From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:47286) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WCAIY-0007fY-7z for qemu-devel@nongnu.org; Sat, 08 Feb 2014 10:58:31 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1WCAIW-0002yU-VZ for qemu-devel@nongnu.org; Sat, 08 Feb 2014 10:58:30 -0500 Received: from mnementh.archaic.org.uk ([2001:8b0:1d0::1]:45684) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WCAIW-0002tl-MP for qemu-devel@nongnu.org; Sat, 08 Feb 2014 10:58:28 -0500 From: Peter Maydell Date: Sat, 8 Feb 2014 15:57:37 +0000 Message-Id: <1391875084-12772-3-git-send-email-peter.maydell@linaro.org> In-Reply-To: <1391875084-12772-1-git-send-email-peter.maydell@linaro.org> References: <1391875084-12772-1-git-send-email-peter.maydell@linaro.org> Subject: [Qemu-devel] [PULL 02/29] target-arm: A64: Implement remaining non-pairwise int SIMD 3-reg-same insns List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Anthony Liguori Cc: Blue Swirl , qemu-devel@nongnu.org, Aurelien Jarno Implement the SIMD 3-reg-same instructions where the size == 3 case is reserved: SHADD, UHADD, SRHADD, URHADD, SHSUB, UHSUB, SMAX, UMAX, SMIN, UMIN, SABD, UABD, SABA, UABA, MLA, MLS, MUL, PMUL, SQRDMULH, SQDMULH. (None of these have scalar-3-same versions.) This completes the non-pairwise integer instructions in this category. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson --- target-arm/translate-a64.c | 131 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 127 insertions(+), 4 deletions(-) diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c index e67cdbb..8d996e9 100644 --- a/target-arm/translate-a64.c +++ b/target-arm/translate-a64.c @@ -6556,6 +6556,27 @@ static void disas_simd_3same_logic(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_res[1]); } +/* Helper functions for 32 bit comparisons */ +static void gen_max_s32(TCGv_i32 res, TCGv_i32 op1, TCGv_i32 op2) +{ + tcg_gen_movcond_i32(TCG_COND_GE, res, op1, op2, op1, op2); +} + +static void gen_max_u32(TCGv_i32 res, TCGv_i32 op1, TCGv_i32 op2) +{ + tcg_gen_movcond_i32(TCG_COND_GEU, res, op1, op2, op1, op2); +} + +static void gen_min_s32(TCGv_i32 res, TCGv_i32 op1, TCGv_i32 op2) +{ + tcg_gen_movcond_i32(TCG_COND_LE, res, op1, op2, op1, op2); +} + +static void gen_min_u32(TCGv_i32 res, TCGv_i32 op1, TCGv_i32 op2) +{ + tcg_gen_movcond_i32(TCG_COND_LEU, res, op1, op2, op1, op2); +} + /* Pairwise op subgroup of C3.6.16. */ static void disas_simd_3same_pair(DisasContext *s, uint32_t insn) { @@ -6656,15 +6677,13 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - unsupported_encoding(s, insn); - return; + break; case 0x16: /* SQDMULH, SQRDMULH */ if (size == 0 || size == 3) { unallocated_encoding(s); return; } - unsupported_encoding(s, insn); - return; + break; default: if (size == 3 && !is_q) { unallocated_encoding(s); @@ -6702,6 +6721,16 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) read_vec_element_i32(s, tcg_op2, rm, pass, MO_32); switch (opcode) { + case 0x0: /* SHADD, UHADD */ + { + static NeonGenTwoOpFn * const fns[3][2] = { + { gen_helper_neon_hadd_s8, gen_helper_neon_hadd_u8 }, + { gen_helper_neon_hadd_s16, gen_helper_neon_hadd_u16 }, + { gen_helper_neon_hadd_s32, gen_helper_neon_hadd_u32 }, + }; + genfn = fns[size][u]; + break; + } case 0x1: /* SQADD, UQADD */ { static NeonGenTwoOpEnvFn * const fns[3][2] = { @@ -6712,6 +6741,26 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genenvfn = fns[size][u]; break; } + case 0x2: /* SRHADD, URHADD */ + { + static NeonGenTwoOpFn * const fns[3][2] = { + { gen_helper_neon_rhadd_s8, gen_helper_neon_rhadd_u8 }, + { gen_helper_neon_rhadd_s16, gen_helper_neon_rhadd_u16 }, + { gen_helper_neon_rhadd_s32, gen_helper_neon_rhadd_u32 }, + }; + genfn = fns[size][u]; + break; + } + case 0x4: /* SHSUB, UHSUB */ + { + static NeonGenTwoOpFn * const fns[3][2] = { + { gen_helper_neon_hsub_s8, gen_helper_neon_hsub_u8 }, + { gen_helper_neon_hsub_s16, gen_helper_neon_hsub_u16 }, + { gen_helper_neon_hsub_s32, gen_helper_neon_hsub_u32 }, + }; + genfn = fns[size][u]; + break; + } case 0x5: /* SQSUB, UQSUB */ { static NeonGenTwoOpEnvFn * const fns[3][2] = { @@ -6782,6 +6831,38 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genenvfn = fns[size][u]; break; } + case 0xc: /* SMAX, UMAX */ + { + static NeonGenTwoOpFn * const fns[3][2] = { + { gen_helper_neon_max_s8, gen_helper_neon_max_u8 }, + { gen_helper_neon_max_s16, gen_helper_neon_max_u16 }, + { gen_max_s32, gen_max_u32 }, + }; + genfn = fns[size][u]; + break; + } + + case 0xd: /* SMIN, UMIN */ + { + static NeonGenTwoOpFn * const fns[3][2] = { + { gen_helper_neon_min_s8, gen_helper_neon_min_u8 }, + { gen_helper_neon_min_s16, gen_helper_neon_min_u16 }, + { gen_min_s32, gen_min_u32 }, + }; + genfn = fns[size][u]; + break; + } + case 0xe: /* SABD, UABD */ + case 0xf: /* SABA, UABA */ + { + static NeonGenTwoOpFn * const fns[3][2] = { + { gen_helper_neon_abd_s8, gen_helper_neon_abd_u8 }, + { gen_helper_neon_abd_s16, gen_helper_neon_abd_u16 }, + { gen_helper_neon_abd_s32, gen_helper_neon_abd_u32 }, + }; + genfn = fns[size][u]; + break; + } case 0x10: /* ADD, SUB */ { static NeonGenTwoOpFn * const fns[3][2] = { @@ -6802,6 +6883,34 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genfn = fns[size][u]; break; } + case 0x13: /* MUL, PMUL */ + if (u) { + /* PMUL */ + assert(size == 0); + genfn = gen_helper_neon_mul_p8; + break; + } + /* fall through : MUL */ + case 0x12: /* MLA, MLS */ + { + static NeonGenTwoOpFn * const fns[3] = { + gen_helper_neon_mul_u8, + gen_helper_neon_mul_u16, + tcg_gen_mul_i32, + }; + genfn = fns[size]; + break; + } + case 0x16: /* SQDMULH, SQRDMULH */ + { + static NeonGenTwoOpEnvFn * const fns[2][2] = { + { gen_helper_neon_qdmulh_s16, gen_helper_neon_qrdmulh_s16 }, + { gen_helper_neon_qdmulh_s32, gen_helper_neon_qrdmulh_s32 }, + }; + assert(size == 1 || size == 2); + genenvfn = fns[size - 1][u]; + break; + } default: g_assert_not_reached(); } @@ -6812,6 +6921,20 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genfn(tcg_res, tcg_op1, tcg_op2); } + if (opcode == 0xf || opcode == 0x12) { + /* SABA, UABA, MLA, MLS: accumulating ops */ + static NeonGenTwoOpFn * const fns[3][2] = { + { gen_helper_neon_add_u8, gen_helper_neon_sub_u8 }, + { gen_helper_neon_add_u16, gen_helper_neon_sub_u16 }, + { tcg_gen_add_i32, tcg_gen_sub_i32 }, + }; + bool is_sub = (opcode == 0x12 && u); /* MLS */ + + genfn = fns[size][is_sub]; + read_vec_element_i32(s, tcg_op1, rd, pass, MO_32); + genfn(tcg_res, tcg_res, tcg_op1); + } + write_vec_element_i32(s, tcg_res, rd, pass, MO_32); tcg_temp_free_i32(tcg_res); -- 1.8.5