@@ -1753,6 +1753,16 @@ static void output_xxr(DisasContext *ctx, arg_xxr *a, const char *mnemonic)
output(ctx, mnemonic, "x%d, x%d, r%d", a->xd, a->xj, a->rk);
}
+static void output_xrr(DisasContext *ctx, arg_xrr *a, const char *mnemonic)
+{
+ output(ctx, mnemonic, "x%d, r%d, r%d", a->xd, a->rj, a->rk);
+}
+
+static void output_xr_ii(DisasContext *ctx, arg_xr_ii *a, const char *mnemonic)
+{
+ output(ctx, mnemonic, "x%d, r%d, 0x%x, 0x%x", a->xd, a->rj, a->imm, a->imm2);
+}
+
INSN_LASX(xvadd_b, xxx)
INSN_LASX(xvadd_h, xxx)
INSN_LASX(xvadd_w, xxx)
@@ -2595,3 +2605,17 @@ INSN_LASX(xvextrins_d, xx_i)
INSN_LASX(xvextrins_w, xx_i)
INSN_LASX(xvextrins_h, xx_i)
INSN_LASX(xvextrins_b, xx_i)
+
+INSN_LASX(xvld, xr_i)
+INSN_LASX(xvst, xr_i)
+INSN_LASX(xvldx, xrr)
+INSN_LASX(xvstx, xrr)
+
+INSN_LASX(xvldrepl_d, xr_i)
+INSN_LASX(xvldrepl_w, xr_i)
+INSN_LASX(xvldrepl_h, xr_i)
+INSN_LASX(xvldrepl_b, xr_i)
+INSN_LASX(xvstelm_d, xr_ii)
+INSN_LASX(xvstelm_w, xr_ii)
+INSN_LASX(xvstelm_h, xr_ii)
+INSN_LASX(xvstelm_b, xr_ii)
@@ -1285,3 +1285,6 @@ 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)
+
+DEF_HELPER_3(xvld_b, void, env, i32, tl)
+DEF_HELPER_3(xvst_b, void, env, i32, tl)
@@ -3104,3 +3104,100 @@ 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)
+
+static bool gen_lasx_memory(DisasContext *ctx, arg_xr_i * a,
+ void (*func)(TCGv_ptr, TCGv_i32, TCGv))
+{
+ TCGv_i32 xd = tcg_constant_i32(a->xd);
+ TCGv addr = gpr_src(ctx, a->rj, EXT_NONE);
+ TCGv temp = NULL;
+
+ CHECK_ASXE;
+
+ if (a->imm) {
+ temp = tcg_temp_new();
+ tcg_gen_addi_tl(temp, addr, a->imm);
+ addr = temp;
+ }
+
+ func(cpu_env, xd, addr);
+ return true;
+}
+
+TRANS(xvld, gen_lasx_memory, gen_helper_xvld_b)
+TRANS(xvst, gen_lasx_memory, gen_helper_xvst_b)
+
+static bool gen_lasx_memoryx(DisasContext *ctx, arg_xrr *a,
+ void (*func)(TCGv_ptr, TCGv_i32, TCGv))
+{
+ TCGv_i32 xd = tcg_constant_i32(a->xd);
+ TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
+ TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+ TCGv addr = tcg_temp_new();
+
+ CHECK_ASXE;
+
+ tcg_gen_add_tl(addr, src1, src2);
+ func(cpu_env, xd, addr);
+ return true;
+}
+
+TRANS(xvldx, gen_lasx_memoryx, gen_helper_xvld_b)
+TRANS(xvstx, gen_lasx_memoryx, gen_helper_xvst_b)
+
+#define XVLDREPL(NAME, MO) \
+static bool trans_## NAME(DisasContext *ctx, arg_xr_i * a) \
+{ \
+ TCGv addr, temp; \
+ TCGv_i64 val; \
+ \
+ CHECK_ASXE; \
+ \
+ addr = gpr_src(ctx, a->rj, EXT_NONE); \
+ val = tcg_temp_new_i64(); \
+ \
+ if (a->imm) { \
+ temp = tcg_temp_new(); \
+ tcg_gen_addi_tl(temp, addr, a->imm); \
