From 92cdfaeb616244581df02ef10ba1ee1bb8d90f70 Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Mon, 21 Feb 2011 11:05:22 +0000 Subject: [PATCH] target-arm: Fix shift by immediate and narrow where src, dest overlap For Neon shifts by immediate and narrow, correctly handle the case where the source registers and the destination registers overlap (the second pass should use the original register contents, not the results of the first pass). This includes a refactoring to pull the size check outside the loop rather than inside, since there is now very little common code between the size == 3 and size != 3 case. Signed-off-by: Peter Maydell Signed-off-by: Aurelien Jarno --- target-arm/translate.c | 84 ++++++++++++++++++++++-------------------- 1 file changed, 44 insertions(+), 40 deletions(-) diff --git a/target-arm/translate.c b/target-arm/translate.c index fa20e8443f..dbd958be78 100644 --- a/target-arm/translate.c +++ b/target-arm/translate.c @@ -4804,64 +4804,68 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn) shift = shift - (1 << (size + 3)); size++; - switch (size) { - case 1: - imm = (uint16_t)shift; - imm |= imm << 16; - tmp2 = tcg_const_i32(imm); - TCGV_UNUSED_I64(tmp64); - break; - case 2: - imm = (uint32_t)shift; - tmp2 = tcg_const_i32(imm); - TCGV_UNUSED_I64(tmp64); - break; - case 3: + if (size == 3) { tmp64 = tcg_const_i64(shift); - TCGV_UNUSED(tmp2); - break; - default: - abort(); - } - - for (pass = 0; pass < 2; pass++) { - if (size == 3) { - neon_load_reg64(cpu_V0, rm + pass); + neon_load_reg64(cpu_V0, rm); + neon_load_reg64(cpu_V1, rm + 1); + for (pass = 0; pass < 2; pass++) { + TCGv_i64 in; + if (pass == 0) { + in = cpu_V0; + } else { + in = cpu_V1; + } if (q) { if (input_unsigned) { - gen_helper_neon_rshl_u64(cpu_V0, cpu_V0, - tmp64); + gen_helper_neon_rshl_u64(cpu_V0, in, tmp64); } else { - gen_helper_neon_rshl_s64(cpu_V0, cpu_V0, - tmp64); + gen_helper_neon_rshl_s64(cpu_V0, in, tmp64); } } else { if (input_unsigned) { - gen_helper_neon_shl_u64(cpu_V0, cpu_V0, - tmp64); + gen_helper_neon_shl_u64(cpu_V0, in, tmp64); } else { - gen_helper_neon_shl_s64(cpu_V0, cpu_V0, - tmp64); + gen_helper_neon_shl_s64(cpu_V0, in, tmp64); } } + tmp = new_tmp(); + gen_neon_narrow_op(op == 8, u, size - 1, tmp, cpu_V0); + neon_store_reg(rd, pass, tmp); + } /* for pass */ + tcg_temp_free_i64(tmp64); + } else { + if (size == 1) { + imm = (uint16_t)shift; + imm |= imm << 16; } else { - tmp = neon_load_reg(rm + pass, 0); + /* size == 2 */ + imm = (uint32_t)shift; + } + tmp2 = tcg_const_i32(imm); + tmp4 = neon_load_reg(rm + 1, 0); + tmp5 = neon_load_reg(rm + 1, 1); + for (pass = 0; pass < 2; pass++) { + if (pass == 0) { + tmp = neon_load_reg(rm, 0); + } else { + tmp = tmp4; + } gen_neon_shift_narrow(size, tmp, tmp2, q, input_unsigned); - tmp3 = neon_load_reg(rm + pass, 1); + if (pass == 0) { + tmp3 = neon_load_reg(rm, 1); + } else { + tmp3 = tmp5; + } gen_neon_shift_narrow(size, tmp3, tmp2, q, input_unsigned); tcg_gen_concat_i32_i64(cpu_V0, tmp, tmp3); dead_tmp(tmp); dead_tmp(tmp3); - } - tmp = new_tmp(); - gen_neon_narrow_op(op == 8, u, size - 1, tmp, cpu_V0); - neon_store_reg(rd, pass, tmp); - } /* for pass */ - if (size == 3) { - tcg_temp_free_i64(tmp64); - } else { + tmp = new_tmp(); + gen_neon_narrow_op(op == 8, u, size - 1, tmp, cpu_V0); + neon_store_reg(rd, pass, tmp); + } /* for pass */ tcg_temp_free_i32(tmp2); } } else if (op == 10) {