From 8ac9e3cff2c700cde1d81e89e4c89c5d9d5f4e8d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alex=20Benn=C3=A9e?= Date: Thu, 8 Mar 2018 18:32:16 -0500 Subject: [PATCH] arm/translate-a64: add FP16 FCMxx (zero) to simd_two_reg_misc_fp16 I re-use the existing handle_2misc_fcmp_zero handler and tweak it slightly to deal with the half-precision case. Backports commit 7d4dd1a73a023f75c893623710e43743501b318e from qemu --- qemu/target/arm/translate-a64.c | 80 +++++++++++++++++++++++---------- 1 file changed, 57 insertions(+), 23 deletions(-) diff --git a/qemu/target/arm/translate-a64.c b/qemu/target/arm/translate-a64.c index 1cf59571..791ec0ff 100644 --- a/qemu/target/arm/translate-a64.c +++ b/qemu/target/arm/translate-a64.c @@ -7954,14 +7954,14 @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode, int size, int rn, int rd) { TCGContext *tcg_ctx = s->uc->tcg_ctx; - bool is_double = (size == 3); + bool is_double = (size == MO_64); TCGv_ptr fpst; if (!fp_access_check(s)) { return; } - fpst = get_fpstatus_ptr(tcg_ctx, false); + fpst = get_fpstatus_ptr(tcg_ctx, size == MO_16); if (is_double) { TCGv_i64 tcg_op = tcg_temp_new_i64(tcg_ctx); @@ -8014,34 +8014,57 @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode, bool swap = false; int pass, maxpasses; - switch (opcode) { - case 0x2e: /* FCMLT (zero) */ - swap = true; - /* fall through */ - case 0x2c: /* FCMGT (zero) */ - genfn = gen_helper_neon_cgt_f32; - break; - case 0x2d: /* FCMEQ (zero) */ - genfn = gen_helper_neon_ceq_f32; - break; - case 0x6d: /* FCMLE (zero) */ - swap = true; - /* fall through */ - case 0x6c: /* FCMGE (zero) */ - genfn = gen_helper_neon_cge_f32; - break; - default: - g_assert_not_reached(); + if (size == MO_16) { + switch (opcode) { + case 0x2e: /* FCMLT (zero) */ + swap = true; + /* fall through */ + case 0x2c: /* FCMGT (zero) */ + genfn = gen_helper_advsimd_cgt_f16; + break; + case 0x2d: /* FCMEQ (zero) */ + genfn = gen_helper_advsimd_ceq_f16; + break; + case 0x6d: /* FCMLE (zero) */ + swap = true; + /* fall through */ + case 0x6c: /* FCMGE (zero) */ + genfn = gen_helper_advsimd_cge_f16; + break; + default: + g_assert_not_reached(); + } + } else { + switch (opcode) { + case 0x2e: /* FCMLT (zero) */ + swap = true; + /* fall through */ + case 0x2c: /* FCMGT (zero) */ + genfn = gen_helper_neon_cgt_f32; + break; + case 0x2d: /* FCMEQ (zero) */ + genfn = gen_helper_neon_ceq_f32; + break; + case 0x6d: /* FCMLE (zero) */ + swap = true; + /* fall through */ + case 0x6c: /* FCMGE (zero) */ + genfn = gen_helper_neon_cge_f32; + break; + default: + g_assert_not_reached(); + } } if (is_scalar) { maxpasses = 1; } else { - maxpasses = is_q ? 4 : 2; + int vector_size = 8 << is_q; + maxpasses = vector_size >> size; } for (pass = 0; pass < maxpasses; pass++) { - read_vec_element_i32(s, tcg_op, rn, pass, MO_32); + read_vec_element_i32(s, tcg_op, rn, pass, size); if (swap) { genfn(tcg_ctx, tcg_res, tcg_zero, tcg_op, fpst); } else { @@ -8050,7 +8073,7 @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode, if (is_scalar) { write_fp_sreg(s, rd, tcg_res); } else { - write_vec_element_i32(s, tcg_res, rd, pass, MO_32); + write_vec_element_i32(s, tcg_res, rd, pass, size); } } tcg_temp_free_i32(tcg_ctx, tcg_res); @@ -11366,7 +11389,18 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) fpop = deposit32(opcode, 5, 1, a); fpop = deposit32(fpop, 6, 1, u); + rd = extract32(insn, 0, 5); + rn = extract32(insn, 5, 5); + switch (fpop) { + break; + case 0x2c: /* FCMGT (zero) */ + case 0x2d: /* FCMEQ (zero) */ + case 0x2e: /* FCMLT (zero) */ + case 0x6c: /* FCMGE (zero) */ + case 0x6d: /* FCMLE (zero) */ + handle_2misc_fcmp_zero(s, fpop, is_scalar, 0, is_q, MO_16, rn, rd); + return; case 0x18: /* FRINTN */ need_rmode = true; only_in_vector = true;