From: Cornelia Huck <cohuck@redhat.com>
To: Peter Maydell <peter.maydell@linaro.org>
Cc: qemu-s390x@nongnu.org, Cornelia Huck <cohuck@redhat.com>,
Richard Henderson <richard.henderson@linaro.org>,
qemu-devel@nongnu.org, David Hildenbrand <david@redhat.com>
Subject: [PULL 05/37] s390x/tcg: Simplify vop64_2() handling
Date: Mon, 21 Jun 2021 11:58:10 +0200 [thread overview]
Message-ID: <20210621095842.335162-6-cohuck@redhat.com> (raw)
In-Reply-To: <20210621095842.335162-1-cohuck@redhat.com>
From: David Hildenbrand <david@redhat.com>
Let's rework our macros and simplify. We still need helper functions in
most cases due to the different parameters types.
Next, we'll only have 32/128bit variants for vfi and vfsq, so special
case the others.
Note that for vfsq, the XxC and erm passed in the simd_data() will never be
set, resulting in the same behavior.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210608092337.12221-5-david@redhat.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
---
target/s390x/helper.h | 6 -
target/s390x/translate_vx.c.inc | 18 ++-
target/s390x/vec_fpu_helper.c | 190 +++++++++-----------------------
3 files changed, 58 insertions(+), 156 deletions(-)
diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 2344f81273d0..4788c1ddaf8c 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -262,16 +262,11 @@ DEF_HELPER_FLAGS_5(gvec_vfche64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i3
DEF_HELPER_5(gvec_vfche64_cc, void, ptr, cptr, cptr, env, i32)
DEF_HELPER_5(gvec_vfche64s_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_vcdg64s, 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_vcdlg64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vcgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
-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_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)
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)
@@ -282,7 +277,6 @@ DEF_HELPER_FLAGS_6(gvec_vfma64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, en
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)
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_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 2d3fbdfab234..280d45bb196f 100644
--- a/target/s390x/translate_vx.c.inc
+++ b/target/s390x/translate_vx.c.inc
@@ -2558,19 +2558,19 @@ static DisasJumpType op_vcdg(DisasContext *s, DisasOps *o)
switch (s->fields.op2) {
case 0xc3:
- fn = se ? gen_helper_gvec_vcdg64s : gen_helper_gvec_vcdg64;
+ fn = gen_helper_gvec_vcdg64;
break;
case 0xc1:
- fn = se ? gen_helper_gvec_vcdlg64s : gen_helper_gvec_vcdlg64;
+ fn = gen_helper_gvec_vcdlg64;
break;
case 0xc2:
- fn = se ? gen_helper_gvec_vcgd64s : gen_helper_gvec_vcgd64;
+ fn = gen_helper_gvec_vcgd64;
break;
case 0xc0:
- fn = se ? gen_helper_gvec_vclgd64s : gen_helper_gvec_vclgd64;
+ fn = gen_helper_gvec_vclgd64;
break;
case 0xc7:
- fn = se ? gen_helper_gvec_vfi64s : gen_helper_gvec_vfi64;
+ fn = gen_helper_gvec_vfi64;
break;
case 0xc5:
fn = se ? gen_helper_gvec_vflr64s : gen_helper_gvec_vflr64;
@@ -2681,18 +2681,14 @@ 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 = gen_helper_gvec_vfsq64;
if (fpf != FPF_LONG || extract32(m4, 0, 3)) {
gen_program_exception(s, PGM_SPECIFICATION);
return DISAS_NORETURN;
}
- if (extract32(m4, 3, 1)) {
- fn = gen_helper_gvec_vfsq64s;
- }
- gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env,
- 0, fn);
+ gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, m4,
+ gen_helper_gvec_vfsq64);
return DISAS_NEXT;
}
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index 280ee0f1eaf6..ab23a597da73 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -88,7 +88,7 @@ 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);
+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,
uintptr_t retaddr)
@@ -99,9 +99,9 @@ static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
old_mode = s390_swap_bfp_rounding_mode(env, erm);
for (i = 0; i < 2; i++) {
- const uint64_t a = s390_vec_read_element64(v2, i);
+ const float64 a = s390_vec_read_float64(v2, i);
- s390_vec_write_element64(&tmp, i, fn(a, &env->fpu_status));
+ s390_vec_write_float64(&tmp, i, fn(a, &env->fpu_status));
vxc = check_ieee_exc(env, i, XxC, &vec_exc);
if (s || vxc) {
break;
@@ -112,6 +112,54 @@ static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
*v1 = tmp;
}
+static float64 vcdg64(float64 a, float_status *s)
+{
+ return int64_to_float64(a, s);
+}
+
+static float64 vcdlg64(float64 a, float_status *s)
+{
+ return uint64_to_float64(a, s);
+}
+
+static float64 vcgd64(float64 a, float_status *s)
+{
+ const float64 tmp = float64_to_int64(a, s);
+
+ return float64_is_any_nan(a) ? INT64_MIN : tmp;
+}
+
+static float64 vclgd64(float64 a, float_status *s)
+{
+ const float64 tmp = float64_to_uint64(a, s);
+
+ return float64_is_any_nan(a) ? 0 : tmp;
+}
+
+#define DEF_GVEC_VOP2_FN(NAME, FN, BITS) \
+void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, CPUS390XState *env, \
+ uint32_t desc) \
+{ \
+ const uint8_t erm = extract32(simd_data(desc), 4, 4); \
+ const bool se = extract32(simd_data(desc), 3, 1); \
+ const bool XxC = extract32(simd_data(desc), 2, 1); \
+ \
+ vop##BITS##_2(v1, v2, env, se, XxC, erm, FN, GETPC()); \
+}
+
+#define DEF_GVEC_VOP2_64(NAME) \
+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_64(vcdg)
+DEF_GVEC_VOP2_64(vcdlg)
+DEF_GVEC_VOP2_64(vcgd)
+DEF_GVEC_VOP2_64(vclgd)
+DEF_GVEC_VOP2(vfi, round_to_int)
+DEF_GVEC_VOP2(vfsq, sqrt)
+
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,
@@ -285,125 +333,6 @@ void HELPER(gvec_vfche64s_cc)(void *v1, const void *v2, const void *v3,
env->cc_op = vfc64(v1, v2, v3, env, true, float64_le_quiet, GETPC());
}
-static uint64_t vcdg64(uint64_t a, float_status *s)
-{
- return int64_to_float64(a, s);
-}
-
-void HELPER(gvec_vcdg64)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- const uint8_t erm = extract32(simd_data(desc), 4, 4);
- const bool XxC = extract32(simd_data(desc), 2, 1);
-
- vop64_2(v1, v2, env, false, XxC, erm, vcdg64, GETPC());
-}
-
-void HELPER(gvec_vcdg64s)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- const uint8_t erm = extract32(simd_data(desc), 4, 4);
- const bool XxC = extract32(simd_data(desc), 2, 1);
-
- vop64_2(v1, v2, env, true, XxC, erm, vcdg64, GETPC());
-}
-
-static uint64_t vcdlg64(uint64_t a, float_status *s)
-{
- return uint64_to_float64(a, s);
-}
-
-void HELPER(gvec_vcdlg64)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- const uint8_t erm = extract32(simd_data(desc), 4, 4);
- const bool XxC = extract32(simd_data(desc), 2, 1);
-
- vop64_2(v1, v2, env, false, XxC, erm, vcdlg64, GETPC());
-}
-
-void HELPER(gvec_vcdlg64s)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- const uint8_t erm = extract32(simd_data(desc), 4, 4);
