Implement fp16 for the Neon VCVT insns which convert between float and fixed-point.
Signed-off-by: Peter Maydell <peter.mayd...@linaro.org> --- target/arm/helper.h | 5 +++++ target/arm/neon-dp.decode | 8 +++++++- target/arm/vec_helper.c | 4 ++++ target/arm/translate-neon.c.inc | 5 +++++ 4 files changed, 21 insertions(+), 1 deletion(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 09e0fa052ef..8c98bc40eb3 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -628,6 +628,11 @@ DEF_HELPER_FLAGS_4(gvec_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index 686f9fbf46a..1e9e8592917 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -254,6 +254,8 @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp # We use size=0 for fp32 and size=1 for fp16 to match the 3-same encodings. @2reg_vcvt .... ... . . . 1 ..... .... .... . q:1 . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i5 +@2reg_vcvt_f16 .... ... . . . 11 .... .... .... . q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=1 shift=%neon_rshift_i4 VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s @@ -370,7 +372,11 @@ VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b # VCVT fixed<->float conversions -# TODO: FP16 fixed<->float conversions are opc==0b1100 and 0b1101 +VCVT_SH_2sh 1111 001 0 1 . ...... .... 1100 0 . . 1 .... @2reg_vcvt_f16 +VCVT_UH_2sh 1111 001 1 1 . ...... .... 1100 0 . . 1 .... @2reg_vcvt_f16 +VCVT_HS_2sh 1111 001 0 1 . ...... .... 1101 0 . . 1 .... @2reg_vcvt_f16 +VCVT_HU_2sh 1111 001 1 1 . ...... .... 1101 0 . . 1 .... @2reg_vcvt_f16 + VCVT_SF_2sh 1111 001 0 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt VCVT_UF_2sh 1111 001 1 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt VCVT_FS_2sh 1111 001 0 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index 6d83953ee8f..ea401910f37 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -1863,5 +1863,9 @@ DO_VCVT_FIXED(gvec_vcvt_sf, helper_vfp_sltos, uint32_t) DO_VCVT_FIXED(gvec_vcvt_uf, helper_vfp_ultos, uint32_t) DO_VCVT_FIXED(gvec_vcvt_fs, helper_vfp_tosls_round_to_zero, uint32_t) DO_VCVT_FIXED(gvec_vcvt_fu, helper_vfp_touls_round_to_zero, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_sh, helper_vfp_shtoh, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_uh, helper_vfp_uhtoh, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_hs, helper_vfp_toshh_round_to_zero, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_hu, helper_vfp_touhh_round_to_zero, uint16_t) #undef DO_VCVT_FIXED diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index 50fcf4159ea..b3b1d46e958 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -1657,6 +1657,11 @@ DO_FP_2SH(VCVT_UF, gen_helper_gvec_vcvt_uf) DO_FP_2SH(VCVT_FS, gen_helper_gvec_vcvt_fs) DO_FP_2SH(VCVT_FU, gen_helper_gvec_vcvt_fu) +DO_FP_2SH(VCVT_SH, gen_helper_gvec_vcvt_sh) +DO_FP_2SH(VCVT_UH, gen_helper_gvec_vcvt_uh) +DO_FP_2SH(VCVT_HS, gen_helper_gvec_vcvt_hs) +DO_FP_2SH(VCVT_HU, gen_helper_gvec_vcvt_hu) + static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) { /* -- 2.20.1