target/loongarch: Implement xvfcmp
This patch includes:
- XVFCMP.cond.{S/D}.
Signed-off-by: Song Gao <gaosong@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230914022645.1151356-50-gaosong@loongson.cn>
diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index 48e0b55..4ab51b7 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -2385,6 +2385,99 @@
INSN_LASX(xvslti_wu, vv_i)
INSN_LASX(xvslti_du, vv_i)
+#define output_xvfcmp(C, PREFIX, SUFFIX) \
+{ \
+ (C)->info->fprintf_func((C)->info->stream, "%08x %s%s\tx%d, x%d, x%d", \
+ (C)->insn, PREFIX, SUFFIX, a->vd, \
+ a->vj, a->vk); \
+}
+static bool output_xxx_fcond(DisasContext *ctx, arg_vvv_fcond * a,
+ const char *suffix)
+{
+ bool ret = true;
+ switch (a->fcond) {
+ case 0x0:
+ output_xvfcmp(ctx, "xvfcmp_caf_", suffix);
+ break;
+ case 0x1:
+ output_xvfcmp(ctx, "xvfcmp_saf_", suffix);
+ break;
+ case 0x2:
+ output_xvfcmp(ctx, "xvfcmp_clt_", suffix);
+ break;
+ case 0x3:
+ output_xvfcmp(ctx, "xvfcmp_slt_", suffix);
+ break;
+ case 0x4:
+ output_xvfcmp(ctx, "xvfcmp_ceq_", suffix);
+ break;
+ case 0x5:
+ output_xvfcmp(ctx, "xvfcmp_seq_", suffix);
+ break;
+ case 0x6:
+ output_xvfcmp(ctx, "xvfcmp_cle_", suffix);
+ break;
+ case 0x7:
+ output_xvfcmp(ctx, "xvfcmp_sle_", suffix);
+ break;
+ case 0x8:
+ output_xvfcmp(ctx, "xvfcmp_cun_", suffix);
+ break;
+ case 0x9:
+ output_xvfcmp(ctx, "xvfcmp_sun_", suffix);
+ break;
+ case 0xA:
+ output_xvfcmp(ctx, "xvfcmp_cult_", suffix);
+ break;
+ case 0xB:
+ output_xvfcmp(ctx, "xvfcmp_sult_", suffix);
+ break;
+ case 0xC:
+ output_xvfcmp(ctx, "xvfcmp_cueq_", suffix);
+ break;
+ case 0xD:
+ output_xvfcmp(ctx, "xvfcmp_sueq_", suffix);
+ break;
+ case 0xE:
+ output_xvfcmp(ctx, "xvfcmp_cule_", suffix);
+ break;
+ case 0xF:
+ output_xvfcmp(ctx, "xvfcmp_sule_", suffix);
+ break;
+ case 0x10:
+ output_xvfcmp(ctx, "xvfcmp_cne_", suffix);
+ break;
+ case 0x11:
+ output_xvfcmp(ctx, "xvfcmp_sne_", suffix);
+ break;
+ case 0x14:
+ output_xvfcmp(ctx, "xvfcmp_cor_", suffix);
+ break;
+ case 0x15:
+ output_xvfcmp(ctx, "xvfcmp_sor_", suffix);
+ break;
+ case 0x18:
+ output_xvfcmp(ctx, "xvfcmp_cune_", suffix);
+ break;
+ case 0x19:
+ output_xvfcmp(ctx, "xvfcmp_sune_", suffix);
+ break;
+ default:
+ ret = false;
+ }
+ return ret;
+}
+
+#define LASX_FCMP_INSN(suffix) \
+static bool trans_xvfcmp_cond_##suffix(DisasContext *ctx, \
+ arg_vvv_fcond * a) \
+{ \
+ return output_xxx_fcond(ctx, a, #suffix); \
+}
+
+LASX_FCMP_INSN(s)
+LASX_FCMP_INSN(d)
+
INSN_LASX(xvreplgr2vr_b, vr)
INSN_LASX(xvreplgr2vr_h, vr)
INSN_LASX(xvreplgr2vr_w, vr)
diff --git a/target/loongarch/helper.h b/target/loongarch/helper.h
index e9c5412..b54ce68 100644
--- a/target/loongarch/helper.h
+++ b/target/loongarch/helper.h
@@ -652,10 +652,10 @@
DEF_HELPER_FLAGS_4(vslti_wu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_4(vslti_du, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_5(vfcmp_c_s, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(vfcmp_s_s, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(vfcmp_c_d, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(vfcmp_s_d, void, env, i32, i32, i32, i32)
+DEF_HELPER_6(vfcmp_c_s, void, env, i32, i32, i32, i32, i32)
+DEF_HELPER_6(vfcmp_s_s, void, env, i32, i32, i32, i32, i32)
+DEF_HELPER_6(vfcmp_c_d, void, env, i32, i32, i32, i32, i32)
+DEF_HELPER_6(vfcmp_s_d, void, env, i32, i32, i32, i32, i32)
DEF_HELPER_FLAGS_4(vbitseli_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
diff --git a/target/loongarch/insn_trans/trans_vec.c.inc b/target/loongarch/insn_trans/trans_vec.c.inc
