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 03/26] s390x/tcg: Simplify vop64_3() handling
Date: Tue, 8 Jun 2021 11:23:14 +0200 [thread overview]
Message-ID: <20210608092337.12221-4-david@redhat.com> (raw)
In-Reply-To: <20210608092337.12221-1-david@redhat.com>
Let's simplify, reworking our handler generation, passing the whole "m5"
register content and not providing specialized handlers for "se", and
reading/writing proper float64 values using new helpers.
Suggested-by: Richard Henderson <richard.henderson@linaro.org>
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 | 11 ++--
target/s390x/vec_fpu_helper.c | 94 +++++++++------------------------
3 files changed, 30 insertions(+), 79 deletions(-)
diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index d4e4f3388f..2344f81273 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -247,7 +247,6 @@ DEF_HELPER_6(gvec_vstrc_cc_rt32, void, ptr, cptr, cptr, cptr, env, i32)
/* === Vector Floating-Point Instructions */
DEF_HELPER_FLAGS_5(gvec_vfa64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfa64s, 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_vfce64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
@@ -271,7 +270,6 @@ DEF_HELPER_FLAGS_4(gvec_vcgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vclgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfd64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vfi64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
@@ -279,7 +277,6 @@ DEF_HELPER_FLAGS_4(gvec_vfll32s, 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_4(gvec_vflr64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfm64s, 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_vfma64s, 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)
@@ -287,7 +284,6 @@ DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, en
DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vfsq64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfs64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32)
DEF_HELPER_4(gvec_vftci64s, void, ptr, cptr, env, i32)
diff --git a/target/s390x/translate_vx.c.inc b/target/s390x/translate_vx.c.inc
index eb767f5288..2d3fbdfab2 100644
--- a/target/s390x/translate_vx.c.inc
+++ b/target/s390x/translate_vx.c.inc
@@ -2443,7 +2443,6 @@ static DisasJumpType op_vfa(DisasContext *s, DisasOps *o)
{
const uint8_t fpf = get_field(s, m4);
const uint8_t m5 = get_field(s, m5);
- const bool se = extract32(m5, 3, 1);
gen_helper_gvec_3_ptr *fn;
if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
@@ -2453,22 +2452,22 @@ static DisasJumpType op_vfa(DisasContext *s, DisasOps *o)
switch (s->fields.op2) {
case 0xe3:
- fn = se ? gen_helper_gvec_vfa64s : gen_helper_gvec_vfa64;
+ fn = gen_helper_gvec_vfa64;
break;
case 0xe5:
- fn = se ? gen_helper_gvec_vfd64s : gen_helper_gvec_vfd64;
+ fn = gen_helper_gvec_vfd64;
break;
case 0xe7:
- fn = se ? gen_helper_gvec_vfm64s : gen_helper_gvec_vfm64;
+ fn = gen_helper_gvec_vfm64;
break;
case 0xe2:
- fn = se ? gen_helper_gvec_vfs64s : gen_helper_gvec_vfs64;
+ fn = gen_helper_gvec_vfs64;
break;
default:
g_assert_not_reached();
}
gen_gvec_3_ptr(get_field(s, v1), get_field(s, v2),
- get_field(s, v3), cpu_env, 0, fn);
+ get_field(s, v3), cpu_env, m5, fn);
return DISAS_NEXT;
}
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index 56765918d2..280ee0f1ea 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -78,6 +78,16 @@ static void handle_ieee_exc(CPUS390XState *env, uint8_t vxc, uint8_t vec_exc,
}
}
+static float64 s390_vec_read_float64(const S390Vector *v, uint8_t enr)
+{
+ return make_float64(s390_vec_read_element64(v, enr));
+}
+
+static void s390_vec_write_float64(S390Vector *v, uint8_t enr, float64 data)
+{
+ return s390_vec_write_element64(v, enr, data);
+}
+
typedef uint64_t (*vop64_2_fn)(uint64_t 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,
@@ -102,7 +112,7 @@ static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
*v1 = tmp;
}
-typedef uint64_t (*vop64_3_fn)(uint64_t a, uint64_t b, float_status *s);
+typedef float64 (*vop64_3_fn)(float64 a, float64 b, float_status *s);