- const bool XxC = extract32(simd_data(desc), 2, 1);
-
- vop64_2(v1, v2, env, true, XxC, erm, vcdlg64, GETPC());
-}
-
-static uint64_t vcgd64(uint64_t a, float_status *s)
-{
- const uint64_t tmp = float64_to_int64(a, s);
-
- return float64_is_any_nan(a) ? INT64_MIN : tmp;
-}
-
-void HELPER(gvec_vcgd64)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- const uint8_t erm = extract32(simd_data(desc), 4, 4);
- const bool XxC = extract32(simd_data(desc), 2, 1);
-
- vop64_2(v1, v2, env, false, XxC, erm, vcgd64, GETPC());
-}
-
-void HELPER(gvec_vcgd64s)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- const uint8_t erm = extract32(simd_data(desc), 4, 4);
- const bool XxC = extract32(simd_data(desc), 2, 1);
-
- vop64_2(v1, v2, env, true, XxC, erm, vcgd64, GETPC());
-}
-
-static uint64_t vclgd64(uint64_t a, float_status *s)
-{
- const uint64_t tmp = float64_to_uint64(a, s);
-
- return float64_is_any_nan(a) ? 0 : tmp;
-}
-
-void HELPER(gvec_vclgd64)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- const uint8_t erm = extract32(simd_data(desc), 4, 4);
- const bool XxC = extract32(simd_data(desc), 2, 1);
-
- vop64_2(v1, v2, env, false, XxC, erm, vclgd64, GETPC());
-}
-
-void HELPER(gvec_vclgd64s)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- const uint8_t erm = extract32(simd_data(desc), 4, 4);
- const bool XxC = extract32(simd_data(desc), 2, 1);
-
- vop64_2(v1, v2, env, true, XxC, erm, vclgd64, GETPC());
-}
-
-static uint64_t vfi64(uint64_t a, float_status *s)
-{
- return float64_round_to_int(a, s);
-}
-
-void HELPER(gvec_vfi64)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- const uint8_t erm = extract32(simd_data(desc), 4, 4);
- const bool XxC = extract32(simd_data(desc), 2, 1);
-
- vop64_2(v1, v2, env, false, XxC, erm, vfi64, GETPC());
-}
-
-void HELPER(gvec_vfi64s)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- const uint8_t erm = extract32(simd_data(desc), 4, 4);
- const bool XxC = extract32(simd_data(desc), 2, 1);
-
- vop64_2(v1, v2, env, true, XxC, erm, vfi64, GETPC());
-}
-
static void vfll32(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
bool s, uintptr_t retaddr)
{
@@ -530,23 +459,6 @@ void HELPER(gvec_vfms64s)(void *v1, const void *v2, const void *v3,
vfma64(v1, v2, v3, v4, env, true, float_muladd_negate_c, GETPC());
}
-static uint64_t vfsq64(uint64_t a, float_status *s)
-{
- return float64_sqrt(a, s);
-}
-
-void HELPER(gvec_vfsq64)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- vop64_2(v1, v2, env, false, false, 0, vfsq64, GETPC());
-}
-
-void HELPER(gvec_vfsq64s)(void *v1, const void *v2, CPUS390XState *env,
- uint32_t desc)
-{
- vop64_2(v1, v2, env, true, false, 0, vfsq64, 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:[~2021-06-21 10:07 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-21 9:58 [PULL 00/37] s390x update Cornelia Huck
2021-06-21 9:58 ` [PULL 01/37] s390x/kvm: remove unused gs handling Cornelia Huck
2021-06-21 9:58 ` [PULL 02/37] s390x/tcg: Fix FP CONVERT TO (LOGICAL) FIXED NaN handling Cornelia Huck
2021-06-21 9:58 ` [PULL 03/37] s390x/tcg: Fix instruction name for VECTOR FP LOAD (LENGTHENED|ROUNDED) Cornelia Huck
2021-06-21 9:58 ` [PULL 04/37] s390x/tcg: Simplify vop64_3() handling Cornelia Huck
2021-06-21 9:58 ` Cornelia Huck [this message]
