret)) {
+        ret = float32_chs(ret);
+    }
+    check_ieee_exceptions(env, GETPC());
+    return ret;
+}
+
+float64 helper_fnaddd(CPUSPARCState *env, float64 src1, float64 src2)
+{
+    float64 ret = float64_add(src1, src2, &env->fp_status);
+
+    /*
+     * NaN inputs or result do not get a sign change.
+     * Nor, apparently, does zero: on hardware, -(x + -x) yields +0.
+     */
+    if (!float64_is_any_nan(ret) && !float64_is_zero(ret)) {
+        ret = float64_chs(ret);
+    }
+    check_ieee_exceptions(env, GETPC());
+    return ret;
+}
+
+float64 helper_fnmuld(CPUSPARCState *env, float64 src1, float64 src2)
+{
+    float64 ret = float64_mul(src1, src2, &env->fp_status);
+
+    /* NaN inputs or result do not get a sign change. */
+    if (!float64_is_any_nan(ret)) {
+        ret = float64_chs(ret);
+    }
+    check_ieee_exceptions(env, GETPC());
+    return ret;
+}
+
+float64 helper_fnsmuld(CPUSPARCState *env, float32 src1, float32 src2)
+{
+    float64 ret = float64_mul(float32_to_float64(src1, &env->fp_status),
+                              float32_to_float64(src2, &env->fp_status),
+                              &env->fp_status);
+
+    /* NaN inputs or result do not get a sign change. */
+    if (!float64_is_any_nan(ret)) {
+        ret = float64_chs(ret);
+    }
+    check_ieee_exceptions(env, GETPC());
+    return ret;
+}
+
 static uint32_t finish_fcmp(CPUSPARCState *env, FloatRelation r, uintptr_t ra)
 {
     check_ieee_exceptions(env, ra);

diff --git a/target/sparc/helper.h b/target/sparc/helper.h
index e59307efc2e89c4fb340870eff2df0f7340e1abd..15f0907a1b03f59b837868fdf7247701fbad6dc5 100644 (file)
--- a/target/sparc/helper.h
+++ b/target/sparc/helper.h
@@ -57,6 +57,8 @@ DEF_HELPER_FLAGS_3(fsubd, TCG_CALL_NO_WG, f64, env, f64, f64)
 DEF_HELPER_FLAGS_3(fmuld, TCG_CALL_NO_WG, f64, env, f64, f64)
 DEF_HELPER_FLAGS_3(fdivd, TCG_CALL_NO_WG, f64, env, f64, f64)
 DEF_HELPER_FLAGS_5(fmaddd, TCG_CALL_NO_WG, f64, env, f64, f64, f64, i32)
+DEF_HELPER_FLAGS_3(fnaddd, TCG_CALL_NO_WG, f64, env, f64, f64)
+DEF_HELPER_FLAGS_3(fnmuld, TCG_CALL_NO_WG, f64, env, f64, f64)
 
 DEF_HELPER_FLAGS_3(faddq, TCG_CALL_NO_WG, i128, env, i128, i128)
 DEF_HELPER_FLAGS_3(fsubq, TCG_CALL_NO_WG, i128, env, i128, i128)
@@ -68,8 +70,11 @@ DEF_HELPER_FLAGS_3(fsubs, TCG_CALL_NO_WG, f32, env, f32, f32)
 DEF_HELPER_FLAGS_3(fmuls, TCG_CALL_NO_WG, f32, env, f32, f32)
 DEF_HELPER_FLAGS_3(fdivs, TCG_CALL_NO_WG, f32, env, f32, f32)
 DEF_HELPER_FLAGS_5(fmadds, TCG_CALL_NO_WG, f32, env, f32, f32, f32, i32)
+DEF_HELPER_FLAGS_3(fnadds, TCG_CALL_NO_WG, f32, env, f32, f32)
+DEF_HELPER_FLAGS_3(fnmuls, TCG_CALL_NO_WG, f32, env, f32, f32)
 
 DEF_HELPER_FLAGS_3(fsmuld, TCG_CALL_NO_WG, f64, env, f32, f32)
+DEF_HELPER_FLAGS_3(fnsmuld, TCG_CALL_NO_WG, f64, env, f32, f32)
 DEF_HELPER_FLAGS_3(fdmulq, TCG_CALL_NO_WG, i128, env, f64, f64)
 
