@@ -2574,3 +2574,24 @@ INSN_LASX(xvilvh_b, xxx)
INSN_LASX(xvilvh_h, xxx)
INSN_LASX(xvilvh_w, xxx)
INSN_LASX(xvilvh_d, xxx)
+
+INSN_LASX(xvshuf_b, xxxx)
+INSN_LASX(xvshuf_h, xxx)
+INSN_LASX(xvshuf_w, xxx)
+INSN_LASX(xvshuf_d, xxx)
+
+INSN_LASX(xvperm_w, xxx)
+
+INSN_LASX(xvshuf4i_b, xx_i)
+INSN_LASX(xvshuf4i_h, xx_i)
+INSN_LASX(xvshuf4i_w, xx_i)
+INSN_LASX(xvshuf4i_d, xx_i)
+
+INSN_LASX(xvpermi_w, xx_i)
+INSN_LASX(xvpermi_d, xx_i)
+INSN_LASX(xvpermi_q, xx_i)
+
+INSN_LASX(xvextrins_d, xx_i)
+INSN_LASX(xvextrins_w, xx_i)
+INSN_LASX(xvextrins_h, xx_i)
+INSN_LASX(xvextrins_b, xx_i)
@@ -1264,3 +1264,24 @@ DEF_HELPER_4(xvilvh_b, void, env, i32, i32, i32)
DEF_HELPER_4(xvilvh_h, void, env, i32, i32, i32)
DEF_HELPER_4(xvilvh_w, void, env, i32, i32, i32)
DEF_HELPER_4(xvilvh_d, void, env, i32, i32, i32)
+
+DEF_HELPER_5(xvshuf_b, void, env, i32, i32, i32, i32)
+DEF_HELPER_4(xvshuf_h, void, env, i32, i32, i32)
+DEF_HELPER_4(xvshuf_w, void, env, i32, i32, i32)
+DEF_HELPER_4(xvshuf_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(xvperm_w, void, env, i32, i32, i32)
+
+DEF_HELPER_4(xvshuf4i_b, void, env, i32, i32, i32)
+DEF_HELPER_4(xvshuf4i_h, void, env, i32, i32, i32)
+DEF_HELPER_4(xvshuf4i_w, void, env, i32, i32, i32)
+DEF_HELPER_4(xvshuf4i_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(xvpermi_w, void, env, i32, i32, i32)
+DEF_HELPER_4(xvpermi_d, void, env, i32, i32, i32)
+DEF_HELPER_4(xvpermi_q, void, env, i32, i32, i32)
+
+DEF_HELPER_4(xvextrins_d, void, env, i32, i32, i32)
+DEF_HELPER_4(xvextrins_w, void, env, i32, i32, i32)
+DEF_HELPER_4(xvextrins_h, void, env, i32, i32, i32)
+DEF_HELPER_4(xvextrins_b, void, env, i32, i32, i32)
@@ -3083,3 +3083,24 @@ TRANS(xvilvh_b, gen_xxx, gen_helper_xvilvh_b)
TRANS(xvilvh_h, gen_xxx, gen_helper_xvilvh_h)
TRANS(xvilvh_w, gen_xxx, gen_helper_xvilvh_w)
TRANS(xvilvh_d, gen_xxx, gen_helper_xvilvh_d)
+
+TRANS(xvshuf_b, gen_xxxx, gen_helper_xvshuf_b)
+TRANS(xvshuf_h, gen_xxx, gen_helper_xvshuf_h)
+TRANS(xvshuf_w, gen_xxx, gen_helper_xvshuf_w)
+TRANS(xvshuf_d, gen_xxx, gen_helper_xvshuf_d)
+
+TRANS(xvperm_w, gen_xxx, gen_helper_xvperm_w)
+
+TRANS(xvshuf4i_b, gen_xx_i, gen_helper_xvshuf4i_b)
+TRANS(xvshuf4i_h, gen_xx_i, gen_helper_xvshuf4i_h)
+TRANS(xvshuf4i_w, gen_xx_i, gen_helper_xvshuf4i_w)
+TRANS(xvshuf4i_d, gen_xx_i, gen_helper_xvshuf4i_d)
+
