@@ -8019,6 +8019,125 @@ static bool trans_ORN_rri(DisasContext *s, arg_s_rri_rot *a)
#undef DO_ANY2
#undef DO_CMP2
+/*
+ * Multiply and multiply accumulate
+ */
+
+static bool op_mla(DisasContext *s, arg_s_rrrr *a, bool add)
+{
+ TCGv_i32 t1, t2;
+
+ t1 = load_reg(s, a->rn);
+ t2 = load_reg(s, a->rm);
+ tcg_gen_mul_i32(t1, t1, t2);
+ tcg_temp_free_i32(t2);
+ if (add) {
+ t2 = load_reg(s, a->ra);
+ tcg_gen_add_i32(t1, t1, t2);
+ tcg_temp_free_i32(t2);
+ }
+ if (a->s) {
+ gen_logic_CC(t1);
+ }
+ store_reg(s, a->rd, t1);
+ return true;
+}
+
+static bool trans_MUL(DisasContext *s, arg_MUL *a)
+{
+ return op_mla(s, a, false);
+}
+
+static bool trans_MLA(DisasContext *s, arg_MLA *a)
+{
+ return op_mla(s, a, true);
+}
+
+static bool trans_MLS(DisasContext *s, arg_MLS *a)
+{
+ TCGv_i32 t1, t2;
+
+ if (!ENABLE_ARCH_6T2) {
+ return false;
+ }
+ t1 = load_reg(s, a->rn);
+ t2 = load_reg(s, a->rm);
+ tcg_gen_mul_i32(t1, t1, t2);
+ tcg_temp_free_i32(t2);
+ t2 = load_reg(s, a->ra);
+ tcg_gen_sub_i32(t1, t2, t1);
+ tcg_temp_free_i32(t2);
+ store_reg(s, a->rd, t1);
+ return true;
+}
+
+static bool op_mlal(DisasContext *s, arg_s_rrrr *a, bool uns, bool add)
+{
+ TCGv_i32 t0, t1, t2, t3;
+
+ t0 = load_reg(s, a->rm);
+ t1 = load_reg(s, a->rn);
+ if (uns) {
+ tcg_gen_mulu2_i32(t0, t1, t0, t1);
+ } else {
+ tcg_gen_muls2_i32(t0, t1, t0, t1);
+ }
+ if (add) {
+ t2 = load_reg(s, a->ra);
+ t3 = load_reg(s, a->rd);
+ tcg_gen_add2_i32(t0, t1, t0, t1, t2, t3);
+ tcg_temp_free_i32(t2);
+ tcg_temp_free_i32(t3);
+ }
+ if (a->s) {
+ gen_logicq_cc(t0, t1);
+ }
+ store_reg(s, a->ra, t0);
+ store_reg(s, a->rd, t1);
+ return true;
+}
+
+static bool trans_UMULL(DisasContext *s, arg_UMULL *a)
+{
+ return op_mlal(s, a, true, false);
+}
+
+static bool trans_SMULL(DisasContext *s, arg_SMULL *a)
+{
+ return op_mlal(s, a, false, false);
+}
+
+static bool trans_UMLAL(DisasContext *s, arg_UMLAL *a)
+{
+ return op_mlal(s, a, true, true);
+}
+
+static bool trans_SMLAL(DisasContext *s, arg_SMLAL *a)
+{
+ return op_mlal(s, a, false, true);
+}
+
+static bool trans_UMAAL(DisasContext *s, arg_UMAAL *a)
+{
+ TCGv_i32 t0, t1;
+ TCGv_i64 t64;
+
+ if (s->thumb
+ ? !arm_dc_feature(s, ARM_FEATURE_THUMB_DSP)
+ : !ENABLE_ARCH_6) {
+ return false;
+ }
+
+ t0 = load_reg(s, a->rm);
+ t1 = load_reg(s, a->rn);
+ t64 = gen_mulu_i64_i32(t0, t1);
+ gen_addq_lo(s, t64, a->ra);
+ gen_addq_lo(s, t64, a->rd);
+ gen_storeq_reg(s, a->ra, a->rd, t64);
+ tcg_temp_free_i64(t64);
+ return true;
+}
+
/*
* Legacy decoder.