+ addr = temp; \
+ } \
+ \
+ tcg_gen_qemu_ld_i64(val, addr, ctx->mem_idx, MO); \
+ tcg_gen_gvec_dup_i64(MO, vec_full_offset(a->xd), 32, ctx->vl / 8, val); \
+ \
+ return true; \
+}
+
+XVLDREPL(xvldrepl_b, MO_8)
+XVLDREPL(xvldrepl_h, MO_16)
+XVLDREPL(xvldrepl_w, MO_32)
+XVLDREPL(xvldrepl_d, MO_64)
+
+#define XVSTELM(NAME, MO, E) \
+static bool trans_## NAME(DisasContext *ctx, arg_xr_ii * a) \
+{ \
+ TCGv addr, temp; \
+ TCGv_i64 val; \
+ \
+ CHECK_ASXE; \
+ \
+ addr = gpr_src(ctx, a->rj, EXT_NONE); \
+ val = tcg_temp_new_i64(); \
+ \
+ if (a->imm) { \
+ temp = tcg_temp_new(); \
+ tcg_gen_addi_tl(temp, addr, a->imm); \
+ addr = temp; \
+ } \
+ \
+ tcg_gen_ld_i64(val, cpu_env, \
+ offsetof(CPULoongArchState, fpr[a->xd].xreg.E(a->imm2))); \
+ tcg_gen_qemu_st_i64(val, addr, ctx->mem_idx, MO); \
+ \
+ return true; \
+}
+
+XVSTELM(xvstelm_b, MO_8, XB)
+XVSTELM(xvstelm_h, MO_16, XH)
+XVSTELM(xvstelm_w, MO_32, XW)
+XVSTELM(xvstelm_d, MO_64, XD)
@@ -1312,6 +1312,8 @@ vstelm_b 0011 000110 .... ........ ..... ..... @vr_i8i4
&xr_i xd rj imm
&rx_i rd xj imm
&xxr xd xj rk
+&xrr xd rj rk
+&xr_ii xd rj imm imm2
#
# LASX Formats
@@ -1338,6 +1340,15 @@ vstelm_b 0011 000110 .... ........ ..... ..... @vr_i8i4
@rx_ui3 .... ........ ..... .. imm:3 xj:5 rd:5 &rx_i
@rx_ui2 .... ........ ..... ... imm:2 xj:5 rd:5 &rx_i
@xxr .... ........ ..... rk:5 xj:5 xd:5 &xxr
+@xr_i9 .... ........ . ......... rj:5 xd:5 &xr_i imm=%i9s3
+@xr_i10 .... ........ .......... rj:5 xd:5 &xr_i imm=%i10s2
+@xr_i11 .... ....... ........... rj:5 xd:5 &xr_i imm=%i11s1
+@xr_i12 .... ...... imm:s12 rj:5 xd:5 &xr_i
+@xr_i8i2 .... ........ imm2:2 ........ rj:5 xd:5 &xr_ii imm=%i8s3
+@xr_i8i3 .... ....... imm2:3 ........ rj:5 xd:5 &xr_ii imm=%i8s2
+@xr_i8i4 .... ...... imm2:4 ........ rj:5 xd:5 &xr_ii imm=%i8s1
+@xr_i8i5 .... ..... imm2:5 imm:s8 rj:5 xd:5 &xr_ii
+@xrr .... ........ ..... rk:5 rj:5 xd:5 &xrr
xvadd_b 0111 01000000 10100 ..... ..... ..... @xxx
xvadd_h 0111 01000000 10101 ..... ..... ..... @xxx
@@ -2099,3 +2110,17 @@ 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
+
+xvld 0010 110010 ............ ..... ..... @xr_i12
+xvst 0010 110011 ............ ..... ..... @xr_i12
+xvldx 0011 10000100 10000 ..... ..... ..... @xrr
+xvstx 0011 10000100 11000 ..... ..... ..... @xrr
+
+xvldrepl_d 0011 00100001 0 ......... ..... ..... @xr_i9
+xvldrepl_w 0011 00100010 .......... ..... ..... @xr_i10
+xvldrepl_h 0011 0010010 ........... ..... ..... @xr_i11
+xvldrepl_b 0011 001010 ............ ..... ..... @xr_i12
+xvstelm_d 0011 00110001 .. ........ ..... ..... @xr_i8i2
