vitalif
/
mirror_qemu
mirror of https://github.com/proxmox/mirror_qemu
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

s390x/tcg: Implement VECTOR GALOIS FIELD MULTIPLY SUM (AND ACCUMULATE) 

A galois field multiplication in field 2 is like binary multiplication,
however instead of doing ordinary binary additions, xor's are performed.
So no carries are considered.

Implement all variants via helpers. s390_vec_sar() and s390_vec_shr()
will be reused later on.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
master
David Hildenbrand 2019-04-11 11:54:53 +02:00
parent 44951e6b03
commit 697a45d695
4 changed files with 217 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
target/s390x/helper.h
View File

@ -154,6 +154,14 @@ DEF_HELPER_FLAGS_3(gvec_vclz8, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
DEF_HELPER_FLAGS_3(gvec_vclz16, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
DEF_HELPER_FLAGS_3(gvec_vctz8, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
DEF_HELPER_FLAGS_3(gvec_vctz16, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
DEF_HELPER_FLAGS_4(gvec_vgfm8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
DEF_HELPER_FLAGS_4(gvec_vgfm16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
DEF_HELPER_FLAGS_4(gvec_vgfm32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
DEF_HELPER_FLAGS_4(gvec_vgfm64, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
DEF_HELPER_FLAGS_5(gvec_vgfma8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
DEF_HELPER_FLAGS_5(gvec_vgfma16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
DEF_HELPER_FLAGS_5(gvec_vgfma32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
DEF_HELPER_FLAGS_5(gvec_vgfma64, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
#ifndef CONFIG_USER_ONLY
DEF_HELPER_3(servc, i32, env, i64, i64)

4
target/s390x/insn-data.def
View File

@ -1090,6 +1090,10 @@
F(0xe752, VCTZ, VRR_a, V, 0, 0, 0, 0, vctz, 0, IF_VEC)
/* VECTOR EXCLUSIVE OR */
F(0xe76d, VX, VRR_c, V, 0, 0, 0, 0, vx, 0, IF_VEC)
/* VECTOR GALOIS FIELD MULTIPLY SUM */
F(0xe7b4, VGFM, VRR_c, V, 0, 0, 0, 0, vgfm, 0, IF_VEC)
/* VECTOR GALOIS FIELD MULTIPLY SUM AND ACCUMULATE */
F(0xe7bc, VGFMA, VRR_d, V, 0, 0, 0, 0, vgfma, 0, IF_VEC)
#ifndef CONFIG_USER_ONLY
/* COMPARE AND SWAP AND PURGE */

38
target/s390x/translate_vx.inc.c
View File

@ -1483,3 +1483,41 @@ static DisasJumpType op_vx(DisasContext *s, DisasOps *o)
get_field(s->fields, v3));
return DISAS_NEXT;
}
static DisasJumpType op_vgfm(DisasContext *s, DisasOps *o)
{
const uint8_t es = get_field(s->fields, m4);
static const GVecGen3 g[4] = {
{ .fno = gen_helper_gvec_vgfm8, },
{ .fno = gen_helper_gvec_vgfm16, },
{ .fno = gen_helper_gvec_vgfm32, },
{ .fno = gen_helper_gvec_vgfm64, },
};
if (es > ES_64) {
gen_program_exception(s, PGM_SPECIFICATION);
return DISAS_NORETURN;
}
gen_gvec_3(get_field(s->fields, v1), get_field(s->fields, v2),
get_field(s->fields, v3), &g[es]);
return DISAS_NEXT;
}
static DisasJumpType op_vgfma(DisasContext *s, DisasOps *o)
{
const uint8_t es = get_field(s->fields, m5);
static const GVecGen4 g[4] = {
{ .fno = gen_helper_gvec_vgfma8, },
{ .fno = gen_helper_gvec_vgfma16, },
{ .fno = gen_helper_gvec_vgfma32, },
{ .fno = gen_helper_gvec_vgfma64, },
};
if (es > ES_64) {
gen_program_exception(s, PGM_SPECIFICATION);
return DISAS_NORETURN;
}
gen_gvec_4(get_field(s->fields, v1), get_field(s->fields, v2),
get_field(s->fields, v3), get_field(s->fields, v4), &g[es]);
return DISAS_NEXT;
}

