qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: mark.cave-ayland@ilande.co.uk
Subject: [PATCH v2 14/37] target/sparc: Implement FHADD, FHSUB, FNHADD, FNADD, FNMUL
Date: Sun, 26 May 2024 12:42:31 -0700	[thread overview]
Message-ID: <20240526194254.459395-15-richard.henderson@linaro.org> (raw)
In-Reply-To: <20240526194254.459395-1-richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/sparc/helper.h     |  5 +++
 target/sparc/insns.decode | 11 ++++++
 target/sparc/fop_helper.c | 68 +++++++++++++++++++++++++++++++++++
 target/sparc/translate.c  | 76 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 160 insertions(+)

diff --git a/target/sparc/helper.h b/target/sparc/helper.h
index e59307efc2..15f0907a1b 100644
--- a/target/sparc/helper.h
+++ b/target/sparc/helper.h
@@ -57,6 +57,8 @@ DEF_HELPER_FLAGS_3(fsubd, TCG_CALL_NO_WG, f64, env, f64, f64)
 DEF_HELPER_FLAGS_3(fmuld, TCG_CALL_NO_WG, f64, env, f64, f64)
 DEF_HELPER_FLAGS_3(fdivd, TCG_CALL_NO_WG, f64, env, f64, f64)
 DEF_HELPER_FLAGS_5(fmaddd, TCG_CALL_NO_WG, f64, env, f64, f64, f64, i32)
+DEF_HELPER_FLAGS_3(fnaddd, TCG_CALL_NO_WG, f64, env, f64, f64)
+DEF_HELPER_FLAGS_3(fnmuld, TCG_CALL_NO_WG, f64, env, f64, f64)
 
 DEF_HELPER_FLAGS_3(faddq, TCG_CALL_NO_WG, i128, env, i128, i128)
 DEF_HELPER_FLAGS_3(fsubq, TCG_CALL_NO_WG, i128, env, i128, i128)
@@ -68,8 +70,11 @@ DEF_HELPER_FLAGS_3(fsubs, TCG_CALL_NO_WG, f32, env, f32, f32)
 DEF_HELPER_FLAGS_3(fmuls, TCG_CALL_NO_WG, f32, env, f32, f32)
 DEF_HELPER_FLAGS_3(fdivs, TCG_CALL_NO_WG, f32, env, f32, f32)
 DEF_HELPER_FLAGS_5(fmadds, TCG_CALL_NO_WG, f32, env, f32, f32, f32, i32)
+DEF_HELPER_FLAGS_3(fnadds, TCG_CALL_NO_WG, f32, env, f32, f32)
+DEF_HELPER_FLAGS_3(fnmuls, TCG_CALL_NO_WG, f32, env, f32, f32)
 
 DEF_HELPER_FLAGS_3(fsmuld, TCG_CALL_NO_WG, f64, env, f32, f32)
+DEF_HELPER_FLAGS_3(fnsmuld, TCG_CALL_NO_WG, f64, env, f32, f32)
 DEF_HELPER_FLAGS_3(fdmulq, TCG_CALL_NO_WG, i128, env, f64, f64)
 