+xvstelm_w 0011 0011001 ... ........ ..... ..... @xr_i8i3
+xvstelm_h 0011 001101 .... ........ ..... ..... @xr_i8i4
+xvstelm_b 0011 00111 ..... ........ ..... ..... @xr_i8i5
@@ -12,6 +12,9 @@
#include "fpu/softfloat.h"
#include "internals.h"
#include "vec.h"
+#include "tcg/tcg.h"
+#include "exec/cpu_ldst.h"
+#include "tcg/tcg-ldst.h"
#define XDO_ODD_EVEN(NAME, BIT, E1, E2, DO_OP) \
void HELPER(NAME)(CPULoongArchState *env, \
@@ -3160,3 +3163,59 @@ XVEXTRINS(xvextrins_b, 8, XB, 0xf)
XVEXTRINS(xvextrins_h, 16, XH, 0x7)
XVEXTRINS(xvextrins_w, 32, XW, 0x3)
XVEXTRINS(xvextrins_d, 64, XD, 0x1)
+
+void helper_xvld_b(CPULoongArchState *env, uint32_t xd, target_ulong addr)
+{
+ int i;
+ XReg *Xd = &(env->fpr[xd].xreg);
+#if !defined(CONFIG_USER_ONLY)
+ MemOpIdx oi = make_memop_idx(MO_TE | MO_UNALN, cpu_mmu_index(env, false));
+
+ for (i = 0; i < LASX_LEN / 8; i++) {
+ Xd->XB(i) = helper_ldub_mmu(env, addr + i, oi, GETPC());
+ }
+#else
+ for (i = 0; i < LASX_LEN / 8; i++) {
+ Xd->XB(i) = cpu_ldub_data(env, addr + i);
+ }
+#endif
+}
+
+#define LASX_PAGESPAN(x) \
+ ((((x) & ~TARGET_PAGE_MASK) + (LASX_LEN / 8) - 1) >= TARGET_PAGE_SIZE)
+
+static inline void ensure_lasx_writable_pages(CPULoongArchState *env,
+ target_ulong addr,
+ int mmu_idx,
+ uintptr_t retaddr)
+{
+#ifndef CONFIG_USER_ONLY
+ /* FIXME: Probe the actual accesses (pass and use a size) */
+ if (unlikely(LASX_PAGESPAN(addr))) {
+ /* first page */
+ probe_write(env, addr, 0, mmu_idx, retaddr);
+ /* second page */
+ addr = (addr & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE;
+ probe_write(env, addr, 0, mmu_idx, retaddr);
+ }
+#endif
+}
+
+void helper_xvst_b(CPULoongArchState *env, uint32_t xd, target_ulong addr)
+{
+ int i;
+ XReg *Xd = &(env->fpr[xd].xreg);
+ int mmu_idx = cpu_mmu_index(env, false);
+
+ ensure_lasx_writable_pages(env, addr, mmu_idx, GETPC());
+#if !defined(CONFIG_USER_ONLY)
+ MemOpIdx oi = make_memop_idx(MO_TE | MO_UNALN, mmu_idx);
+ for (i = 0; i < LASX_LEN / 8; i++) {
+ helper_stb_mmu(env, addr + i, Xd->XB(i), oi, GETPC());
+ }
+#else
+ for (i = 0; i < LASX_LEN / 8; i++) {
+ cpu_stb_data(env, addr + i, Xd->XB(i));
+ }
+#endif
+}
This patch includes: - XVLD[X], XVST[X]; - XVLDREPL.{B/H/W/D}; - XVSTELM.{B/H/W/D}. Signed-off-by: Song Gao <gaosong@loongson.cn> --- target/loongarch/disas.c | 24 +++++ target/loongarch/helper.h | 3 + target/loongarch/insn_trans/trans_lasx.c.inc | 97 ++++++++++++++++++++ target/loongarch/insns.decode | 25 +++++ target/loongarch/lasx_helper.c | 59 ++++++++++++ 5 files changed, 208 insertions(+)