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 15/26] s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE *
Date: Tue,  8 Jun 2021 11:23:26 +0200	[thread overview]
Message-ID: <20210608092337.12221-16-david@redhat.com> (raw)
In-Reply-To: <20210608092337.12221-1-david@redhat.com>

In addition to 32/128bit variants, we also have to support the
"Signal-on-QNaN (SQ)" bit.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/helper.h           | 12 +++++++
 target/s390x/translate_vx.c.inc | 57 ++++++++++++++++++++++++-----
 target/s390x/vec_fpu_helper.c   | 64 +++++++++++++++++++++++++++++++--
 3 files changed, 121 insertions(+), 12 deletions(-)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 28797a6ccc..146836126c 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -252,12 +252,24 @@ DEF_HELPER_FLAGS_5(gvec_vfa64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfa128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfc64, void, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfk64, void, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfce32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfce32_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfce64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfce64_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfce128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfce128_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfch32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfch32_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfch64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfch64_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfch128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfch128_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfche32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfche32_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfche64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfche64_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vfche128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfche128_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcdg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcdlg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
diff --git a/target/s390x/translate_vx.c.inc b/target/s390x/translate_vx.c.inc
index 6241279e68..6f6ef6b6b8 100644
--- a/target/s390x/translate_vx.c.inc
+++ b/target/s390x/translate_vx.c.inc
@@ -2621,26 +2621,65 @@ static DisasJumpType op_vfc(DisasContext *s, DisasOps *o)
     const uint8_t m5 = get_field(s, m5);
     const uint8_t m6 = get_field(s, m6);
     const bool cs = extract32(m6, 0, 1);
-    gen_helper_gvec_3_ptr *fn;
-
-    if (fpf != FPF_LONG || extract32(m5, 0, 3) || extract32(m6, 1, 3)) {
-        gen_program_exception(s, PGM_SPECIFICATION);
-        return DISAS_NORETURN;
-    }
+    const bool sq = extract32(m5, 2, 1);
+    gen_helper_gvec_3_ptr *fn = NULL;
 
     switch (s->fields.op2) {
     case 0xe8:
-        fn = cs ? gen_helper_gvec_vfce64_cc : gen_helper_gvec_vfce64;
+        switch (fpf) {
+        case FPF_SHORT:
+            fn = cs ? gen_helper_gvec_vfce32_cc : gen_helper_gvec_vfce32;
+            break;
+        case FPF_LONG:
+            fn = cs ? gen_helper_gvec_vfce64_cc : gen_helper_gvec_vfce64;
+            break;
+        case FPF_EXT:
+            fn = cs ? gen_helper_gvec_vfce128_cc : gen_helper_gvec_vfce128;
+            break;
+        default:
+            break;
+        }
         break;
     case 0xeb:
-        fn = cs ? gen_helper_gvec_vfch64_cc : gen_helper_gvec_vfch64;
+        switch (fpf) {
+        case FPF_SHORT:
+            fn = cs ? gen_helper_gvec_vfch32_cc : gen_helper_gvec_vfch32;
+            break;
+        case FPF_LONG:
+            fn = cs ? gen_helper_gvec_vfch64_cc : gen_helper_gvec_vfch64;
+            break;
+        case FPF_EXT:
+            fn = cs ? gen_helper_gvec_vfch128_cc : gen_helper_gvec_vfch128;
+            break;
+        default:
+            break;
+        }
         break;
     case 0xea:
-        fn = cs ? gen_helper_gvec_vfche64_cc : gen_helper_gvec_vfche64;
+        switch (fpf) {
+        case FPF_SHORT:
+            fn = cs ? gen_helper_gvec_vfche32_cc : gen_helper_gvec_vfche32;
+            break;
+        case FPF_LONG:
+            fn = cs ? gen_helper_gvec_vfche64_cc : gen_helper_gvec_vfche64;
+            break;
+        case FPF_EXT:
+            fn = cs ? gen_helper_gvec_vfche128_cc : gen_helper_gvec_vfche128;
+            break;
+        default:
+            break;
+        }
         break;
     default:
         g_assert_not_reached();
     }
+
+    if (!fn || extract32(m5, 0, 2) || extract32(m6, 1, 3) ||
+        (!s390_has_feat(S390_FEAT_VECTOR_ENH) && (fpf != FPF_LONG || sq))) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
     gen_gvec_3_ptr(get_field(s, v1), get_field(s, v2), get_field(s, v3),
                    cpu_env, m5, fn);
     if (cs) {
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index 1df8f3d5a3..67dcd8b50a 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -340,6 +340,38 @@ void HELPER(gvec_##NAME##BITS)(const void *v1, const void *v2,                 \
 DEF_GVEC_WFC(wfc, false)
 DEF_GVEC_WFC(wfk, true)
 
