[PULL 10/87] target/ppc: vmulh* instructions without helpers

["Cédric Le Goater" <clg@kaod.org>]

From: "Lucas Mateus Castro (alqotel)" <lucas.castro@eldorado.org.br>

Changed vmulhuw, vmulhud, vmulhsw, vmulhsd to not
use helpers.

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Signed-off-by: Matheus Ferst <matheus.ferst@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220225210936.1749575-5-matheus.ferst@eldorado.org.br>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
---
 target/ppc/helper.h                 |  4 --
 target/ppc/int_helper.c             | 35 -----------
 target/ppc/translate/vmx-impl.c.inc | 91 +++++++++++++++++++++++++++--
 3 files changed, 87 insertions(+), 43 deletions(-)

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 43c7a0263c6c..0fdf2e8a75a4 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -204,10 +204,6 @@ DEF_HELPER_FLAGS_3(VMULOSW, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VMULOUB, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VMULOUH, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VMULOUW, TCG_CALL_NO_RWG, void, avr, avr, avr)
-DEF_HELPER_FLAGS_3(VMULHSW, TCG_CALL_NO_RWG, void, avr, avr, avr)
-DEF_HELPER_FLAGS_3(VMULHUW, TCG_CALL_NO_RWG, void, avr, avr, avr)
-DEF_HELPER_FLAGS_3(VMULHSD, TCG_CALL_NO_RWG, void, avr, avr, avr)
-DEF_HELPER_FLAGS_3(VMULHUD, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_3(vslo, void, avr, avr, avr)
 DEF_HELPER_3(vsro, void, avr, avr, avr)
 DEF_HELPER_3(vsrv, void, avr, avr, avr)
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index 873f957bf4ea..46ef3ffb3f62 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1097,41 +1097,6 @@ VMUL(UW, u32, VsrW, VsrD, uint64_t)
 #undef VMUL_DO_ODD
 #undef VMUL
 
-void helper_VMULHSW(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
-{
-    int i;
-
-    for (i = 0; i < 4; i++) {
-        r->s32[i] = (int32_t)(((int64_t)a->s32[i] * (int64_t)b->s32[i]) >> 32);
-    }
-}
-
-void helper_VMULHUW(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
-{
-    int i;
-
-    for (i = 0; i < 4; i++) {
-        r->u32[i] = (uint32_t)(((uint64_t)a->u32[i] *
-                               (uint64_t)b->u32[i]) >> 32);
-    }
-}
-
-void helper_VMULHSD(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
-{
-    uint64_t discard;
-
-    muls64(&discard, &r->u64[0], a->s64[0], b->s64[0]);
-    muls64(&discard, &r->u64[1], a->s64[1], b->s64[1]);
-}
-
-void helper_VMULHUD(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
-{
-    uint64_t discard;
-
-    mulu64(&discard, &r->u64[0], a->u64[0], b->u64[0]);
-    mulu64(&discard, &r->u64[1], a->u64[1], b->u64[1]);
-}
-
 void helper_vperm(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b,
                   ppc_avr_t *c)
 {
diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index d493de3629e5..97a075efd1ef 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -2151,10 +2151,93 @@ TRANS_FLAGS2(ISA310, VMULOSD, do_vx_vmuleo, false, tcg_gen_muls2_i64)
 TRANS_FLAGS2(ISA310, VMULEUD, do_vx_vmuleo, true , tcg_gen_mulu2_i64)
 TRANS_FLAGS2(ISA310, VMULOUD, do_vx_vmuleo, false, tcg_gen_mulu2_i64)
 
-TRANS_FLAGS2(ISA310, VMULHSW, do_vx_helper, gen_helper_VMULHSW)
-TRANS_FLAGS2(ISA310, VMULHSD, do_vx_helper, gen_helper_VMULHSD)
-TRANS_FLAGS2(ISA310, VMULHUW, do_vx_helper, gen_helper_VMULHUW)
-TRANS_FLAGS2(ISA310, VMULHUD, do_vx_helper, gen_helper_VMULHUD)
+static void do_vx_vmulhw_i64(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b, bool sign)
+{
+    TCGv_i64 hh, lh, temp;
+
+    uint64_t c;
+    hh = tcg_temp_new_i64();
+    lh = tcg_temp_new_i64();
+    temp = tcg_temp_new_i64();
+
+    c = 0xFFFFFFFF;
+
+    if (sign) {
+        tcg_gen_ext32s_i64(lh, a);
+        tcg_gen_ext32s_i64(temp, b);
+    } else {
+        tcg_gen_andi_i64(lh, a, c);
+        tcg_gen_andi_i64(temp, b, c);
+    }
+    tcg_gen_mul_i64(lh, lh, temp);
+
+    if (sign) {
+        tcg_gen_sari_i64(hh, a, 32);
+        tcg_gen_sari_i64(temp, b, 32);
+    } else {
+        tcg_gen_shri_i64(hh, a, 32);
+        tcg_gen_shri_i64(temp, b, 32);
+    }
+    tcg_gen_mul_i64(hh, hh, temp);
+
+    tcg_gen_shri_i64(lh, lh, 32);
+    tcg_gen_andi_i64(hh, hh, c << 32);
+    tcg_gen_or_i64(t, hh, lh);
+
+    tcg_temp_free_i64(hh);
+    tcg_temp_free_i64(lh);
+    tcg_temp_free_i64(temp);
+}
+
+static void do_vx_vmulhd_i64(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b, bool sign)
+{
+    TCGv_i64 tlow;
+
+    tlow  = tcg_temp_new_i64();
+    if (sign) {
+        tcg_gen_muls2_i64(tlow, t, a, b);
+    } else {
+        tcg_gen_mulu2_i64(tlow, t, a, b);
+    }
+
+    tcg_temp_free_i64(tlow);
+}
+
+static bool do_vx_mulh(DisasContext *ctx, arg_VX *a, bool sign,
+                       void (*func)(TCGv_i64, TCGv_i64, TCGv_i64, bool))
+{
+    REQUIRE_INSNS_FLAGS2(ctx, ISA310);
+    REQUIRE_VECTOR(ctx);
+
+    TCGv_i64 vra, vrb, vrt;
+    int i;
+
+    vra = tcg_temp_new_i64();
+    vrb = tcg_temp_new_i64();
+    vrt = tcg_temp_new_i64();
+
+    for (i = 0; i < 2; i++) {
+        get_avr64(vra, a->vra, i);
+        get_avr64(vrb, a->vrb, i);
+        get_avr64(vrt, a->vrt, i);
+
+        func(vrt, vra, vrb, sign);
+
+        set_avr64(a->vrt, vrt, i);
+    }
+
+    tcg_temp_free_i64(vra);
+    tcg_temp_free_i64(vrb);
+    tcg_temp_free_i64(vrt);
+
+    return true;
+
+}
+
+TRANS(VMULHSW, do_vx_mulh, true , do_vx_vmulhw_i64)
+TRANS(VMULHSD, do_vx_mulh, true , do_vx_vmulhd_i64)
+TRANS(VMULHUW, do_vx_mulh, false, do_vx_vmulhw_i64)
+TRANS(VMULHUD, do_vx_mulh, false, do_vx_vmulhd_i64)
 
 #undef GEN_VR_LDX
 #undef GEN_VR_STX
-- 
2.34.1