*/
@@ -8565,71 +8684,9 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
sh = (insn >> 5) & 3;
if (sh == 0) {
if (op1 == 0x0) {
- rd = (insn >> 16) & 0xf;
- rn = (insn >> 12) & 0xf;
- rs = (insn >> 8) & 0xf;
- rm = (insn) & 0xf;
- op1 = (insn >> 20) & 0xf;
- switch (op1) {
- case 0: case 1: case 2: case 3: case 6:
- /* 32 bit mul */
- tmp = load_reg(s, rs);
- tmp2 = load_reg(s, rm);
- tcg_gen_mul_i32(tmp, tmp, tmp2);
- tcg_temp_free_i32(tmp2);
- if (insn & (1 << 22)) {
- /* Subtract (mls) */
- ARCH(6T2);
- tmp2 = load_reg(s, rn);
- tcg_gen_sub_i32(tmp, tmp2, tmp);
- tcg_temp_free_i32(tmp2);
- } else if (insn & (1 << 21)) {
- /* Add */
- tmp2 = load_reg(s, rn);
- tcg_gen_add_i32(tmp, tmp, tmp2);
- tcg_temp_free_i32(tmp2);
- }
- if (insn & (1 << 20))
- gen_logic_CC(tmp);
- store_reg(s, rd, tmp);
- break;
- case 4:
- /* 64 bit mul double accumulate (UMAAL) */
- ARCH(6);
- tmp = load_reg(s, rs);
- tmp2 = load_reg(s, rm);
- tmp64 = gen_mulu_i64_i32(tmp, tmp2);
- gen_addq_lo(s, tmp64, rn);
- gen_addq_lo(s, tmp64, rd);
- gen_storeq_reg(s, rn, rd, tmp64);
- tcg_temp_free_i64(tmp64);
- break;
- case 8: case 9: case 10: case 11:
- case 12: case 13: case 14: case 15:
- /* 64 bit mul: UMULL, UMLAL, SMULL, SMLAL. */
- tmp = load_reg(s, rs);
- tmp2 = load_reg(s, rm);
- if (insn & (1 << 22)) {
- tcg_gen_muls2_i32(tmp, tmp2, tmp, tmp2);
- } else {
- tcg_gen_mulu2_i32(tmp, tmp2, tmp, tmp2);
- }
- if (insn & (1 << 21)) { /* mult accumulate */
- TCGv_i32 al = load_reg(s, rn);
- TCGv_i32 ah = load_reg(s, rd);
- tcg_gen_add2_i32(tmp, tmp2, tmp, tmp2, al, ah);
- tcg_temp_free_i32(al);
- tcg_temp_free_i32(ah);
- }
- if (insn & (1 << 20)) {
- gen_logicq_cc(tmp, tmp2);
- }
- store_reg(s, rn, tmp);
- store_reg(s, rd, tmp2);
- break;
- default:
- goto illegal_op;
- }
+ /* Multiply and multiply accumulate. */
+ /* All done in decodetree. Reach here for illegal ops. */
+ goto illegal_op;
} else {
rn = (insn >> 16) & 0xf;
rd = (insn >> 12) & 0xf;
@@ -10075,7 +10132,8 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn)
break;
case 4: case 5: /* 32-bit multiply. Sum of absolute differences. */
switch ((insn >> 20) & 7) {
- case 0: /* 32 x 32 -> 32 */
+ case 0: /* 32 x 32 -> 32, in decodetree */
+ goto illegal_op;
case 7: /* Unsigned sum of absolute differences. */
break;
case 1: /* 16 x 16 -> 32 */
@@ -10092,18 +10150,6 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn)
tmp = load_reg(s, rn);
tmp2 = load_reg(s, rm);
switch ((insn >> 20) & 7) {
- case 0: /* 32 x 32 -> 32 */
- tcg_gen_mul_i32(tmp, tmp, tmp2);
- tcg_temp_free_i32(tmp2);
- if (rs != 15) {
- tmp2 = load_reg(s, rs);
- if (op)
- tcg_gen_sub_i32(tmp, tmp2, tmp);
- else
- tcg_gen_add_i32(tmp, tmp, tmp2);
- tcg_temp_free_i32(tmp2);
- }
- break;
case 1: /* 16 x 16 -> 32 */
gen_mulxy(tmp, tmp2, op & 2, op & 1);
tcg_temp_free_i32(tmp2);
@@ -10233,36 +10279,24 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn)
gen_storeq_reg(s, rs, rd, tmp64);
tcg_temp_free_i64(tmp64);
} else {
- if (op & 0x20) {
- /* Unsigned 64-bit multiply */
- tmp64 = gen_mulu_i64_i32(tmp, tmp2);
- } else {
- if (op & 8) {
- /* smlalxy */
- if (!arm_dc_feature(s, ARM_FEATURE_THUMB_DSP)) {
- tcg_temp_free_i32(tmp2);
- tcg_temp_free_i32(tmp);