 DEF_HELPER_FLAGS_2(fitod, TCG_CALL_NO_WG, f64, env, s32)

diff --git a/target/sparc/insns.decode b/target/sparc/insns.decode
index 18d068d2af3a9a6a6ddf5f24bd5a7afe3f7d3c6d..6ec383886560b6dc325cbd08e3e4af32cc8e598e 100644 (file)
--- a/target/sparc/insns.decode
+++ b/target/sparc/insns.decode
@@ -307,8 +307,19 @@ FMULq       10 ..... 110100 ..... 0 0100 1011 .....        @q_q_q
 FDIVs       10 ..... 110100 ..... 0 0100 1101 .....        @r_r_r
 FDIVd       10 ..... 110100 ..... 0 0100 1110 .....        @d_d_d
 FDIVq       10 ..... 110100 ..... 0 0100 1111 .....        @q_q_q
+FNADDs      10 ..... 110100 ..... 0 0101 0001 .....        @r_r_r
+FNADDd      10 ..... 110100 ..... 0 0101 0010 .....        @d_d_d
+FNMULs      10 ..... 110100 ..... 0 0101 1001 .....        @r_r_r
+FNMULd      10 ..... 110100 ..... 0 0101 1010 .....        @d_d_d
+FHADDs      10 ..... 110100 ..... 0 0110 0001 .....        @r_r_r
+FHADDd      10 ..... 110100 ..... 0 0110 0010 .....        @d_d_d
+FHSUBs      10 ..... 110100 ..... 0 0110 0101 .....        @r_r_r
+FHSUBd      10 ..... 110100 ..... 0 0110 0110 .....        @d_d_d
 FsMULd      10 ..... 110100 ..... 0 0110 1001 .....        @d_r_r
 FdMULq      10 ..... 110100 ..... 0 0110 1110 .....        @q_d_d
+FNHADDs     10 ..... 110100 ..... 0 0111 0001 .....        @r_r_r
+FNHADDd     10 ..... 110100 ..... 0 0111 0010 .....        @d_d_d
+FNsMULd     10 ..... 110100 ..... 0 0111 1001 .....        @d_r_r
 FsTOx       10 ..... 110100 00000 0 1000 0001 .....        @r_r2
 FdTOx       10 ..... 110100 00000 0 1000 0010 .....        @r_d2
 FqTOx       10 ..... 110100 00000 0 1000 0011 .....        @r_q2

diff --git a/target/sparc/translate.c b/target/sparc/translate.c
index b8ba8eea74fe0581d1277b167c498196707fa2f3..d81b9ce5a8715e0048464ba82ef3afe4e495098e 100644 (file)
--- a/target/sparc/translate.c
+++ b/target/sparc/translate.c
@@ -1234,6 +1234,51 @@ static void gen_op_fnmaddd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2, TCGv_i64 s3)
     gen_helper_fmaddd(d, tcg_env, s1, s2, s3, tcg_constant_i32(op));
 }
 
+/* Use muladd to compute (1 * src1) + src2 / 2 with one rounding. */
+static void gen_op_fhadds(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2)
+{
+    TCGv_i32 one = tcg_constant_i32(float32_one);
+    int op = float_muladd_halve_result;
+    gen_helper_fmadds(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
+static void gen_op_fhaddd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2)
+{
+    TCGv_i64 one = tcg_constant_i64(float64_one);
+    int op = float_muladd_halve_result;
+    gen_helper_fmaddd(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
+/* Use muladd to compute (1 * src1) - src2 / 2 with one rounding. */
+static void gen_op_fhsubs(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2)
+{
+    TCGv_i32 one = tcg_constant_i32(float32_one);
+    int op = float_muladd_negate_c | float_muladd_halve_result;
+    gen_helper_fmadds(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
+static void gen_op_fhsubd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2)
+{
+    TCGv_i64 one = tcg_constant_i64(float64_one);
+    int op = float_muladd_negate_c | float_muladd_halve_result;
+    gen_helper_fmaddd(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
+/* Use muladd to compute -((1 * src1) + src2 / 2) with one rounding. */
+static void gen_op_fnhadds(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2)
+{
+    TCGv_i32 one = tcg_constant_i32(float32_one);
+    int op = float_muladd_negate_result | float_muladd_halve_result;
+    gen_helper_fmadds(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
+static void gen_op_fnhaddd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2)
+{
+    TCGv_i64 one = tcg_constant_i64(float64_one);
+    int op = float_muladd_negate_result | float_muladd_halve_result;
+    gen_helper_fmaddd(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
 static void gen_op_fpexception_im(DisasContext *dc, int ftt)
 {
     /*
@@ -4710,6 +4755,10 @@ TRANS(FXNORs, VIS1, do_fff, a, tcg_gen_eqv_i32)
 TRANS(FORNOTs, VIS1, do_fff, a, tcg_gen_orc_i32)
 TRANS(FORs, VIS1, do_fff, a, tcg_gen_or_i32)
 