static void vop64_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
CPUS390XState *env, bool s, vop64_3_fn fn,
uintptr_t retaddr)
@@ -112,10 +122,10 @@ static void vop64_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
int i;
for (i = 0; i < 2; i++) {
- const uint64_t a = s390_vec_read_element64(v2, i);
- const uint64_t b = s390_vec_read_element64(v3, i);
+ const float64 a = s390_vec_read_float64(v2, i);
+ const float64 b = s390_vec_read_float64(v3, i);
- s390_vec_write_element64(&tmp, i, fn(a, b, &env->fpu_status));
+ s390_vec_write_float64(&tmp, i, fn(a, b, &env->fpu_status));
vxc = check_ieee_exc(env, i, false, &vec_exc);
if (s || vxc) {
break;
@@ -125,22 +135,19 @@ static void vop64_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
*v1 = tmp;
}
-static uint64_t vfa64(uint64_t a, uint64_t b, float_status *s)
-{
- return float64_add(a, b, s);
+#define DEF_GVEC_VOP3(NAME, OP) \
+void HELPER(gvec_##NAME##64)(void *v1, const void *v2, const void *v3, \
+ CPUS390XState *env, uint32_t desc) \
+{ \
+ const bool se = extract32(simd_data(desc), 3, 1); \
+ \
+ vop64_3(v1, v2, v3, env, se, float64_##OP, GETPC()); \
}
-void HELPER(gvec_vfa64)(void *v1, const void *v2, const void *v3,
- CPUS390XState *env, uint32_t desc)
-{
- vop64_3(v1, v2, v3, env, false, vfa64, GETPC());
-}
-
-void HELPER(gvec_vfa64s)(void *v1, const void *v2, const void *v3,
- CPUS390XState *env, uint32_t desc)
-{
- vop64_3(v1, v2, v3, env, true, vfa64, GETPC());
-}
+DEF_GVEC_VOP3(vfa, add)
+DEF_GVEC_VOP3(vfs, sub)
+DEF_GVEC_VOP3(vfd, div)
+DEF_GVEC_VOP3(vfm, mul)
static int wfc64(const S390Vector *v1, const S390Vector *v2,
CPUS390XState *env, bool signal, uintptr_t retaddr)
@@ -374,23 +381,6 @@ void HELPER(gvec_vclgd64s)(void *v1, const void *v2, CPUS390XState *env,
vop64_2(v1, v2, env, true, XxC, erm, vclgd64, GETPC());
}
-static uint64_t vfd64(uint64_t a, uint64_t b, float_status *s)
-{
- return float64_div(a, b, s);
-}
-
-void HELPER(gvec_vfd64)(void *v1, const void *v2, const void *v3,
- CPUS390XState *env, uint32_t desc)
-{
- vop64_3(v1, v2, v3, env, false, vfd64, GETPC());
-}
-
-void HELPER(gvec_vfd64s)(void *v1, const void *v2, const void *v3,
- CPUS390XState *env, uint32_t desc)
-{
- vop64_3(v1, v2, v3, env, true, vfd64, GETPC());
-}
-
static uint64_t vfi64(uint64_t a, float_status *s)
{
return float64_round_to_int(a, s);
@@ -492,23 +482,6 @@ void HELPER(gvec_vflr64s)(void *v1, const void *v2, CPUS390XState *env,
vflr64(v1, v2, env, true, XxC, erm, GETPC());
}
-static uint64_t vfm64(uint64_t a, uint64_t b, float_status *s)
-{
- return float64_mul(a, b, s);
-}
-
-void HELPER(gvec_vfm64)(void *v1, const void *v2, const void *v3,
- CPUS390XState *env, uint32_t desc)
-{
- vop64_3(v1, v2, v3, env, false, vfm64, GETPC());
-}
-
-void HELPER(gvec_vfm64s)(void *v1, const void *v2, const void *v3,
- CPUS390XState *env, uint32_t desc)
-{
- vop64_3(v1, v2, v3, env, true, vfm64, GETPC());
-}
-
static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
const S390Vector *v4, CPUS390XState *env, bool s, int flags,
uintptr_t retaddr)
@@ -574,23 +547,6 @@ void HELPER(gvec_vfsq64s)(void *v1, const void *v2, CPUS390XState *env,
vop64_2(v1, v2, env, true, false, 0, vfsq64, GETPC());
}
-static uint64_t vfs64(uint64_t a, uint64_t b, float_status *s)
-{
- return float64_sub(a, b, s);
-}
-
-void HELPER(gvec_vfs64)(void *v1, const void *v2, const void *v3,
- CPUS390XState *env, uint32_t desc)
-{
- vop64_3(v1, v2, v3, env, false, vfs64, GETPC());
-}
-
-void HELPER(gvec_vfs64s)(void *v1, const void *v2, const void *v3,
- CPUS390XState *env, uint32_t desc)
-{
- vop64_3(v1, v2, v3, env, true, vfs64, GETPC());
-}
-
static int vftci64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
bool s, uint16_t i3)
{
--
2.31.1
next prev parent reply other threads:[~2021-06-08 9:25 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 ` David Hildenbrand [this message]
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 ` [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=20210608092337.12221-4-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.