 DEF_HELPER_FLAGS_2(fitod, TCG_CALL_NO_WG, f64, env, s32)
diff --git a/target/sparc/insns.decode b/target/sparc/insns.decode
index 18d068d2af..6ec3838865 100644
--- a/target/sparc/insns.decode
+++ b/target/sparc/insns.decode
@@ -307,8 +307,19 @@ FMULq       10 ..... 110100 ..... 0 0100 1011 .....        @q_q_q
 FDIVs       10 ..... 110100 ..... 0 0100 1101 .....        @r_r_r
 FDIVd       10 ..... 110100 ..... 0 0100 1110 .....        @d_d_d
 FDIVq       10 ..... 110100 ..... 0 0100 1111 .....        @q_q_q
+FNADDs      10 ..... 110100 ..... 0 0101 0001 .....        @r_r_r
+FNADDd      10 ..... 110100 ..... 0 0101 0010 .....        @d_d_d
+FNMULs      10 ..... 110100 ..... 0 0101 1001 .....        @r_r_r
+FNMULd      10 ..... 110100 ..... 0 0101 1010 .....        @d_d_d
+FHADDs      10 ..... 110100 ..... 0 0110 0001 .....        @r_r_r
+FHADDd      10 ..... 110100 ..... 0 0110 0010 .....        @d_d_d
+FHSUBs      10 ..... 110100 ..... 0 0110 0101 .....        @r_r_r
+FHSUBd      10 ..... 110100 ..... 0 0110 0110 .....        @d_d_d
 FsMULd      10 ..... 110100 ..... 0 0110 1001 .....        @d_r_r
 FdMULq      10 ..... 110100 ..... 0 0110 1110 .....        @q_d_d
+FNHADDs     10 ..... 110100 ..... 0 0111 0001 .....        @r_r_r
+FNHADDd     10 ..... 110100 ..... 0 0111 0010 .....        @d_d_d
+FNsMULd     10 ..... 110100 ..... 0 0111 1001 .....        @d_r_r
 FsTOx       10 ..... 110100 00000 0 1000 0001 .....        @r_r2
 FdTOx       10 ..... 110100 00000 0 1000 0010 .....        @r_d2
 FqTOx       10 ..... 110100 00000 0 1000 0011 .....        @r_q2
diff --git a/target/sparc/fop_helper.c b/target/sparc/fop_helper.c
index 1de44d79c1..08b5f96f95 100644
--- a/target/sparc/fop_helper.c
+++ b/target/sparc/fop_helper.c
@@ -359,6 +359,74 @@ float64 helper_fmaddd(CPUSPARCState *env, float64 s1,
     return ret;
 }
 
+float32 helper_fnadds(CPUSPARCState *env, float32 src1, float32 src2)
+{
+    float32 ret = float32_add(src1, src2, &env->fp_status);
+
+    /*
+     * NaN inputs or result do not get a sign change.
+     * Nor, apparently, does zero: on hardware, -(x + -x) yields +0.
+     */
+    if (!float32_is_any_nan(ret) && !float32_is_zero(ret)) {
+        ret = float32_chs(ret);
+    }
+    check_ieee_exceptions(env, GETPC());
+    return ret;
+}
+
+float32 helper_fnmuls(CPUSPARCState *env, float32 src1, float32 src2)
+{
+    float32 ret = float32_mul(src1, src2, &env->fp_status);
+
+    /* NaN inputs or result do not get a sign change. */
+    if (!float32_is_any_nan(ret)) {
+        ret = float32_chs(ret);
+    }
+    check_ieee_exceptions(env, GETPC());
+    return ret;
+}
+
+float64 helper_fnaddd(CPUSPARCState *env, float64 src1, float64 src2)
+{
+    float64 ret = float64_add(src1, src2, &env->fp_status);
+
+    /*
+     * NaN inputs or result do not get a sign change.
+     * Nor, apparently, does zero: on hardware, -(x + -x) yields +0.
+     */
+    if (!float64_is_any_nan(ret) && !float64_is_zero(ret)) {
+        ret = float64_chs(ret);
+    }
+    check_ieee_exceptions(env, GETPC());
+    return ret;
+}
+
+float64 helper_fnmuld(CPUSPARCState *env, float64 src1, float64 src2)
+{
+    float64 ret = float64_mul(src1, src2, &env->fp_status);
+
+    /* NaN inputs or result do not get a sign change. */
+    if (!float64_is_any_nan(ret)) {
+        ret = float64_chs(ret);
+    }
+    check_ieee_exceptions(env, GETPC());
+    return ret;
+}
+
+float64 helper_fnsmuld(CPUSPARCState *env, float32 src1, float32 src2)
+{
+    float64 ret = float64_mul(float32_to_float64(src1, &env->fp_status),
+                              float32_to_float64(src2, &env->fp_status),
+                              &env->fp_status);
+
+    /* NaN inputs or result do not get a sign change. */
+    if (!float64_is_any_nan(ret)) {
+        ret = float64_chs(ret);
+    }
+    check_ieee_exceptions(env, GETPC());
+    return ret;
+}
+
 static uint32_t finish_fcmp(CPUSPARCState *env, FloatRelation r, uintptr_t ra)
 {
     check_ieee_exceptions(env, ra);
diff --git a/target/sparc/translate.c b/target/sparc/translate.c
index 48ee1abd68..4515886590 100644
--- a/target/sparc/translate.c
+++ b/target/sparc/translate.c
@@ -1234,6 +1234,51 @@ static void gen_op_fnmaddd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2, TCGv_i64 s3)
     gen_helper_fmaddd(d, tcg_env, s1, s2, s3, tcg_constant_i32(op));
 }
 
