[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH 2/6] target/arm: Convert SADDL, SSUBL, SABDL, SABAL, and unsigned
|
From: |
Richard Henderson |
|
Subject: |
[PATCH 2/6] target/arm: Convert SADDL, SSUBL, SABDL, SABAL, and unsigned to decodetree |
|
Date: |
Mon, 8 Jul 2024 16:59:32 -0700 |
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-a64.c | 150 +++++++++++++++++----------------
target/arm/tcg/a64.decode | 9 ++
2 files changed, 87 insertions(+), 72 deletions(-)
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 8f0781e1f7..95a37c71bc 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5779,6 +5779,65 @@ TRANS(UMLSL_vi, do_3op_widening,
a->esz, a->q, a->rd, a->rn, a->rm, a->idx,
gen_mulsub_i64, true)
+static void gen_sabd_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m)
+{
+ TCGv_i64 t1 = tcg_temp_new_i64();
+ TCGv_i64 t2 = tcg_temp_new_i64();
+
+ tcg_gen_sub_i64(t1, n, m);
+ tcg_gen_sub_i64(t2, m, n);
+ tcg_gen_movcond_i64(TCG_COND_GE, d, n, m, t1, t2);
+}
+
+static void gen_uabd_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m)
+{
+ TCGv_i64 t1 = tcg_temp_new_i64();
+ TCGv_i64 t2 = tcg_temp_new_i64();
+
+ tcg_gen_sub_i64(t1, n, m);
+ tcg_gen_sub_i64(t2, m, n);
+ tcg_gen_movcond_i64(TCG_COND_GEU, d, n, m, t1, t2);
+}
+
+static void gen_saba_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+ gen_sabd_i64(t, n, m);
+ tcg_gen_add_i64(d, d, t);
+}
+
+static void gen_uaba_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+ gen_uabd_i64(t, n, m);
+ tcg_gen_add_i64(d, d, t);
+}
+
+TRANS(SADDL_v, do_3op_widening,
+ a->esz | MO_SIGN, a->q, a->rd, a->rn, a->rm, -1,
+ tcg_gen_add_i64, false)
+TRANS(UADDL_v, do_3op_widening,
+ a->esz, a->q, a->rd, a->rn, a->rm, -1,
+ tcg_gen_add_i64, false)
+TRANS(SSUBL_v, do_3op_widening,
+ a->esz | MO_SIGN, a->q, a->rd, a->rn, a->rm, -1,
+ tcg_gen_sub_i64, false)
+TRANS(USUBL_v, do_3op_widening,
+ a->esz, a->q, a->rd, a->rn, a->rm, -1,
+ tcg_gen_sub_i64, false)
+TRANS(SABDL_v, do_3op_widening,
+ a->esz | MO_SIGN, a->q, a->rd, a->rn, a->rm, -1,
+ gen_sabd_i64, false)
+TRANS(UABDL_v, do_3op_widening,
+ a->esz, a->q, a->rd, a->rn, a->rm, -1,
+ gen_uabd_i64, false)
+TRANS(SABAL_v, do_3op_widening,
+ a->esz | MO_SIGN, a->q, a->rd, a->rn, a->rm, -1,
+ gen_saba_i64, true)
+TRANS(UABAL_v, do_3op_widening,
+ a->esz, a->q, a->rd, a->rn, a->rm, -1,
+ gen_uaba_i64, true)
+
/*
* Advanced SIMD scalar/vector x indexed element
*/
@@ -10780,25 +10839,6 @@ static void handle_3rd_widening(DisasContext *s, int
is_q, int is_u, int size,
}
switch (opcode) {
- case 0: /* SADDL, SADDL2, UADDL, UADDL2 */
- tcg_gen_add_i64(tcg_passres, tcg_op1, tcg_op2);
- break;
- case 2: /* SSUBL, SSUBL2, USUBL, USUBL2 */
- tcg_gen_sub_i64(tcg_passres, tcg_op1, tcg_op2);
- break;
- case 5: /* SABAL, SABAL2, UABAL, UABAL2 */
- case 7: /* SABDL, SABDL2, UABDL, UABDL2 */
- {
- TCGv_i64 tcg_tmp1 = tcg_temp_new_i64();
- TCGv_i64 tcg_tmp2 = tcg_temp_new_i64();
-
- tcg_gen_sub_i64(tcg_tmp1, tcg_op1, tcg_op2);
