From: Richard Henderson Date: Fri, 4 Jul 2025 14:20:31 +0000 (-0600) Subject: target/arm: Implement FCLAMP for SME2, SVE2p1 X-Git-Tag: v10.1.0-rc0~29^2~39 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=e9b743947b154b51dad778e31e323c8ef3133a52;p=thirdparty%2Fqemu.git target/arm: Implement FCLAMP for SME2, SVE2p1 This is the single vector version within SVE decode space. Tested-by: Alex Bennée Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20250704142112.1018902-69-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index f808362f239..dcfc40ef44b 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -1721,3 +1721,5 @@ PSEL 00100101 .1 1 000 .. 01 .... 0 .... 0 .... \ SCLAMP 01000100 .. 0 ..... 110000 ..... ..... @rda_rn_rm UCLAMP 01000100 .. 0 ..... 110001 ..... ..... @rda_rn_rm + +FCLAMP 01100100 .. 1 ..... 001001 ..... ..... @rda_rn_rm diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index ff70bf27b01..210a029ab84 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -7428,6 +7428,28 @@ static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, TRANS_FEAT(UCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_uclamp, a) +static bool trans_FCLAMP(DisasContext *s, arg_FCLAMP *a) +{ + static gen_helper_gvec_3_ptr * const fn[] = { + gen_helper_sme2_bfclamp, + gen_helper_sme2_fclamp_h, + gen_helper_sme2_fclamp_s, + gen_helper_sme2_fclamp_d, + }; + + /* This insn uses MO_8 to encode BFloat16. */ + if (a->esz == MO_8 + ? !dc_isar_feature(aa64_sve_b16b16, s) + : !dc_isar_feature(aa64_sme2_or_sve2p1, s)) { + return false; + } + + /* So far we never optimize rda with MOVPRFX */ + assert(a->rd == a->ra); + return gen_gvec_fpst_zzz(s, fn[a->esz], a->rd, a->rn, a->rm, 1, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); +} + TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0) TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,