+/* Use muladd to compute (1 * src1) + src2 / 2 with one rounding. */
+static void gen_op_fhadds(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2)
+{
+    TCGv_i32 one = tcg_constant_i32(float32_one);
+    int op = float_muladd_halve_result;
+    gen_helper_fmadds(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
+static void gen_op_fhaddd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2)
+{
+    TCGv_i64 one = tcg_constant_i64(float64_one);
+    int op = float_muladd_halve_result;
+    gen_helper_fmaddd(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
+/* Use muladd to compute (1 * src1) - src2 / 2 with one rounding. */
+static void gen_op_fhsubs(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2)
+{
+    TCGv_i32 one = tcg_constant_i32(float32_one);
+    int op = float_muladd_negate_c | float_muladd_halve_result;
+    gen_helper_fmadds(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
+static void gen_op_fhsubd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2)
+{
+    TCGv_i64 one = tcg_constant_i64(float64_one);
+    int op = float_muladd_negate_c | float_muladd_halve_result;
+    gen_helper_fmaddd(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
+/* Use muladd to compute -((1 * src1) + src2 / 2) with one rounding. */
+static void gen_op_fnhadds(TCGv_i32 d, TCGv_i32 s1, TCGv_i32 s2)
+{
+    TCGv_i32 one = tcg_constant_i32(float32_one);
+    int op = float_muladd_negate_result | float_muladd_halve_result;
+    gen_helper_fmadds(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
+static void gen_op_fnhaddd(TCGv_i64 d, TCGv_i64 s1, TCGv_i64 s2)
+{
+    TCGv_i64 one = tcg_constant_i64(float64_one);
+    int op = float_muladd_negate_result | float_muladd_halve_result;
+    gen_helper_fmaddd(d, tcg_env, one, s1, s2, tcg_constant_i32(op));
+}
+
 static void gen_op_fpexception_im(DisasContext *dc, int ftt)
 {
     /*
@@ -4710,6 +4755,10 @@ TRANS(FXNORs, VIS1, do_fff, a, tcg_gen_eqv_i32)
 TRANS(FORNOTs, VIS1, do_fff, a, tcg_gen_orc_i32)
 TRANS(FORs, VIS1, do_fff, a, tcg_gen_or_i32)
 
+TRANS(FHADDs, VIS3, do_fff, a, gen_op_fhadds)
+TRANS(FHSUBs, VIS3, do_fff, a, gen_op_fhsubs)
+TRANS(FNHADDs, VIS3, do_fff, a, gen_op_fnhadds)
+
 static bool do_env_fff(DisasContext *dc, arg_r_r_r *a,
                        void (*func)(TCGv_i32, TCGv_env, TCGv_i32, TCGv_i32))
 {
@@ -4730,6 +4779,8 @@ TRANS(FADDs, ALL, do_env_fff, a, gen_helper_fadds)
 TRANS(FSUBs, ALL, do_env_fff, a, gen_helper_fsubs)
 TRANS(FMULs, ALL, do_env_fff, a, gen_helper_fmuls)
 TRANS(FDIVs, ALL, do_env_fff, a, gen_helper_fdivs)
+TRANS(FNADDs, VIS3, do_env_fff, a, gen_helper_fnadds)
+TRANS(FNMULs, VIS3, do_env_fff, a, gen_helper_fnmuls)
 
 static bool do_dff(DisasContext *dc, arg_r_r_r *a,
                    void (*func)(TCGv_i64, TCGv_i32, TCGv_i32))
@@ -4823,6 +4874,10 @@ TRANS(FPACK32, VIS1, do_ddd, a, gen_op_fpack32)
 TRANS(FALIGNDATAg, VIS1, do_ddd, a, gen_op_faligndata)
 TRANS(BSHUFFLE, VIS2, do_ddd, a, gen_op_bshuffle)
 
