From: Cornelia Huck <cohuck@redhat.com>
To: Peter Maydell <peter.maydell@linaro.org>
Cc: qemu-s390x@nongnu.org,
Richard Henderson <richard.henderson@linaro.org>,
qemu-devel@nongnu.org, David Hildenbrand <david@redhat.com>
Subject: [Qemu-devel] [PULL 26/35] s390x/tcg: Implement VECTOR FP MULTIPLY AND (ADD|SUBTRACT)
Date: Fri, 7 Jun 2019 11:52:28 +0200 [thread overview]
Message-ID: <20190607095237.11364-27-cohuck@redhat.com> (raw)
In-Reply-To: <20190607095237.11364-1-cohuck@redhat.com>
From: David Hildenbrand <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/insn-data.def | 4 +++
target/s390x/translate_vx.inc.c | 23 ++++++++++++++++
target/s390x/vec_fpu_helper.c | 48 +++++++++++++++++++++++++++++++++
4 files changed, 79 insertions(+)
diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 22e02a01784c..bcaabb91a510 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -284,6 +284,10 @@ 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)
+DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
#ifndef CONFIG_USER_ONLY
DEF_HELPER_3(servc, i32, env, i64, i64)
diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index e56059ac345f..e86ade9e443e 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1236,6 +1236,10 @@
F(0xe7c5, VFLR, VRR_a, V, 0, 0, 0, 0, vcdg, 0, IF_VEC)
/* VECTOR FP MULTIPLY */
F(0xe7e7, VFM, VRR_c, V, 0, 0, 0, 0, vfa, 0, IF_VEC)
+/* VECTOR FP MULTIPLY AND ADD */
+ F(0xe78f, VFMA, VRR_e, V, 0, 0, 0, 0, vfma, 0, IF_VEC)
+/* VECTOR FP MULTIPLY AND SUBTRACT */
+ F(0xe78e, VFMS, VRR_e, V, 0, 0, 0, 0, vfma, 0, IF_VEC)
#ifndef CONFIG_USER_ONLY
/* COMPARE AND SWAP AND PURGE */
diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
index ae31a327cf8e..b624c7a8aa6b 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -2704,3 +2704,26 @@ static DisasJumpType op_vfll(DisasContext *s, DisasOps *o)
0, fn);
return DISAS_NEXT;
}
+
+static DisasJumpType op_vfma(DisasContext *s, DisasOps *o)
+{
+ const uint8_t m5 = get_field(s->fields, m5);
+ const uint8_t fpf = get_field(s->fields, m6);
+ const bool se = extract32(m5, 3, 1);
+ gen_helper_gvec_4_ptr *fn;
+
+ if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
+ gen_program_exception(s, PGM_SPECIFICATION);
+ return DISAS_NORETURN;
+ }
+
+ if (s->fields->op2 == 0x8f) {
+ fn = se ? gen_helper_gvec_vfma64s : gen_helper_gvec_vfma64;
+ } else {
+ fn = se ? gen_helper_gvec_vfms64s : gen_helper_gvec_vfms64;
+ }
+ gen_gvec_4_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+ get_field(s->fields, v3), get_field(s->fields, v4), cpu_env,
+ 0, fn);
+ return DISAS_NEXT;
+}
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index 57b7fe4affce..7993a6fafa41 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -504,3 +504,51 @@ void HELPER(gvec_vfm64s)(void *v1, const void *v2, const void *v3,
{
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)
+{
+ uint8_t vxc, vec_exc = 0;
+ S390Vector tmp = {};
+ 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 uint64_t c = s390_vec_read_element64(v4, i);
+ uint64_t ret = float64_muladd(a, b, c, flags, &env->fpu_status);
+
+ s390_vec_write_element64(&tmp, i, ret);
+ vxc = check_ieee_exc(env, i, false, &vec_exc);
+ if (s || vxc) {
+ break;
+ }
+ }
+ handle_ieee_exc(env, vxc, vec_exc, retaddr);
+ *v1 = tmp;
+}
+
+void HELPER(gvec_vfma64)(void *v1, const void *v2, const void *v3,
+ const void *v4, CPUS390XState *env, uint32_t desc)
+{
+ vfma64(v1, v2, v3, v4, env, false, 0, GETPC());
+}
+
+void HELPER(gvec_vfma64s)(void *v1, const void *v2, const void *v3,
+ const void *v4, CPUS390XState *env, uint32_t desc)
+{
+ vfma64(v1, v2, v3, v4, env, true, 0, GETPC());
+}
+
+void HELPER(gvec_vfms64)(void *v1, const void *v2, const void *v3,
+ const void *v4, CPUS390XState *env, uint32_t desc)
+{
+ vfma64(v1, v2, v3, v4, env, false, float_muladd_negate_c, GETPC());
+}
+
+void HELPER(gvec_vfms64s)(void *v1, const void *v2, const void *v3,
+ const void *v4, CPUS390XState *env, uint32_t desc)
+{
+ vfma64(v1, v2, v3, v4, env, true, float_muladd_negate_c, GETPC());
+}
--
2.20.1
