All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Hildenbrand <david@redhat.com>
To: qemu-devel@nongnu.org
Cc: Thomas Huth <thuth@redhat.com>,
	David Hildenbrand <david@redhat.com>,
	Cornelia Huck <cohuck@redhat.com>,
	Richard Henderson <richard.henderson@linaro.org>,
	Laurent Vivier <laurent@vivier.eu>,
	Halil Pasic <pasic@linux.ibm.com>,
	Christian Borntraeger <borntraeger@de.ibm.com>,
	qemu-s390x@nongnu.org
Subject: [PATCH v4 14/26] s390x/tcg: Implement 32/128 bit for VECTOR (LOAD FP INTEGER|FP SQUARE ROOT)
Date: Tue,  8 Jun 2021 11:23:25 +0200	[thread overview]
Message-ID: <20210608092337.12221-15-david@redhat.com> (raw)
In-Reply-To: <20210608092337.12221-1-david@redhat.com>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/helper.h           |  4 ++
 target/s390x/translate_vx.c.inc | 74 ++++++++++++++++++++++++++-------
 target/s390x/vec_fpu_helper.c   | 46 +++++++++++++++++++-
 3 files changed, 109 insertions(+), 15 deletions(-)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 2d5e382e61..28797a6ccc 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -265,7 +265,9 @@ DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfi32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfi128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
@@ -273,7 +275,9 @@ DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfsq32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfsq128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
diff --git a/target/s390x/translate_vx.c.inc b/target/s390x/translate_vx.c.inc
index 0fbd914b40..6241279e68 100644
--- a/target/s390x/translate_vx.c.inc
+++ b/target/s390x/translate_vx.c.inc
@@ -2654,35 +2654,63 @@ static DisasJumpType op_vcdg(DisasContext *s, DisasOps *o)
     const uint8_t fpf = get_field(s, m3);
     const uint8_t m4 = get_field(s, m4);
     const uint8_t erm = get_field(s, m5);
-    gen_helper_gvec_2_ptr *fn;
+    gen_helper_gvec_2_ptr *fn = NULL;
 
-    if (fpf != FPF_LONG || extract32(m4, 0, 2) || erm > 7 || erm == 2) {
-        gen_program_exception(s, PGM_SPECIFICATION);
-        return DISAS_NORETURN;
-    }
 
     switch (s->fields.op2) {
     case 0xc3:
-        fn = gen_helper_gvec_vcdg64;
+        if (fpf == FPF_LONG) {
+            fn = gen_helper_gvec_vcdg64;
+        }
         break;
     case 0xc1:
-        fn = gen_helper_gvec_vcdlg64;
+        if (fpf == FPF_LONG) {
+            fn = gen_helper_gvec_vcdlg64;
+        }
         break;
     case 0xc2:
-        fn = gen_helper_gvec_vcgd64;
+        if (fpf == FPF_LONG) {
+            fn = gen_helper_gvec_vcgd64;
+        }
         break;
     case 0xc0:
-        fn = gen_helper_gvec_vclgd64;
+        if (fpf == FPF_LONG) {
+            fn = gen_helper_gvec_vclgd64;
+        }
         break;
     case 0xc7:
-        fn = gen_helper_gvec_vfi64;
+        switch (fpf) {
+        case FPF_SHORT:
+            if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+                fn = gen_helper_gvec_vfi32;
+            }
+            break;
+        case FPF_LONG:
+            fn = gen_helper_gvec_vfi64;
+            break;
+        case FPF_EXT:
+            if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+                fn = gen_helper_gvec_vfi128;
+            }
+            break;
+        default:
+            break;
+        }
         break;
     case 0xc5:
-        fn = gen_helper_gvec_vflr64;
+        if (fpf == FPF_LONG) {
+            fn = gen_helper_gvec_vflr64;
+        }
         break;
     default:
         g_assert_not_reached();
     }
+
+    if (!fn || extract32(m4, 0, 2) || erm > 7 || erm == 2) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
     gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env,
                    deposit32(m4, 4, 4, erm), fn);
     return DISAS_NEXT;
@@ -2780,14 +2808,32 @@ static DisasJumpType op_vfsq(DisasContext *s, DisasOps *o)
 {
     const uint8_t fpf = get_field(s, m3);
     const uint8_t m4 = get_field(s, m4);
+    gen_helper_gvec_2_ptr *fn = NULL;
+
+    switch (fpf) {
+    case FPF_SHORT:
+        if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+            fn = gen_helper_gvec_vfsq32;
+        }
+        break;
+    case FPF_LONG:
+        fn = gen_helper_gvec_vfsq64;
+        break;
+    case FPF_EXT:
+        if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+            fn = gen_helper_gvec_vfsq128;
+        }
+        break;
+    default:
+        break;
+    }
 
-    if (fpf != FPF_LONG || extract32(m4, 0, 3)) {
+    if (!fn || extract32(m4, 0, 3)) {
         gen_program_exception(s, PGM_SPECIFICATION);
         return DISAS_NORETURN;
     }
 
-    gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, m4,
-                   gen_helper_gvec_vfsq64);
+    gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, m4, fn);
     return DISAS_NEXT;
 }
 
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index 3484c161ba..1df8f3d5a3 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -110,6 +110,30 @@ static void s390_vec_write_float128(S390Vector *v, float128 data)
     s390_vec_write_element64(v, 1, data.low);
 }
 
