qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Peter Maydell <peter.maydell@linaro.org>
To: qemu-devel@nongnu.org
Subject: [PULL 097/114] target/arm: Implement SVE2 FLOGB
Date: Tue, 25 May 2021 16:07:19 +0100	[thread overview]
Message-ID: <20210525150736.32695-3-peter.maydell@linaro.org> (raw)
In-Reply-To: <20210525150736.32695-1-peter.maydell@linaro.org>

From: Stephen Long <steplong@quicinc.com>

Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-76-richard.henderson@linaro.org
Message-Id: <20200430191405.21641-1-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  4 ++
 target/arm/sve.decode      |  3 ++
 target/arm/sve_helper.c    | 88 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 24 +++++++++++
 4 files changed, 119 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index be4b17f1c2e..342bb837214 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2754,3 +2754,7 @@ DEF_HELPER_FLAGS_5(sve2_fcvtlt_hs, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve2_fcvtlt_sd, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(flogb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(flogb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(flogb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 5dcc79759e0..5a1cceccb60 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1588,3 +1588,6 @@ FCVTNT_sh       01100100 10 0010 00 101 ... ..... .....  @rd_pg_rn_e0
 FCVTLT_hs       01100100 10 0010 01 101 ... ..... .....  @rd_pg_rn_e0
 FCVTNT_ds       01100100 11 0010 10 101 ... ..... .....  @rd_pg_rn_e0
 FCVTLT_sd       01100100 11 0010 11 101 ... ..... .....  @rd_pg_rn_e0
+
+### SVE2 floating-point convert to integer
+FLOGB           01100101 00 011 esz:2 0101 pg:3 rn:5 rd:5  &rpr_esz
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 88823935156..a0518549849 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -4729,6 +4729,94 @@ DO_ZPZ_FP(sve_ucvt_dh, uint64_t,     , uint64_to_float16)
 DO_ZPZ_FP(sve_ucvt_ds, uint64_t,     , uint64_to_float32)
 DO_ZPZ_FP(sve_ucvt_dd, uint64_t,     , uint64_to_float64)
 
+static int16_t do_float16_logb_as_int(float16 a, float_status *s)
+{
+    /* Extract frac to the top of the uint32_t. */
+    uint32_t frac = (uint32_t)a << (16 + 6);
+    int16_t exp = extract32(a, 10, 5);
+
+    if (unlikely(exp == 0)) {
+        if (frac != 0) {
+            if (!get_flush_inputs_to_zero(s)) {
+                /* denormal: bias - fractional_zeros */
+                return -15 - clz32(frac);
+            }
+            /* flush to zero */
+            float_raise(float_flag_input_denormal, s);
+        }
+    } else if (unlikely(exp == 0x1f)) {
+        if (frac == 0) {
+            return INT16_MAX; /* infinity */
+        }
+    } else {
+        /* normal: exp - bias */
+        return exp - 15;
+    }
+    /* nan or zero */
+    float_raise(float_flag_invalid, s);
+    return INT16_MIN;
+}
+
+static int32_t do_float32_logb_as_int(float32 a, float_status *s)
+{
+    /* Extract frac to the top of the uint32_t. */
+    uint32_t frac = a << 9;
+    int32_t exp = extract32(a, 23, 8);
+
+    if (unlikely(exp == 0)) {
+        if (frac != 0) {
+            if (!get_flush_inputs_to_zero(s)) {
+                /* denormal: bias - fractional_zeros */
+                return -127 - clz32(frac);
+            }
+            /* flush to zero */
+            float_raise(float_flag_input_denormal, s);
+        }
+    } else if (unlikely(exp == 0xff)) {
+        if (frac == 0) {
+            return INT32_MAX; /* infinity */
+        }
+    } else {
+        /* normal: exp - bias */
+        return exp - 127;
+    }
+    /* nan or zero */
+    float_raise(float_flag_invalid, s);
+    return INT32_MIN;
+}
+
+static int64_t do_float64_logb_as_int(float64 a, float_status *s)
+{
+    /* Extract frac to the top of the uint64_t. */
+    uint64_t frac = a << 12;
+    int64_t exp = extract64(a, 52, 11);
+
+    if (unlikely(exp == 0)) {
+        if (frac != 0) {
+            if (!get_flush_inputs_to_zero(s)) {
+                /* denormal: bias - fractional_zeros */
+                return -1023 - clz64(frac);
+            }
+            /* flush to zero */
+            float_raise(float_flag_input_denormal, s);
+        }
+    } else if (unlikely(exp == 0x7ff)) {
+        if (frac == 0) {
+            return INT64_MAX; /* infinity */
+        }
+    } else {
+        /* normal: exp - bias */
+        return exp - 1023;
+    }
+    /* nan or zero */
+    float_raise(float_flag_invalid, s);
+    return INT64_MIN;
+}
+
+DO_ZPZ_FP(flogb_h, float16, H1_2, do_float16_logb_as_int)
+DO_ZPZ_FP(flogb_s, float32, H1_4, do_float32_logb_as_int)
+DO_ZPZ_FP(flogb_d, float64,     , do_float64_logb_as_int)
+
 #undef DO_ZPZ_FP
 