+TRANS(FHADDd, VIS3, do_ddd, a, gen_op_fhaddd)
+TRANS(FHSUBd, VIS3, do_ddd, a, gen_op_fhsubd)
+TRANS(FNHADDd, VIS3, do_ddd, a, gen_op_fnhaddd)
+
 static bool do_rdd(DisasContext *dc, arg_r_r_r *a,
                    void (*func)(TCGv, TCGv_i64, TCGv_i64))
 {
@@ -4872,6 +4927,8 @@ TRANS(FADDd, ALL, do_env_ddd, a, gen_helper_faddd)
 TRANS(FSUBd, ALL, do_env_ddd, a, gen_helper_fsubd)
 TRANS(FMULd, ALL, do_env_ddd, a, gen_helper_fmuld)
 TRANS(FDIVd, ALL, do_env_ddd, a, gen_helper_fdivd)
+TRANS(FNADDd, VIS3, do_env_ddd, a, gen_helper_fnaddd)
+TRANS(FNMULd, VIS3, do_env_ddd, a, gen_helper_fnmuld)
 
 static bool trans_FsMULd(DisasContext *dc, arg_r_r_r *a)
 {
@@ -4893,6 +4950,25 @@ static bool trans_FsMULd(DisasContext *dc, arg_r_r_r *a)
     return advance_pc(dc);
 }
 
+static bool trans_FNsMULd(DisasContext *dc, arg_r_r_r *a)
+{
+    TCGv_i64 dst;
+    TCGv_i32 src1, src2;
+
+    if (!avail_VIS3(dc)) {
+        return false;
+    }
+    if (gen_trap_ifnofpu(dc)) {
+        return true;
+    }
+    dst = tcg_temp_new_i64();
+    src1 = gen_load_fpr_F(dc, a->rs1);
+    src2 = gen_load_fpr_F(dc, a->rs2);
+    gen_helper_fnsmuld(dst, tcg_env, src1, src2);
+    gen_store_fpr_D(dc, a->rd, dst);
+    return advance_pc(dc);
+}
+
 static bool do_ffff(DisasContext *dc, arg_r_r_r_r *a,
                     void (*func)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32))
 {
-- 
2.34.1