+TRANS(xvpermi_w, gen_xx_i, gen_helper_xvpermi_w)
+TRANS(xvpermi_d, gen_xx_i, gen_helper_xvpermi_d)
+TRANS(xvpermi_q, gen_xx_i, gen_helper_xvpermi_q)
+
+TRANS(xvextrins_b, gen_xx_i, gen_helper_xvextrins_b)
+TRANS(xvextrins_h, gen_xx_i, gen_helper_xvextrins_h)
+TRANS(xvextrins_w, gen_xx_i, gen_helper_xvextrins_w)
+TRANS(xvextrins_d, gen_xx_i, gen_helper_xvextrins_d)
@@ -2078,3 +2078,24 @@ xvilvh_b 0111 01010001 11000 ..... ..... ..... @xxx
xvilvh_h 0111 01010001 11001 ..... ..... ..... @xxx
xvilvh_w 0111 01010001 11010 ..... ..... ..... @xxx
xvilvh_d 0111 01010001 11011 ..... ..... ..... @xxx
+
+xvshuf_b 0000 11010110 ..... ..... ..... ..... @xxxx
+xvshuf_h 0111 01010111 10101 ..... ..... ..... @xxx
+xvshuf_w 0111 01010111 10110 ..... ..... ..... @xxx
+xvshuf_d 0111 01010111 10111 ..... ..... ..... @xxx
+
+xvperm_w 0111 01010111 11010 ..... ..... ..... @xxx
+
+xvshuf4i_b 0111 01111001 00 ........ ..... ..... @xx_ui8
+xvshuf4i_h 0111 01111001 01 ........ ..... ..... @xx_ui8
+xvshuf4i_w 0111 01111001 10 ........ ..... ..... @xx_ui8
+xvshuf4i_d 0111 01111001 11 ........ ..... ..... @xx_ui8
+
+xvpermi_w 0111 01111110 01 ........ ..... ..... @xx_ui8
+xvpermi_d 0111 01111110 10 ........ ..... ..... @xx_ui8
+xvpermi_q 0111 01111110 11 ........ ..... ..... @xx_ui8
+
+xvextrins_d 0111 01111000 00 ........ ..... ..... @xx_ui8
+xvextrins_w 0111 01111000 01 ........ ..... ..... @xx_ui8
+xvextrins_h 0111 01111000 10 ........ ..... ..... @xx_ui8
+xvextrins_b 0111 01111000 11 ........ ..... ..... @xx_ui8
@@ -2992,3 +2992,171 @@ XVILVH(xvilvh_b, 8, XB)
XVILVH(xvilvh_h, 16, XH)
XVILVH(xvilvh_w, 32, XW)
XVILVH(xvilvh_d, 64, XD)
+
+void HELPER(xvshuf_b)(CPULoongArchState *env,
+ uint32_t xd, uint32_t xj, uint32_t xk, uint32_t xa)
+{
+ int i, m;
+ XReg temp;
+ XReg *Xd = &(env->fpr[xd].xreg);
+ XReg *Xj = &(env->fpr[xj].xreg);
+ XReg *Xk = &(env->fpr[xk].xreg);
+ XReg *Xa = &(env->fpr[xa].xreg);
+
+ m = LASX_LEN / (8 * 2);
+ for (i = 0; i < 2 * m ; i++) {
+ uint64_t k = (uint8_t)Xa->XB(i) % (2 * m);
+ if (i < m) {
+ temp.XB(i) = k < m ? Xk->XB(k) : Xj->XB(k - m);
+ } else {
+ temp.XB(i) = k < m ? Xk->XB(k + m) : Xj->XB(k);
+ }
+ }
+ *Xd = temp;
+}
+
+#define XVSHUF(NAME, BIT, E) \
+void HELPER(NAME)(CPULoongArchState *env, \
+ uint32_t xd, uint32_t xj, uint32_t xk) \
+{ \
+ int i, m; \
+ XReg temp; \