- goto illegal_op;
- }
- gen_mulxy(tmp, tmp2, op & 2, op & 1);
- tcg_temp_free_i32(tmp2);
- tmp64 = tcg_temp_new_i64();
- tcg_gen_ext_i32_i64(tmp64, tmp);
- tcg_temp_free_i32(tmp);
- } else {
- /* Signed 64-bit multiply */
- tmp64 = gen_muls_i64_i32(tmp, tmp2);
- }
+ if ((op & 0x20) || !(op & 8)) {
+ /* Signed/unsigned 64-bit multiply, in decodetree */
+ tcg_temp_free_i32(tmp2);
+ tcg_temp_free_i32(tmp);
+ goto illegal_op;
}
- if (op & 4) {
- /* umaal */
- if (!arm_dc_feature(s, ARM_FEATURE_THUMB_DSP)) {
- tcg_temp_free_i64(tmp64);
- goto illegal_op;
- }
- gen_addq_lo(s, tmp64, rs);
- gen_addq_lo(s, tmp64, rd);
- } else if (op & 0x40) {
+ /* smlalxy */
+ if (!arm_dc_feature(s, ARM_FEATURE_THUMB_DSP)) {
+ tcg_temp_free_i32(tmp2);
+ tcg_temp_free_i32(tmp);
+ goto illegal_op;
+ }
+ gen_mulxy(tmp, tmp2, op & 2, op & 1);
+ tcg_temp_free_i32(tmp2);
+ tmp64 = tcg_temp_new_i64();
+ tcg_gen_ext_i32_i64(tmp64, tmp);
+ tcg_temp_free_i32(tmp);
+ if (op & 0x40) {
/* 64-bit accumulate. */
gen_addq(s, tmp64, rs, rd);
}
@@ -25,6 +25,8 @@
&s_rrr_shi s rd rn rm shim shty
&s_rrr_shr s rn rd rm rs shty
&s_rri_rot s rn rd imm rot
+&s_rrrr s rd rn rm ra
+&rrrr rd rn rm ra
# Data-processing (register)
@@ -105,3 +107,18 @@ ORR_rri .... 001 1100 . .... .... ............ @s_rri_rot
MOV_rxi .... 001 1101 . 0000 .... ............ @s_rxi_rot
BIC_rri .... 001 1110 . .... .... ............ @s_rri_rot
MVN_rxi .... 001 1111 . 0000 .... ............ @s_rxi_rot
+
+# Multiply and multiply accumulate
+
+@s_rdamn ---- .... ... s:1 rd:4 ra:4 rm:4 .... rn:4 &s_rrrr
+@s_rd0mn ---- .... ... s:1 rd:4 .... rm:4 .... rn:4 &s_rrrr ra=0
+@rdamn ---- .... ... . rd:4 ra:4 rm:4 .... rn:4 &rrrr
+
+MUL .... 0000 000 . .... 0000 .... 1001 .... @s_rd0mn
+MLA .... 0000 001 . .... .... .... 1001 .... @s_rdamn
+UMAAL .... 0000 010 0 .... .... .... 1001 .... @rdamn
+MLS .... 0000 011 0 .... .... .... 1001 .... @rdamn
+UMULL .... 0000 100 . .... .... .... 1001 .... @s_rdamn
+UMLAL .... 0000 101 . .... .... .... 1001 .... @s_rdamn
+SMULL .... 0000 110 . .... .... .... 1001 .... @s_rdamn
+SMLAL .... 0000 111 . .... .... .... 1001 .... @s_rdamn
@@ -22,6 +22,8 @@
&s_rrr_shi !extern s rd rn rm shim shty
&s_rrr_shr !extern s rn rd rm rs shty
&s_rri_rot !extern s rn rd imm rot
+&s_rrrr !extern s rd rn rm ra
+&rrrr !extern rd rn rm ra
# Data-processing (register)
@@ -109,3 +111,20 @@ SBC_rri 1111 0.0 1011 . .... 0 ... .... ........ @s_rri_rot
SUB_rri 1111 0.0 1101 . .... 0 ... .... ........ @s_rri_rot
}
RSB_rri 1111 0.0 1110 . .... 0 ... .... ........ @s_rri_rot
+
+# Multiply and multiply accumulate
+
+@s0_rnadm .... .... .... rn:4 ra:4 rd:4 .... rm:4 &s_rrrr s=0
+@s0_rn0dm .... .... .... rn:4 .... rd:4 .... rm:4 &s_rrrr ra=0 s=0
+@rnadm .... .... .... rn:4 ra:4 rd:4 .... rm:4 &rrrr
+
+{
+ MUL 1111 1011 0000 .... 1111 .... 0000 .... @s0_rn0dm
+ MLA 1111 1011 0000 .... .... .... 0000 .... @s0_rnadm
+}
+MLS 1111 1011 0000 .... .... .... 0001 .... @rnadm
+SMULL 1111 1011 1000 .... .... .... 0000 .... @s0_rnadm
+UMULL 1111 1011 1010 .... .... .... 0000 .... @s0_rnadm
+SMLAL 1111 1011 1100 .... .... .... 0000 .... @s0_rnadm
+UMLAL 1111 1011 1110 .... .... .... 0000 .... @s0_rnadm
+UMAAL 1111 1011 1110 .... .... .... 0110 .... @rnadm