2021-06-21 9:58 ` [PULL 06/37] s390x/tcg: Simplify vfc64() handling Cornelia Huck
2021-06-21 9:58 ` [PULL 07/37] s390x/tcg: Simplify vftci64() handling Cornelia Huck
2021-06-21 9:58 ` [PULL 08/37] s390x/tcg: Simplify vfma64() handling Cornelia Huck
2021-06-21 9:58 ` [PULL 09/37] s390x/tcg: Simplify vfll32() handling Cornelia Huck
2021-06-21 9:58 ` [PULL 10/37] s390x/tcg: Simplify vflr64() handling Cornelia Huck
2021-06-21 9:58 ` [PULL 11/37] s390x/tcg: Simplify wfc64() handling Cornelia Huck
2021-06-21 9:58 ` [PULL 12/37] s390x/tcg: Implement VECTOR BIT PERMUTE Cornelia Huck
2021-06-21 9:58 ` [PULL 13/37] s390x/tcg: Implement VECTOR MULTIPLY SUM LOGICAL Cornelia Huck
2021-06-21 9:58 ` [PULL 14/37] s390x/tcg: Implement 32/128 bit for VECTOR FP (ADD|DIVIDE|MULTIPLY|SUBTRACT) Cornelia Huck
2021-06-21 9:58 ` [PULL 15/37] s390x/tcg: Implement 32/128 bit for VECTOR (LOAD FP INTEGER|FP SQUARE ROOT) Cornelia Huck
2021-06-21 9:58 ` [PULL 16/37] s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE * Cornelia Huck
2021-06-21 9:58 ` [PULL 17/37] s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE (AND SIGNAL) SCALAR Cornelia Huck
2021-06-21 9:58 ` [PULL 18/37] s390x/tcg: Implement 64 bit for VECTOR FP LOAD LENGTHENED Cornelia Huck
2021-06-21 9:58 ` [PULL 19/37] s390x/tcg: Implement 128 bit for VECTOR FP LOAD ROUNDED Cornelia Huck
2021-06-21 9:58 ` [PULL 20/37] s390x/tcg: Implement 32/128 bit for VECTOR FP PERFORM SIGN OPERATION Cornelia Huck
2021-06-21 9:58 ` [PULL 21/37] s390x/tcg: Implement 32/128 bit for VECTOR FP TEST DATA CLASS IMMEDIATE Cornelia Huck
2021-06-21 9:58 ` [PULL 22/37] s390x/tcg: Implement 32/128 bit for VECTOR FP MULTIPLY AND (ADD|SUBTRACT) Cornelia Huck
2021-06-21 9:58 ` [PULL 23/37] s390x/tcg: Implement VECTOR FP NEGATIVE " Cornelia Huck
2021-06-21 9:58 ` [PULL 24/37] s390x/tcg: Implement VECTOR FP (MAXIMUM|MINIMUM) Cornelia Huck
2021-06-21 9:58 ` [PULL 25/37] linux-user: elf: s390x: Prepare for Vector enhancements facility Cornelia Huck
2021-06-21 9:58 ` [PULL 26/37] s390x/tcg: We support " Cornelia Huck
2021-06-21 9:58 ` [PULL 27/37] s390x/cpumodel: Bump up QEMU model to a stripped-down IBM z14 GA2 Cornelia Huck
2021-06-21 9:58 ` [PULL 28/37] configure: Check whether we can compile the s390-ccw bios with -msoft-float Cornelia Huck
2021-06-21 9:58 ` [PULL 29/37] target/s390x: Expose load_psw and get_psw_mask to cpu.h Cornelia Huck
2021-06-21 9:58 ` [PULL 30/37] target/s390x: Do not modify cpu state in s390_cpu_get_psw_mask Cornelia Huck
2021-06-21 9:58 ` [PULL 31/37] target/s390x: Improve s390_cpu_dump_state vs cc_op Cornelia Huck
2021-06-21 9:58 ` [PULL 32/37] target/s390x: Use s390_cpu_{set_psw, get_psw_mask} in gdbstub Cornelia Huck
2021-06-21 9:58 ` [PULL 33/37] linux-user/s390x: Save and restore psw.mask properly Cornelia Huck
2021-06-21 9:58 ` [PULL 34/37] s390x/css: Introduce an ESW struct Cornelia Huck
2021-06-21 9:58 ` [PULL 35/37] s390x/css: Split out the IRB sense data Cornelia Huck
2021-06-21 9:58 ` [PULL 36/37] s390x/css: Refactor IRB construction Cornelia Huck
2021-06-21 9:58 ` [PULL 37/37] s390x/css: Add passthrough IRB Cornelia Huck
2021-06-21 10:39 ` [PULL 00/37] s390x update no-reply
2021-06-22 15:07 ` Peter Maydell
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=20210621095842.335162-6-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).