+ XReg *Xd = &(env->fpr[xd].xreg); \
+ XReg *Xj = &(env->fpr[xj].xreg); \
+ XReg *Xk = &(env->fpr[xk].xreg); \
+ \
+ m = LASX_LEN / (BIT * 2); \
+ for (i = 0; i < m * 2; i++) { \
+ uint64_t k = (uint8_t)Xd->E(i) % (2 * m); \
+ if (i < m) { \
+ temp.E(i) = k < m ? Xk->E(k) : Xj->E(k - m); \
+ } else { \
+ temp.E(i) = k < m ? Xk->E(k + m) : Xj->E(k); \
+ } \
+ } \
+ *Xd = temp; \
+}
+
+XVSHUF(xvshuf_h, 16, XH)
+XVSHUF(xvshuf_w, 32, XW)
+XVSHUF(xvshuf_d, 64, XD)
+
+void HELPER(xvperm_w)(CPULoongArchState *env,
+ uint32_t xd, uint32_t xj, uint32_t xk)
+{
+ int i, m;
+ XReg temp;
+ XReg *Xd = &(env->fpr[xd].xreg);
+ XReg *Xj = &(env->fpr[xj].xreg);
+ XReg *Xk = &(env->fpr[xk].xreg);
+
+ m = LASX_LEN / 32;
+ for (i = 0; i < m ; i++) {
+ uint64_t k = (uint8_t)Xk->XW(i) % 8;
+ temp.XW(i) = Xj->XW(k);
+ }
+ *Xd = temp;
+}
+
+#define XVSHUF4I(NAME, BIT, E) \
+void HELPER(NAME)(CPULoongArchState *env, \
+ uint32_t xd, uint32_t xj, uint32_t imm) \
+{ \
+ int i, m; \
+ XReg temp; \
+ XReg *Xd = &(env->fpr[xd].xreg); \
+ XReg *Xj = &(env->fpr[xj].xreg); \
+ \
+ m = LASX_LEN / BIT; \
+ for (i = 0; i < m; i++) { \
+ if (i < (m / 2)) { \
+ temp.E(i) = Xj->E(SHF_POS(i, imm)); \
+ } else { \
+ temp.E(i) = Xj->E(SHF_POS(i - (m / 2), imm) + (m / 2)); \
+ } \
+ } \
+ *Xd = temp; \
+}
+
+XVSHUF4I(xvshuf4i_b, 8, XB)
+XVSHUF4I(xvshuf4i_h, 16, XH)
+XVSHUF4I(xvshuf4i_w, 32, XW)
+
+void HELPER(xvshuf4i_d)(CPULoongArchState *env,
+ uint32_t xd, uint32_t xj, uint32_t imm)
+{
+ XReg *Xd = &(env->fpr[xd].xreg);
+ XReg *Xj = &(env->fpr[xj].xreg);
+
+ XReg temp;
+ temp.XD(0) = (imm & 2 ? Xj : Xd)->XD(imm & 1);
+ temp.XD(1) = (imm & 8 ? Xj : Xd)->XD((imm >> 2) & 1);
+ temp.XD(2) = (imm & 2 ? Xj : Xd)->XD((imm & 1) + 2);
+ temp.XD(3) = (imm & 8 ? Xj : Xd)->XD(((imm >> 2) & 1) + 2);
+ *Xd = temp;
+}
+
+void HELPER(xvpermi_w)(CPULoongArchState *env,
+ uint32_t xd, uint32_t xj, uint32_t imm)
+{
+ XReg temp;
+ XReg *Xd = &(env->fpr[xd].xreg);
+ XReg *Xj = &(env->fpr[xj].xreg);
+
+ temp.XW(0) = Xj->XW(imm & 0x3);
+ temp.XW(1) = Xj->XW((imm >> 2) & 0x3);
+ temp.XW(2) = Xd->XW((imm >> 4) & 0x3);
+ temp.XW(3) = Xd->XW((imm >> 6) & 0x3);
+ temp.XW(4) = Xj->XW((imm & 0x3) + 4);
+ temp.XW(5) = Xj->XW(((imm >> 2) & 0x3) + 4);
+ temp.XW(6) = Xd->XW(((imm >> 4) & 0x3) + 4);
+ temp.XW(7) = Xd->XW(((imm >> 6) & 0x3) + 4);
+ *Xd = temp;
+}
+