index 63d71e2..9b89b81 100644
--- a/target/loongarch/insn_trans/trans_vec.c.inc
+++ b/target/loongarch/insn_trans/trans_vec.c.inc
@@ -4645,52 +4645,51 @@
TRANS(xvslti_wu, LASX, do_xcmpi, MO_32, TCG_COND_LTU)
TRANS(xvslti_du, LASX, do_xcmpi, MO_64, TCG_COND_LTU)
-static bool trans_vfcmp_cond_s(DisasContext *ctx, arg_vvv_fcond *a)
+static bool do_vfcmp_cond_s(DisasContext *ctx, arg_vvv_fcond *a, uint32_t sz)
{
uint32_t flags;
- void (*fn)(TCGv_env, TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32);
+ void (*fn)(TCGv_env, TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32);
TCGv_i32 vd = tcg_constant_i32(a->vd);
TCGv_i32 vj = tcg_constant_i32(a->vj);
TCGv_i32 vk = tcg_constant_i32(a->vk);
+ TCGv_i32 oprsz = tcg_constant_i32(sz);
- if (!avail_LSX(ctx)) {
- return false;
- }
-
- if (!check_vec(ctx, 16)) {
+ if (!check_vec(ctx, sz)) {
return true;
}
fn = (a->fcond & 1 ? gen_helper_vfcmp_s_s : gen_helper_vfcmp_c_s);
flags = get_fcmp_flags(a->fcond >> 1);
- fn(cpu_env, vd, vj, vk, tcg_constant_i32(flags));
+ fn(cpu_env, oprsz, vd, vj, vk, tcg_constant_i32(flags));
return true;
}
-static bool trans_vfcmp_cond_d(DisasContext *ctx, arg_vvv_fcond *a)
+static bool do_vfcmp_cond_d(DisasContext *ctx, arg_vvv_fcond *a, uint32_t sz)
{
uint32_t flags;
- void (*fn)(TCGv_env, TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32);
+ void (*fn)(TCGv_env, TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32);
TCGv_i32 vd = tcg_constant_i32(a->vd);
TCGv_i32 vj = tcg_constant_i32(a->vj);
TCGv_i32 vk = tcg_constant_i32(a->vk);
+ TCGv_i32 oprsz = tcg_constant_i32(sz);
- if (!avail_LSX(ctx)) {
- return false;
- }
-
- if (!check_vec(ctx, 16)) {
+ if (!check_vec(ctx, sz)) {
return true;
}
fn = (a->fcond & 1 ? gen_helper_vfcmp_s_d : gen_helper_vfcmp_c_d);
flags = get_fcmp_flags(a->fcond >> 1);
- fn(cpu_env, vd, vj, vk, tcg_constant_i32(flags));
+ fn(cpu_env, oprsz, vd, vj, vk, tcg_constant_i32(flags));
return true;
}
+TRANS(vfcmp_cond_s, LSX, do_vfcmp_cond_s, 16)
+TRANS(vfcmp_cond_d, LSX, do_vfcmp_cond_d, 16)
+TRANS(xvfcmp_cond_s, LASX, do_vfcmp_cond_s, 32)
+TRANS(xvfcmp_cond_d, LASX, do_vfcmp_cond_d, 32)
+
static bool trans_vbitsel_v(DisasContext *ctx, arg_vvvv *a)
{
if (!avail_LSX(ctx)) {
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index 82c26a3..0d46bd5 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -1958,6 +1958,9 @@
xvslti_wu 0111 01101000 10010 ..... ..... ..... @vv_ui5
xvslti_du 0111 01101000 10011 ..... ..... ..... @vv_ui5
+xvfcmp_cond_s 0000 11001001 ..... ..... ..... ..... @vvv_fcond
+xvfcmp_cond_d 0000 11001010 ..... ..... ..... ..... @vvv_fcond
+
xvreplgr2vr_b 0111 01101001 11110 00000 ..... ..... @vr
xvreplgr2vr_h 0111 01101001 11110 00001 ..... ..... @vr
xvreplgr2vr_w 0111 01101001 11110 00010 ..... ..... @vr
diff --git a/target/loongarch/vec_helper.c b/target/loongarch/vec_helper.c
index 960b3d1..5188b7f 100644
--- a/target/loongarch/vec_helper.c
+++ b/target/loongarch/vec_helper.c
@@ -3122,7 +3122,7 @@
}
#define VFCMP(NAME, BIT, E, FN) \
-void HELPER(NAME)(CPULoongArchState *env, \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t oprsz, \
uint32_t vd, uint32_t vj, uint32_t vk, uint32_t flags) \
{ \
int i; \
@@ -3132,7 +3132,7 @@
VReg *Vk = &(env->fpr[vk].vreg); \
\
vec_clear_cause(env); \
- for (i = 0; i < LSX_LEN/BIT ; i++) { \
+ for (i = 0; i < oprsz / (BIT / 8); i++) { \
FloatRelation cmp; \
cmp = FN(Vj->E(i), Vk->E(i), &env->fp_status); \
t.E(i) = vfcmp_common(env, cmp, flags); \