  parent reply	other threads:[~2024-05-26 19:47 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-26 19:42 [PATCH v2 00/37] target/sparc: Implement VIS4 Richard Henderson
2024-05-26 19:42 ` [PATCH v2 01/37] target/sparc: Fix ARRAY8 Richard Henderson
2024-05-26 19:42 ` [PATCH v2 02/37] target/sparc: Rewrite gen_edge Richard Henderson
2024-05-26 19:42 ` [PATCH v2 03/37] target/sparc: Fix do_dc Richard Henderson
2024-06-04 11:41   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 04/37] target/sparc: Fix helper_fmul8ulx16 Richard Henderson
2024-05-26 19:42 ` [PATCH v2 05/37] target/sparc: Perform DFPREG/QFPREG in decodetree Richard Henderson
2024-05-26 19:42 ` [PATCH v2 06/37] target/sparc: Remove gen_dest_fpr_D Richard Henderson
2024-05-26 19:42 ` [PATCH v2 07/37] target/sparc: Remove cpu_fpr[] Richard Henderson
2024-05-26 19:42 ` [PATCH v2 08/37] target/sparc: Use gvec for VIS1 parallel add/sub Richard Henderson
2024-06-04 13:18   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 09/37] target/sparc: Implement FMAf extension Richard Henderson
2024-05-26 19:42 ` [PATCH v2 10/37] target/sparc: Add feature bits for VIS 3 Richard Henderson
2024-05-26 19:42 ` [PATCH v2 11/37] target/sparc: Implement ADDXC, ADDXCcc Richard Henderson
2024-05-26 19:42 ` [PATCH v2 12/37] target/sparc: Implement CMASK instructions Richard Henderson
2024-06-04 13:30   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 13/37] target/sparc: Implement FCHKSM16 Richard Henderson
2024-06-05  8:07   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` Richard Henderson [this message]
2024-05-26 19:42 ` [PATCH v2 15/37] target/sparc: Implement FLCMP Richard Henderson
2024-05-26 19:42 ` [PATCH v2 16/37] target/sparc: Implement FMEAN16 Richard Henderson
2024-06-04 13:33   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 17/37] target/sparc: Implement FPADD64, FPSUB64 Richard Henderson
2024-05-26 19:42 ` [PATCH v2 18/37] target/sparc: Implement FPADDS, FPSUBS Richard Henderson
2024-06-05  8:04   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 19/37] target/sparc: Implement FPCMPEQ8, FPCMPNE8, FPCMPULE8, FPCMPUGT8 Richard Henderson
2024-06-05  7:57   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 20/37] target/sparc: Implement FSLL, FSRL, FSRA, FSLAS Richard Henderson
2024-06-04 13:38   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 21/37] target/sparc: Implement LDXEFSR Richard Henderson
2024-06-05  7:55   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 22/37] target/sparc: Implement LZCNT Richard Henderson
2024-05-26 19:42 ` [PATCH v2 23/37] target/sparc: Implement MOVsTOw, MOVdTOx, MOVwTOs, MOVxTOd Richard Henderson
2024-06-05  7:49   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 24/37] target/sparc: Implement PDISTN Richard Henderson
2024-05-26 19:42 ` [PATCH v2 25/37] target/sparc: Implement UMULXHI Richard Henderson
2024-06-04 13:40   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 26/37] target/sparc: Implement XMULX Richard Henderson
2024-06-04 13:41   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 27/37] target/sparc: Enable VIS3 feature bit Richard Henderson
2024-06-04 13:42   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 28/37] target/sparc: Implement IMA extension Richard Henderson
2024-05-26 19:42 ` [PATCH v2 29/37] target/sparc: Add feature bit for VIS4 Richard Henderson
2024-05-26 19:42 ` [PATCH v2 30/37] target/sparc: Implement FALIGNDATAi Richard Henderson
2024-06-05  7:35   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 31/37] target/sparc: Implement 8-bit FPADD, FPADDS, and FPADDUS Richard Henderson
2024-05-26 19:42 ` [PATCH v2 32/37] target/sparc: Implement VIS4 comparisons Richard Henderson
2024-06-05  7:10   ` Philippe Mathieu-Daudé
2024-05-26 19:42 ` [PATCH v2 33/37] target/sparc: Implement FPMIN, FPMAX Richard Henderson
2024-05-26 19:42 ` [PATCH v2 34/37] target/sparc: Implement SUBXC, SUBXCcc Richard Henderson
2024-05-26 19:42 ` [PATCH v2 35/37] target/sparc: Implement MWAIT Richard Henderson
2024-06-05  7:27   ` Philippe Mathieu-Daudé
2024-06-05 16:11     ` Richard Henderson
2024-05-26 19:42 ` [PATCH v2 36/37] target/sparc: Implement monitor ASIs Richard Henderson
2024-05-26 19:42 ` [PATCH v2 37/37] target/sparc: Enable VIS4 feature bit Richard Henderson
2024-05-28 21:29 ` [PATCH v2 00/37] target/sparc: Implement VIS4 Mark Cave-Ayland
2024-06-04  6:25   ` Mark Cave-Ayland

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=20240526194254.459395-15-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=mark.cave-ayland@ilande.co.uk \
    --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).