+void HELPER(xvpermi_d)(CPULoongArchState *env,
+ uint32_t xd, uint32_t xj, uint32_t imm)
+{
+ XReg temp;
+ XReg *Xd = &(env->fpr[xd].xreg);
+ XReg *Xj = &(env->fpr[xj].xreg);
+
+ temp.XD(0) = Xj->XD(imm & 0x3);
+ temp.XD(1) = Xj->XD((imm >> 2) & 0x3);
+ temp.XD(2) = Xj->XD((imm >> 4) & 0x3);
+ temp.XD(3) = Xj->XD((imm >> 6) & 0x3);
+ *Xd = temp;
+}
+
+void HELPER(xvpermi_q)(CPULoongArchState *env,
+ uint32_t xd, uint32_t xj, uint32_t imm)
+{
+ XReg temp;
+ XReg *Xd = &(env->fpr[xd].xreg);
+ XReg *Xj = &(env->fpr[xj].xreg);
+
+ temp.XQ(0) = (imm & 0x3) > 1 ? Xd->XQ((imm & 0x3) - 2) : Xj->XQ(imm & 0x3);
+ temp.XQ(1) = ((imm >> 4) & 0x3) > 1 ? Xd->XQ(((imm >> 4) & 0x3) - 2) :
+ Xj->XQ((imm >> 4) & 0x3);
+ *Xd = temp;
+}
+
+#define XVEXTRINS(NAME, BIT, E, MASK) \
+void HELPER(NAME)(CPULoongArchState *env, \
+ uint32_t xd, uint32_t xj, uint32_t imm) \
+{ \
+ int ins, extr, m; \
+ XReg *Xd = &(env->fpr[xd].xreg); \
+ XReg *Xj = &(env->fpr[xj].xreg); \
+ \
+ m = LASX_LEN / (BIT * 2); \
+ ins = (imm >> 4) & MASK; \
+ extr = imm & MASK; \
+ Xd->E(ins) = Xj->E(extr); \
+ Xd->E(ins + m) = Xj->E(extr + m); \
+}
+
+XVEXTRINS(xvextrins_b, 8, XB, 0xf)
+XVEXTRINS(xvextrins_h, 16, XH, 0x7)
+XVEXTRINS(xvextrins_w, 32, XW, 0x3)
+XVEXTRINS(xvextrins_d, 64, XD, 0x1)
@@ -2909,8 +2909,7 @@ void HELPER(NAME)(CPULoongArchState *env, \
VReg *Vj = &(env->fpr[vj].vreg); \
\
for (i = 0; i < LSX_LEN/BIT; i++) { \
- temp.E(i) = Vj->E(((i) & 0xfc) + (((imm) >> \
- (2 * ((i) & 0x03))) & 0x03)); \
+ temp.E(i) = Vj->E(SHF_POS(i, imm)); \
} \
*Vd = temp; \
}
@@ -96,6 +96,8 @@
#define VSLE(a, b) (a <= b ? -1 : 0)
#define VSLT(a, b) (a < b ? -1 : 0)
+#define SHF_POS(i, imm) (((i) & 0xfc) + (((imm) >> (2 * ((i) & 0x03))) & 0x03))
+
uint64_t do_vmskltz_b(int64_t val);
uint64_t do_vmskltz_h(int64_t val);
uint64_t do_vmskltz_w(int64_t val);
This patch includes: - XVSHUF.{B/H/W/D}; - XVPERM.W; - XVSHUF4i.{B/H/W/D}; - XVPERMI.{W/D/Q}; - XVEXTRINS.{B/H/W/D}. Signed-off-by: Song Gao <gaosong@loongson.cn> --- target/loongarch/disas.c | 21 +++ target/loongarch/helper.h | 21 +++ target/loongarch/insn_trans/trans_lasx.c.inc | 21 +++ target/loongarch/insns.decode | 21 +++ target/loongarch/lasx_helper.c | 168 +++++++++++++++++++ target/loongarch/lsx_helper.c | 3 +- target/loongarch/vec.h | 2 + 7 files changed, 255 insertions(+), 2 deletions(-)