+typedef bool (*vfc32_fn)(float32 a, float32 b, float_status *status);
+static int vfc32(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
+                 CPUS390XState *env, bool s, vfc32_fn fn, uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int match = 0;
+    int i;
+
+    for (i = 0; i < 4; i++) {
+        const float32 a = s390_vec_read_float32(v2, i);
+        const float32 b = s390_vec_read_float32(v3, i);
+
+        /* swap the order of the parameters, so we can use existing functions */
+        if (fn(b, a, &env->fpu_status)) {
+            match++;
+            s390_vec_write_element32(&tmp, i, -1u);
+        }
+        vxc = check_ieee_exc(env, i, false, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+    if (match) {
+        return s || match == 4 ? 0 : 1;
+    }
+    return 3;
+}
+
 typedef bool (*vfc64_fn)(float64 a, float64 b, float_status *status);
 static int vfc64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
                  CPUS390XState *env, bool s, vfc64_fn fn, uintptr_t retaddr)
@@ -372,12 +404,35 @@ static int vfc64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
     return 3;
 }
 
+typedef bool (*vfc128_fn)(float128 a, float128 b, float_status *status);
+static int vfc128(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
+                 CPUS390XState *env, bool s, vfc128_fn fn, uintptr_t retaddr)
+{
+    const float128 a = s390_vec_read_float128(v2);
+    const float128 b = s390_vec_read_float128(v3);
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    bool match = false;
+
+    /* swap the order of the parameters, so we can use existing functions */
+    if (fn(b, a, &env->fpu_status)) {
+        match = true;
+        s390_vec_write_element64(&tmp, 0, -1ull);
+        s390_vec_write_element64(&tmp, 1, -1ull);
+    }
+    vxc = check_ieee_exc(env, 0, false, &vec_exc);
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+    return match ? 0 : 3;
+}
+
 #define DEF_GVEC_VFC_B(NAME, OP, BITS)                                         \
 void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, const void *v3,       \
                                CPUS390XState *env, uint32_t desc)              \
 {                                                                              \
     const bool se = extract32(simd_data(desc), 3, 1);                          \
-    vfc##BITS##_fn fn = float##BITS##_##OP##_quiet;                            \
+    const bool sq = extract32(simd_data(desc), 2, 1);                          \
+    vfc##BITS##_fn fn = sq ? float##BITS##_##OP : float##BITS##_##OP##_quiet;  \
                                                                                \
     vfc##BITS(v1, v2, v3, env, se, fn, GETPC());                               \
 }                                                                              \
@@ -386,13 +441,16 @@ void HELPER(gvec_##NAME##BITS##_cc)(void *v1, const void *v2, const void *v3,  \
                                     CPUS390XState *env, uint32_t desc)         \
 {                                                                              \
     const bool se = extract32(simd_data(desc), 3, 1);                          \
-    vfc##BITS##_fn fn = float##BITS##_##OP##_quiet;                            \
+    const bool sq = extract32(simd_data(desc), 2, 1);                          \
+    vfc##BITS##_fn fn = sq ? float##BITS##_##OP : float##BITS##_##OP##_quiet;  \
                                                                                \
     env->cc_op = vfc##BITS(v1, v2, v3, env, se, fn, GETPC());                  \
 }
 
 #define DEF_GVEC_VFC(NAME, OP)                                                 \
-DEF_GVEC_VFC_B(NAME, OP, 64)
+DEF_GVEC_VFC_B(NAME, OP, 32)                                                   \
+DEF_GVEC_VFC_B(NAME, OP, 64)                                                   \
+DEF_GVEC_VFC_B(NAME, OP, 128)                                                  \
 
 DEF_GVEC_VFC(vfce, eq)
 DEF_GVEC_VFC(vfch, lt)
-- 
2.31.1



  parent reply	other threads:[~2021-06-08  9:36 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 ` [PATCH v4 14/26] s390x/tcg: Implement 32/128 bit for VECTOR (LOAD FP INTEGER|FP SQUARE ROOT) David Hildenbrand
2021-06-08  9:23 ` David Hildenbrand [this message]
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=20210608092337.12221-16-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.