167
target/s390x/vec_int_helper.c
View File

@ -15,6 +15,59 @@
#include "vec.h"
#include "exec/helper-proto.h"
static bool s390_vec_is_zero(const S390Vector *v)
{
return !v->doubleword[0] && !v->doubleword[1];
}
static void s390_vec_xor(S390Vector *res, const S390Vector *a,
const S390Vector *b)
{
res->doubleword[0] = a->doubleword[0] ^ b->doubleword[0];
res->doubleword[1] = a->doubleword[1] ^ b->doubleword[1];
}
static void s390_vec_shl(S390Vector *d, const S390Vector *a, uint64_t count)
{
uint64_t tmp;
g_assert(count < 128);
if (count == 0) {
d->doubleword[0] = a->doubleword[0];
d->doubleword[1] = a->doubleword[1];
} else if (count == 64) {
d->doubleword[0] = a->doubleword[1];
d->doubleword[1] = 0;
} else if (count < 64) {
tmp = extract64(a->doubleword[1], 64 - count, count);
d->doubleword[1] = a->doubleword[1] << count;
d->doubleword[0] = (a->doubleword[0] << count) | tmp;
} else {
d->doubleword[0] = a->doubleword[1] << (count - 64);
d->doubleword[1] = 0;
}
}
static void s390_vec_shr(S390Vector *d, const S390Vector *a, uint64_t count)
{
uint64_t tmp;
g_assert(count < 128);
if (count == 0) {
d->doubleword[0] = a->doubleword[0];
d->doubleword[1] = a->doubleword[1];
} else if (count == 64) {
d->doubleword[1] = a->doubleword[0];
d->doubleword[0] = 0;
} else if (count < 64) {
tmp = a->doubleword[1] >> count;
d->doubleword[1] = deposit64(tmp, 64 - count, count, a->doubleword[0]);
d->doubleword[0] = a->doubleword[0] >> count;
} else {
d->doubleword[1] = a->doubleword[0] >> (count - 64);
d->doubleword[0] = 0;
}
}
#define DEF_VAVG(BITS) \
void HELPER(gvec_vavg##BITS)(void *v1, const void *v2, const void *v3, \
uint32_t desc) \
@ -74,3 +127,117 @@ void HELPER(gvec_vctz##BITS)(void *v1, const void *v2, uint32_t desc) \
}
DEF_VCTZ(8)
DEF_VCTZ(16)
/* like binary multiplication, but XOR instead of addition */
#define DEF_GALOIS_MULTIPLY(BITS, TBITS) \
static uint##TBITS##_t galois_multiply##BITS(uint##TBITS##_t a, \
uint##TBITS##_t b) \
{ \
uint##TBITS##_t res = 0; \
\
while (b) { \
if (b & 0x1) { \
res = res ^ a; \
} \
a = a << 1; \
b = b >> 1; \
} \
return res; \
}
DEF_GALOIS_MULTIPLY(8, 16)
DEF_GALOIS_MULTIPLY(16, 32)
DEF_GALOIS_MULTIPLY(32, 64)
static S390Vector galois_multiply64(uint64_t a, uint64_t b)
{
S390Vector res = {};
S390Vector va = {
.doubleword[1] = a,
};
S390Vector vb = {
.doubleword[1] = b,
};
while (!s390_vec_is_zero(&vb)) {
if (vb.doubleword[1] & 0x1) {
s390_vec_xor(&res, &res, &va);
}
s390_vec_shl(&va, &va, 1);
s390_vec_shr(&vb, &vb, 1);
}
return res;
}
#define DEF_VGFM(BITS, TBITS) \
void HELPER(gvec_vgfm##BITS)(void *v1, const void *v2, const void *v3, \
uint32_t desc) \
{ \
int i; \
\
for (i = 0; i < (128 / TBITS); i++) { \
uint##BITS##_t a = s390_vec_read_element##BITS(v2, i * 2); \
uint##BITS##_t b = s390_vec_read_element##BITS(v3, i * 2); \
uint##TBITS##_t d = galois_multiply##BITS(a, b); \
\
a = s390_vec_read_element##BITS(v2, i * 2 + 1); \
b = s390_vec_read_element##BITS(v3, i * 2 + 1); \
d = d ^ galois_multiply32(a, b); \
s390_vec_write_element##TBITS(v1, i, d); \
} \
}
DEF_VGFM(8, 16)
DEF_VGFM(16, 32)
DEF_VGFM(32, 64)
void HELPER(gvec_vgfm64)(void *v1, const void *v2, const void *v3,
uint32_t desc)
{
S390Vector tmp1, tmp2;
uint64_t a, b;
a = s390_vec_read_element64(v2, 0);
b = s390_vec_read_element64(v3, 0);
tmp1 = galois_multiply64(a, b);
a = s390_vec_read_element64(v2, 1);
b = s390_vec_read_element64(v3, 1);
tmp2 = galois_multiply64(a, b);
s390_vec_xor(v1, &tmp1, &tmp2);
}
#define DEF_VGFMA(BITS, TBITS) \
void HELPER(gvec_vgfma##BITS)(void *v1, const void *v2, const void *v3, \
const void *v4, uint32_t desc) \
{ \
int i; \
\
for (i = 0; i < (128 / TBITS); i++) { \
uint##BITS##_t a = s390_vec_read_element##BITS(v2, i * 2); \
uint##BITS##_t b = s390_vec_read_element##BITS(v3, i * 2); \
uint##TBITS##_t d = galois_multiply##BITS(a, b); \
\
a = s390_vec_read_element##BITS(v2, i * 2 + 1); \
b = s390_vec_read_element##BITS(v3, i * 2 + 1); \
d = d ^ galois_multiply32(a, b); \
d = d ^ s390_vec_read_element##TBITS(v4, i); \
s390_vec_write_element##TBITS(v1, i, d); \
} \
}
DEF_VGFMA(8, 16)
DEF_VGFMA(16, 32)
DEF_VGFMA(32, 64)
void HELPER(gvec_vgfma64)(void *v1, const void *v2, const void *v3,
const void *v4, uint32_t desc)
{
S390Vector tmp1, tmp2;
uint64_t a, b;
a = s390_vec_read_element64(v2, 0);
b = s390_vec_read_element64(v3, 0);
tmp1 = galois_multiply64(a, b);
a = s390_vec_read_element64(v2, 1);
b = s390_vec_read_element64(v3, 1);
tmp2 = galois_multiply64(a, b);
s390_vec_xor(&tmp1, &tmp1, &tmp2);
s390_vec_xor(v1, &tmp1, v4);
}