- tcg_gen_sub_i64(tcg_tmp2, tcg_op2, tcg_op1);
- tcg_gen_movcond_i64(is_u ? TCG_COND_GEU : TCG_COND_GE,
- tcg_passres,
- tcg_op1, tcg_op2, tcg_tmp1, tcg_tmp2);
- break;
- }
case 9: /* SQDMLAL, SQDMLAL2 */
case 11: /* SQDMLSL, SQDMLSL2 */
case 13: /* SQDMULL, SQDMULL2 */
@@ -10810,20 +10850,20 @@ static void handle_3rd_widening(DisasContext *s, int
is_q, int is_u, int size,
case 8: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
case 10: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
case 12: /* UMULL, UMULL2, SMULL, SMULL2 */
+ case 0: /* SADDL, SADDL2, UADDL, UADDL2 */
+ case 2: /* SSUBL, SSUBL2, USUBL, USUBL2 */
+ case 5: /* SABAL, SABAL2, UABAL, UABAL2 */
+ case 7: /* SABDL, SABDL2, UABDL, UABDL2 */
g_assert_not_reached();
}
- if (opcode == 9 || opcode == 11) {
+ if (accop != 0) {
/* saturating accumulate ops */
if (accop < 0) {
tcg_gen_neg_i64(tcg_passres, tcg_passres);
}
gen_helper_neon_addl_saturate_s64(tcg_res[pass], tcg_env,
tcg_res[pass], tcg_passres);
- } else if (accop > 0) {
- tcg_gen_add_i64(tcg_res[pass], tcg_res[pass], tcg_passres);
- } else if (accop < 0) {
- tcg_gen_sub_i64(tcg_res[pass], tcg_res[pass], tcg_passres);
}
}
} else {
@@ -10844,38 +10884,6 @@ static void handle_3rd_widening(DisasContext *s, int
is_q, int is_u, int size,
}
switch (opcode) {
- case 0: /* SADDL, SADDL2, UADDL, UADDL2 */
- case 2: /* SSUBL, SSUBL2, USUBL, USUBL2 */
- {
- TCGv_i64 tcg_op2_64 = tcg_temp_new_i64();
- static NeonGenWidenFn * const widenfns[2][2] = {
- { gen_helper_neon_widen_s8, gen_helper_neon_widen_u8 },
- { gen_helper_neon_widen_s16, gen_helper_neon_widen_u16 },
- };
- NeonGenWidenFn *widenfn = widenfns[size][is_u];
-
- widenfn(tcg_op2_64, tcg_op2);
- widenfn(tcg_passres, tcg_op1);
- gen_neon_addl(size, (opcode == 2), tcg_passres,
- tcg_passres, tcg_op2_64);
- break;
- }
- case 5: /* SABAL, SABAL2, UABAL, UABAL2 */
- case 7: /* SABDL, SABDL2, UABDL, UABDL2 */
- if (size == 0) {
- if (is_u) {
- gen_helper_neon_abdl_u16(tcg_passres, tcg_op1,
tcg_op2);
- } else {
- gen_helper_neon_abdl_s16(tcg_passres, tcg_op1,
tcg_op2);
- }
- } else {
- if (is_u) {
- gen_helper_neon_abdl_u32(tcg_passres, tcg_op1,
tcg_op2);
- } else {
- gen_helper_neon_abdl_s32(tcg_passres, tcg_op1,
tcg_op2);
- }
- }
- break;
case 9: /* SQDMLAL, SQDMLAL2 */
case 11: /* SQDMLSL, SQDMLSL2 */
case 13: /* SQDMULL, SQDMULL2 */
@@ -10888,22 +10896,21 @@ static void handle_3rd_widening(DisasContext *s, int
is_q, int is_u, int size,
case 8: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
case 10: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
case 12: /* UMULL, UMULL2, SMULL, SMULL2 */
+ case 0: /* SADDL, SADDL2, UADDL, UADDL2 */
+ case 2: /* SSUBL, SSUBL2, USUBL, USUBL2 */
+ case 5: /* SABAL, SABAL2, UABAL, UABAL2 */
+ case 7: /* SABDL, SABDL2, UABDL, UABDL2 */
g_assert_not_reached();
}
if (accop != 0) {
- if (opcode == 9 || opcode == 11) {
- /* saturating accumulate ops */
- if (accop < 0) {
