target/loongarch: Implement xvsat
This patch includes:
- XVSAT.{B/H/W/D}[U].
Signed-off-by: Song Gao <gaosong@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230914022645.1151356-29-gaosong@loongson.cn>
diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index d932318..4e54dcd 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -1979,6 +1979,15 @@
INSN_LASX(xvmod_wu, vvv)
INSN_LASX(xvmod_du, vvv)
+INSN_LASX(xvsat_b, vv_i)
+INSN_LASX(xvsat_h, vv_i)
+INSN_LASX(xvsat_w, vv_i)
+INSN_LASX(xvsat_d, vv_i)
+INSN_LASX(xvsat_bu, vv_i)
+INSN_LASX(xvsat_hu, vv_i)
+INSN_LASX(xvsat_wu, vv_i)
+INSN_LASX(xvsat_du, vv_i)
+
INSN_LASX(xvreplgr2vr_b, vr)
INSN_LASX(xvreplgr2vr_h, vr)
INSN_LASX(xvreplgr2vr_w, vr)
diff --git a/target/loongarch/insn_trans/trans_vec.c.inc b/target/loongarch/insn_trans/trans_vec.c.inc
index a22ced9..a6c6675 100644
--- a/target/loongarch/insn_trans/trans_vec.c.inc
+++ b/target/loongarch/insn_trans/trans_vec.c.inc
@@ -3267,6 +3267,10 @@
TRANS(vsat_h, LSX, gvec_vv_i, MO_16, do_vsat_s)
TRANS(vsat_w, LSX, gvec_vv_i, MO_32, do_vsat_s)
TRANS(vsat_d, LSX, gvec_vv_i, MO_64, do_vsat_s)
+TRANS(xvsat_b, LASX, gvec_xx_i, MO_8, do_vsat_s)
+TRANS(xvsat_h, LASX, gvec_xx_i, MO_16, do_vsat_s)
+TRANS(xvsat_w, LASX, gvec_xx_i, MO_32, do_vsat_s)
+TRANS(xvsat_d, LASX, gvec_xx_i, MO_64, do_vsat_s)
static void gen_vsat_u(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec max)
{
@@ -3316,6 +3320,10 @@
TRANS(vsat_hu, LSX, gvec_vv_i, MO_16, do_vsat_u)
TRANS(vsat_wu, LSX, gvec_vv_i, MO_32, do_vsat_u)
TRANS(vsat_du, LSX, gvec_vv_i, MO_64, do_vsat_u)
+TRANS(xvsat_bu, LASX, gvec_xx_i, MO_8, do_vsat_u)
+TRANS(xvsat_hu, LASX, gvec_xx_i, MO_16, do_vsat_u)
+TRANS(xvsat_wu, LASX, gvec_xx_i, MO_32, do_vsat_u)
+TRANS(xvsat_du, LASX, gvec_xx_i, MO_64, do_vsat_u)
TRANS(vexth_h_b, LSX, gen_vv, gen_helper_vexth_h_b)
TRANS(vexth_w_h, LSX, gen_vv, gen_helper_vexth_w_h)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index fa25c87..e366cf7 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -1562,6 +1562,15 @@
xvmod_wu 0111 01001110 01110 ..... ..... ..... @vvv
xvmod_du 0111 01001110 01111 ..... ..... ..... @vvv
+xvsat_b 0111 01110010 01000 01 ... ..... ..... @vv_ui3
+xvsat_h 0111 01110010 01000 1 .... ..... ..... @vv_ui4
+xvsat_w 0111 01110010 01001 ..... ..... ..... @vv_ui5
+xvsat_d 0111 01110010 0101 ...... ..... ..... @vv_ui6
+xvsat_bu 0111 01110010 10000 01 ... ..... ..... @vv_ui3
+xvsat_hu 0111 01110010 10000 1 .... ..... ..... @vv_ui4
+xvsat_wu 0111 01110010 10001 ..... ..... ..... @vv_ui5
+xvsat_du 0111 01110010 1001 ...... ..... ..... @vv_ui6
+
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 9cf979a..f2e1934 100644
--- a/target/loongarch/vec_helper.c
+++ b/target/loongarch/vec_helper.c
@@ -677,18 +677,19 @@
VDIV(vmod_wu, 32, UW, DO_REMU)
VDIV(vmod_du, 64, UD, DO_REMU)
-#define VSAT_S(NAME, BIT, E) \
-void HELPER(NAME)(void *vd, void *vj, uint64_t max, uint32_t v) \
-{ \
- int i; \
- VReg *Vd = (VReg *)vd; \
- VReg *Vj = (VReg *)vj; \
- typedef __typeof(Vd->E(0)) TD; \
- \
- for (i = 0; i < LSX_LEN/BIT; i++) { \
- Vd->E(i) = Vj->E(i) > (TD)max ? (TD)max : \
- Vj->E(i) < (TD)~max ? (TD)~max: Vj->E(i); \
- } \
+#define VSAT_S(NAME, BIT, E) \
+void HELPER(NAME)(void *vd, void *vj, uint64_t max, uint32_t desc) \
+{ \
+ int i; \
+ VReg *Vd = (VReg *)vd; \
+ VReg *Vj = (VReg *)vj; \
+ typedef __typeof(Vd->E(0)) TD; \
+ int oprsz = simd_oprsz(desc); \
+ \
+ for (i = 0; i < oprsz / (BIT / 8); i++) { \
+ Vd->E(i) = Vj->E(i) > (TD)max ? (TD)max : \
+ Vj->E(i) < (TD)~max ? (TD)~max: Vj->E(i); \
+ } \
}
VSAT_S(vsat_b, 8, B)
@@ -696,17 +697,18 @@
VSAT_S(vsat_w, 32, W)
VSAT_S(vsat_d, 64, D)
-#define VSAT_U(NAME, BIT, E) \
-void HELPER(NAME)(void *vd, void *vj, uint64_t max, uint32_t v) \
-{ \
- int i; \
- VReg *Vd = (VReg *)vd; \
- VReg *Vj = (VReg *)vj; \
- typedef __typeof(Vd->E(0)) TD; \
- \
- for (i = 0; i < LSX_LEN/BIT; i++) { \
- Vd->E(i) = Vj->E(i) > (TD)max ? (TD)max : Vj->E(i); \
- } \
+#define VSAT_U(NAME, BIT, E) \
+void HELPER(NAME)(void *vd, void *vj, uint64_t max, uint32_t desc) \
+{ \
+ int i; \
+ VReg *Vd = (VReg *)vd; \
+ VReg *Vj = (VReg *)vj; \
+ typedef __typeof(Vd->E(0)) TD; \
+ int oprsz = simd_oprsz(desc); \
+ \
+ for (i = 0; i < oprsz / (BIT / 8); i++) { \
+ Vd->E(i) = Vj->E(i) > (TD)max ? (TD)max : Vj->E(i); \
+ } \
}
VSAT_U(vsat_bu, 8, UB)