next prev parent reply other threads:[~2019-06-07 11:25 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-07 9:52 [Qemu-devel] [PULL 00/35] s390x updates Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 01/35] MAINTAINERS: cover tests/migration/s390x/ Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 02/35] vfio-ccw: support async command subregion Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 03/35] s390x/tcg: Implement VECTOR FIND ANY ELEMENT EQUAL Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 04/35] s390x/tcg: Implement VECTOR FIND " Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 05/35] s390x/tcg: Implement VECTOR FIND ELEMENT NOT EQUAL Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 06/35] s390x/tcg: Implement VECTOR ISOLATE STRING Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 07/35] s390x/tcg: Implement VECTOR STRING RANGE COMPARE Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 08/35] s390x: Align vector registers to 16 bytes Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 09/35] s390x: Use uint64_t for vector registers Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 10/35] s390x/tcg: Fix max_byte detection for stfle Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 11/35] s390x/tcg: Store only the necessary amount of doublewords for STFLE Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 12/35] s390x/tcg: Introduce tcg_s390_vector_exception() Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 13/35] s390x/tcg: Export float_comp_to_cc() and float(32|64|128)_dcmask() Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 14/35] s390x/tcg: Implement VECTOR FP ADD Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 15/35] s390x/tcg: Implement VECTOR FP COMPARE (AND SIGNAL) SCALAR Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 16/35] s390x/tcg: Implement VECTOR FP COMPARE (EQUAL|HIGH|HIGH OR EQUAL) Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 17/35] s390x/tcg: Implement VECTOR FP CONVERT FROM FIXED 64-BIT Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 18/35] s390x/tcg: Implement VECTOR FP CONVERT FROM LOGICAL 64-BIT Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 19/35] s390x/tcg: Implement VECTOR FP CONVERT TO FIXED 64-BIT Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 20/35] s390x/tcg: Implement VECTOR FP CONVERT TO LOGICAL 64-BIT Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 21/35] s390x/tcg: Implement VECTOR FP DIVIDE Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 22/35] s390x/tcg: Implement VECTOR LOAD FP INTEGER Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 23/35] s390x/tcg: Implement VECTOR LOAD LENGTHENED Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 24/35] s390x/tcg: Implement VECTOR LOAD ROUNDED Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 25/35] s390x/tcg: Implement VECTOR FP MULTIPLY Cornelia Huck
2019-06-07 9:52 ` Cornelia Huck [this message]
2019-06-07 9:52 ` [Qemu-devel] [PULL 27/35] s390x/tcg: Implement VECTOR FP PERFORM SIGN OPERATION Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 28/35] s390x/tcg: Implement VECTOR FP SQUARE ROOT Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 29/35] s390x/tcg: Implement VECTOR FP SUBTRACT Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 30/35] s390x/tcg: Implement VECTOR FP TEST DATA CLASS IMMEDIATE Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 31/35] s390x/tcg: Allow linux-user to use vector instructions Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 32/35] s390x/tcg: We support the Vector Facility Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 33/35] s390x: Bump the "qemu" CPU model up to a stripped-down z13 Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 34/35] s390x/tcg: Use tcg_gen_gvec_bitsel for VECTOR SELECT Cornelia Huck
2019-06-07 9:52 ` [Qemu-devel] [PULL 35/35] linux-user: elf: ELF_HWCAP for s390x Cornelia Huck
2019-06-07 9:57 ` [Qemu-devel] [PULL 00/35] s390x updates Peter Maydell
2019-06-07 9:58 ` Peter Maydell
2019-06-07 10:02 ` Cornelia Huck
2019-06-07 10:06 ` Cornelia Huck
2019-06-07 13:00 ` 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=20190607095237.11364-27-cohuck@redhat.com \
--to=cohuck@redhat.com \
--cc=david@redhat.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-devel@nongnu.org \
--cc=qemu-s390x@nongnu.org \
--cc=richard.henderson@linaro.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).