+typedef float32 (*vop32_2_fn)(float32 a, float_status *s);
+static void vop32_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
+                    bool s, bool XxC, uint8_t erm, vop32_2_fn fn,
+                    uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int i, old_mode;
+
+    old_mode = s390_swap_bfp_rounding_mode(env, erm);
+    for (i = 0; i < 4; i++) {
+        const float32 a = s390_vec_read_float32(v2, i);
+
+        s390_vec_write_float32(&tmp, i, fn(a, &env->fpu_status));
+        vxc = check_ieee_exc(env, i, XxC, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+    s390_restore_bfp_rounding_mode(env, old_mode);
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
 typedef float64 (*vop64_2_fn)(float64 a, float_status *s);
 static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
                     bool s, bool XxC, uint8_t erm, vop64_2_fn fn,
@@ -134,6 +158,24 @@ static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
     *v1 = tmp;
 }
 
+typedef float128 (*vop128_2_fn)(float128 a, float_status *s);
+static void vop128_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
+                    bool s, bool XxC, uint8_t erm, vop128_2_fn fn,
+                    uintptr_t retaddr)
+{
+    const float128 a = s390_vec_read_float128(v2);
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int old_mode;
+
+    old_mode = s390_swap_bfp_rounding_mode(env, erm);
+    s390_vec_write_float128(&tmp, fn(a, &env->fpu_status));
+    vxc = check_ieee_exc(env, 0, XxC, &vec_exc);
+    s390_restore_bfp_rounding_mode(env, old_mode);
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
 static float64 vcdg64(float64 a, float_status *s)
 {
     return int64_to_float64(a, s);
@@ -173,7 +215,9 @@ void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, CPUS390XState *env,   \
 DEF_GVEC_VOP2_FN(NAME, NAME##64, 64)
 
 #define DEF_GVEC_VOP2(NAME, OP)                                                \
-DEF_GVEC_VOP2_FN(NAME, float64_##OP, 64)
+DEF_GVEC_VOP2_FN(NAME, float32_##OP, 32)                                       \
+DEF_GVEC_VOP2_FN(NAME, float64_##OP, 64)                                       \
+DEF_GVEC_VOP2_FN(NAME, float128_##OP, 128)
 
 DEF_GVEC_VOP2_64(vcdg)
 DEF_GVEC_VOP2_64(vcdlg)
-- 
2.31.1



  parent reply	other threads:[~2021-06-08  9:32 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-08  9:23 [PATCH v4 00/26] s390x/tcg: Implement Vector enhancements facility and switch to z14 David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 01/26] s390x/tcg: Fix FP CONVERT TO (LOGICAL) FIXED NaN handling David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 02/26] s390x/tcg: Fix instruction name for VECTOR FP LOAD (LENGTHENED|ROUNDED) David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 03/26] s390x/tcg: Simplify vop64_3() handling David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 04/26] s390x/tcg: Simplify vop64_2() handling David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 05/26] s390x/tcg: Simplify vfc64() handling David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 06/26] s390x/tcg: Simplify vftci64() handling David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 07/26] s390x/tcg: Simplify vfma64() handling David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 08/26] s390x/tcg: Simplify vfll32() handling David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 09/26] s390x/tcg: Simplify vflr64() handling David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 10/26] s390x/tcg: Simplify wfc64() handling David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 11/26] s390x/tcg: Implement VECTOR BIT PERMUTE David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 12/26] s390x/tcg: Implement VECTOR MULTIPLY SUM LOGICAL David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 13/26] s390x/tcg: Implement 32/128 bit for VECTOR FP (ADD|DIVIDE|MULTIPLY|SUBTRACT) David Hildenbrand
2021-06-08  9:23 ` David Hildenbrand [this message]
2021-06-08  9:23 ` [PATCH v4 15/26] s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE * David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 16/26] s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE (AND SIGNAL) SCALAR David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 17/26] s390x/tcg: Implement 64 bit for VECTOR FP LOAD LENGTHENED David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 18/26] s390x/tcg: Implement 128 bit for VECTOR FP LOAD ROUNDED David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 19/26] s390x/tcg: Implement 32/128 bit for VECTOR FP PERFORM SIGN OPERATION David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 20/26] s390x/tcg: Implement 32/128 bit for VECTOR FP TEST DATA CLASS IMMEDIATE David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 21/26] s390x/tcg: Implement 32/128 bit for VECTOR FP MULTIPLY AND (ADD|SUBTRACT) David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 22/26] s390x/tcg: Implement VECTOR FP NEGATIVE " David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 23/26] s390x/tcg: Implement VECTOR FP (MAXIMUM|MINIMUM) David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 24/26] linux-user: elf: s390x: Prepare for Vector enhancements facility David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 25/26] s390x/tcg: We support " David Hildenbrand
2021-06-08  9:23 ` [PATCH v4 26/26] s390x/cpumodel: Bump up QEMU model to a stripped-down IBM z14 GA2 David Hildenbrand
2021-06-09  9:09 ` [PATCH v4 00/26] s390x/tcg: Implement Vector enhancements facility and switch to z14 Cornelia Huck

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=20210608092337.12221-15-david@redhat.com \
    --to=david@redhat.com \
    --cc=borntraeger@de.ibm.com \
    --cc=cohuck@redhat.com \
    --cc=laurent@vivier.eu \
    --cc=pasic@linux.ibm.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-s390x@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --cc=thuth@redhat.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.