- gen_helper_neon_negl_u32(tcg_passres, tcg_passres);
- }
- gen_helper_neon_addl_saturate_s32(tcg_res[pass], tcg_env,
- tcg_res[pass],
- tcg_passres);
- } else {
- gen_neon_addl(size, (accop < 0), tcg_res[pass],
- tcg_res[pass], tcg_passres);
+ /* saturating accumulate ops */
+ if (accop < 0) {
+ gen_helper_neon_negl_u32(tcg_passres, tcg_passres);
}
+ gen_helper_neon_addl_saturate_s32(tcg_res[pass], tcg_env,
+ tcg_res[pass],
+ tcg_passres);
}
}
}
@@ -11075,11 +11082,6 @@ static void disas_simd_three_reg_diff(DisasContext *s,
uint32_t insn)
unallocated_encoding(s);
return;
}
- /* fall through */
- case 0: /* SADDL, SADDL2, UADDL, UADDL2 */
- case 2: /* SSUBL, SSUBL2, USUBL, USUBL2 */
- case 5: /* SABAL, SABAL2, UABAL, UABAL2 */
- case 7: /* SABDL, SABDL2, UABDL, UABDL2 */
/* 64 x 64 -> 128 */
if (size == 3) {
unallocated_encoding(s);
@@ -11092,6 +11094,10 @@ static void disas_simd_three_reg_diff(DisasContext *s,
uint32_t insn)
handle_3rd_widening(s, is_q, is_u, size, opcode, rd, rn, rm);
break;
default:
+ case 0: /* SADDL, SADDL2, UADDL, UADDL2 */
+ case 2: /* SSUBL, SSUBL2, USUBL, USUBL2 */
+ case 5: /* SABAL, SABAL2, UABAL, UABAL2 */
+ case 7: /* SABDL, SABDL2, UABDL, UABDL2 */
case 8: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
case 10: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
case 12: /* SMULL, SMULL2, UMULL, UMULL2 */
diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 513d112787..e626ee067f 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -969,6 +969,15 @@ UMLAL_v 0.10 1110 ..1 ..... 10000 0 ..... .....
@qrrr_e
SMLSL_v 0.00 1110 ..1 ..... 10100 0 ..... ..... @qrrr_e
UMLSL_v 0.10 1110 ..1 ..... 10100 0 ..... ..... @qrrr_e
+SADDL_v 0.00 1110 ..1 ..... 00000 0 ..... ..... @qrrr_e
+UADDL_v 0.10 1110 ..1 ..... 00000 0 ..... ..... @qrrr_e
+SSUBL_v 0.00 1110 ..1 ..... 00100 0 ..... ..... @qrrr_e
+USUBL_v 0.10 1110 ..1 ..... 00100 0 ..... ..... @qrrr_e
+SABAL_v 0.00 1110 ..1 ..... 01010 0 ..... ..... @qrrr_e
+UABAL_v 0.10 1110 ..1 ..... 01010 0 ..... ..... @qrrr_e
+SABDL_v 0.00 1110 ..1 ..... 01110 0 ..... ..... @qrrr_e
+UABDL_v 0.10 1110 ..1 ..... 01110 0 ..... ..... @qrrr_e
+
### Advanced SIMD scalar x indexed element
FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h
--
2.43.0
- [PATCH 0/6] target/arm: AdvSIMD decodetree conversion, part 3, Richard Henderson, 2024/07/08
- [PATCH 4/6] target/arm: Convert SADDW, SSUBW, UADDW, USUBW to decodetree, Richard Henderson, 2024/07/08
- [PATCH 1/6] target/arm: Convert SMULL, UMULL, SMLAL, UMLAL, SMLSL, UMLSL to decodetree, Richard Henderson, 2024/07/08
- [PATCH 6/6] target/arm: Convert PMULL to decodetree, Richard Henderson, 2024/07/08
- [PATCH 5/6] target/arm: Convert ADDHN, SUBHN, RADDHN, RSUBHN to decodetree, Richard Henderson, 2024/07/08
- [PATCH 3/6] target/arm: Convert SQDMULL, SQDMLAL, SQDMLSL to decodetree, Richard Henderson, 2024/07/08
- [PATCH 2/6] target/arm: Convert SADDL, SSUBL, SABDL, SABAL, and unsigned to decodetree,
Richard Henderson <=