+TRANS(FHADDs, VIS3, do_fff, a, gen_op_fhadds)
+TRANS(FHSUBs, VIS3, do_fff, a, gen_op_fhsubs)
+TRANS(FNHADDs, VIS3, do_fff, a, gen_op_fnhadds)
+
 static bool do_env_fff(DisasContext *dc, arg_r_r_r *a,
                        void (*func)(TCGv_i32, TCGv_env, TCGv_i32, TCGv_i32))
 {
@@ -4730,6 +4779,8 @@ TRANS(FADDs, ALL, do_env_fff, a, gen_helper_fadds)
 TRANS(FSUBs, ALL, do_env_fff, a, gen_helper_fsubs)
 TRANS(FMULs, ALL, do_env_fff, a, gen_helper_fmuls)
 TRANS(FDIVs, ALL, do_env_fff, a, gen_helper_fdivs)
+TRANS(FNADDs, VIS3, do_env_fff, a, gen_helper_fnadds)
+TRANS(FNMULs, VIS3, do_env_fff, a, gen_helper_fnmuls)
 
 static bool do_dff(DisasContext *dc, arg_r_r_r *a,
                    void (*func)(TCGv_i64, TCGv_i32, TCGv_i32))
@@ -4827,6 +4878,10 @@ TRANS(FPACK32, VIS1, do_ddd, a, gen_op_fpack32)
 TRANS(FALIGNDATAg, VIS1, do_ddd, a, gen_op_faligndata)
 TRANS(BSHUFFLE, VIS2, do_ddd, a, gen_op_bshuffle)
 
+TRANS(FHADDd, VIS3, do_ddd, a, gen_op_fhaddd)
+TRANS(FHSUBd, VIS3, do_ddd, a, gen_op_fhsubd)
+TRANS(FNHADDd, VIS3, do_ddd, a, gen_op_fnhaddd)
+
 static bool do_rdd(DisasContext *dc, arg_r_r_r *a,
                    void (*func)(TCGv, TCGv_i64, TCGv_i64))
 {
@@ -4876,6 +4931,8 @@ TRANS(FADDd, ALL, do_env_ddd, a, gen_helper_faddd)
 TRANS(FSUBd, ALL, do_env_ddd, a, gen_helper_fsubd)
 TRANS(FMULd, ALL, do_env_ddd, a, gen_helper_fmuld)
 TRANS(FDIVd, ALL, do_env_ddd, a, gen_helper_fdivd)
+TRANS(FNADDd, VIS3, do_env_ddd, a, gen_helper_fnaddd)
+TRANS(FNMULd, VIS3, do_env_ddd, a, gen_helper_fnmuld)
 
 static bool trans_FsMULd(DisasContext *dc, arg_r_r_r *a)
 {
@@ -4897,6 +4954,25 @@ static bool trans_FsMULd(DisasContext *dc, arg_r_r_r *a)
     return advance_pc(dc);
 }
 
+static bool trans_FNsMULd(DisasContext *dc, arg_r_r_r *a)
+{
+    TCGv_i64 dst;
+    TCGv_i32 src1, src2;
+
+    if (!avail_VIS3(dc)) {
+        return false;
+    }
+    if (gen_trap_ifnofpu(dc)) {
+        return true;
+    }
+    dst = tcg_temp_new_i64();
+    src1 = gen_load_fpr_F(dc, a->rs1);
+    src2 = gen_load_fpr_F(dc, a->rs2);
+    gen_helper_fnsmuld(dst, tcg_env, src1, src2);
+    gen_store_fpr_D(dc, a->rd, dst);
+    return advance_pc(dc);
+}
+
 static bool do_ffff(DisasContext *dc, arg_r_r_r_r *a,
                     void (*func)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32))
 {