 static void do_fmla_zpzzz_h(void *vd, void *vn, void *vm, void *va, void *vg,
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 0a2718c4810..3ea51a73d36 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -8307,3 +8307,27 @@ static bool trans_FCVTXNT_ds(DisasContext *s, arg_rpr_esz *a)
     }
     return do_frint_mode(s, a, float_round_to_odd, gen_helper_sve2_fcvtnt_ds);
 }
+
+static bool trans_FLOGB(DisasContext *s, arg_rpr_esz *a)
+{
+    static gen_helper_gvec_3_ptr * const fns[] = {
+        NULL,               gen_helper_flogb_h,
+        gen_helper_flogb_s, gen_helper_flogb_d
+    };
+
+    if (!dc_isar_feature(aa64_sve2, s) || fns[a->esz] == NULL) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        TCGv_ptr status =
+            fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR);
+        unsigned vsz = vec_full_reg_size(s);
+
+        tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           pred_full_reg_offset(s, a->pg),
+                           status, vsz, vsz, 0, fns[a->esz]);
+        tcg_temp_free_ptr(status);
+    }
+    return true;
+}
-- 
2.20.1



  parent reply	other threads:[~2021-05-25 16:59 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-25 15:07 [PULL 095/114] target/arm: Implement SVE2 FCVTLT Peter Maydell
2021-05-25 15:07 ` [PULL 096/114] target/arm: Implement SVE2 FCVTXNT, FCVTX Peter Maydell
2021-05-25 15:07 ` Peter Maydell [this message]
2021-05-25 15:07 ` [PULL 098/114] target/arm: Share table of sve load functions Peter Maydell
2021-05-25 15:07 ` [PULL 099/114] target/arm: Tidy do_ldrq Peter Maydell
2021-05-25 15:07 ` [PULL 100/114] target/arm: Implement SVE2 LD1RO Peter Maydell
2021-05-25 15:07 ` [PULL 101/114] target/arm: Implement 128-bit ZIP, UZP, TRN Peter Maydell
2021-05-25 15:07 ` [PULL 102/114] target/arm: Implement SVE2 bitwise shift immediate Peter Maydell
2021-05-25 15:07 ` [PULL 103/114] target/arm: Move endian adjustment macros to vec_internal.h Peter Maydell
2021-05-25 15:07 ` [PULL 104/114] target/arm: Implement SVE2 fp multiply-add long Peter Maydell
2021-05-25 15:07 ` [PULL 105/114] target/arm: Implement aarch64 SUDOT, USDOT Peter Maydell
2021-05-25 15:07 ` [PULL 106/114] target/arm: Split out do_neon_ddda_fpst Peter Maydell
2021-05-25 15:07 ` [PULL 107/114] target/arm: Remove unused fpst from VDOT_scalar Peter Maydell
2021-05-25 15:07 ` [PULL 108/114] target/arm: Fix decode for VDOT (indexed) Peter Maydell
2021-05-25 15:07 ` [PULL 109/114] target/arm: Split out do_neon_ddda Peter Maydell
2021-05-25 15:07 ` [PULL 110/114] target/arm: Split decode of VSDOT and VUDOT Peter Maydell
2021-05-25 15:07 ` [PULL 111/114] target/arm: Implement aarch32 VSUDOT, VUSDOT Peter Maydell
2021-05-25 15:07 ` [PULL 112/114] target/arm: Implement integer matrix multiply accumulate Peter Maydell
2021-05-25 15:07 ` [PULL 113/114] linux-user/aarch64: Enable hwcap bits for sve2 and related extensions Peter Maydell
2021-05-25 15:07 ` [PULL 114/114] target/arm: Enable SVE2 " Peter Maydell

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210525150736.32695-3-peter.maydell@linaro.org \
    --to=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).