mirror of
https://github.com/qemu/qemu.git
synced 2024-11-25 03:43:37 +08:00
target/arm: Implement SVE Predicate Misc Group
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180516223007.10256-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson
Peter Maydell
parent
516e246a1a
commit
028e2a7b87
@ -540,6 +540,7 @@ typedef struct CPUARMState {
|
||||
|
||||
#ifdef TARGET_AARCH64
|
||||
/* Store FFR as pregs[16] to make it easier to treat as any other. */
|
||||
#define FFR_PRED_NUM 16
|
||||
ARMPredicateReg pregs[17];
|
||||
/* Scratch space for aa64 sve predicate temporary. */
|
||||
ARMPredicateReg preg_tmp;
|
||||
@ -2975,4 +2976,7 @@ static inline uint64_t *aa64_vfp_qreg(CPUARMState *env, unsigned regno)
|
||||
return &env->vfp.zregs[regno].d[0];
|
||||
}
|
||||
|
||||
/* Shared between translate-sve.c and sve_helper.c. */
|
||||
extern const uint64_t pred_esz_masks[4];
|
||||
|
||||
#endif
|
||||
|
||||
@ -20,6 +20,9 @@
|
||||
DEF_HELPER_FLAGS_2(sve_predtest1, TCG_CALL_NO_WG, i32, i64, i64)
|
||||
DEF_HELPER_FLAGS_3(sve_predtest, TCG_CALL_NO_WG, i32, ptr, ptr, i32)
|
||||
|
||||
DEF_HELPER_FLAGS_3(sve_pfirst, TCG_CALL_NO_WG, i32, ptr, ptr, i32)
|
||||
DEF_HELPER_FLAGS_3(sve_pnext, TCG_CALL_NO_WG, i32, ptr, ptr, i32)
|
||||
|
||||
DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
|
||||
DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
|
||||
DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
|
||||
|
||||
@ -29,6 +29,7 @@
|
||||
# when creating helpers common to those for the individual
|
||||
# instruction patterns.
|
||||
|
||||
&rr_esz rd rn esz
|
||||
&rri rd rn imm
|
||||
&rrr_esz rd rn rm esz
|
||||
&rprr_s rd pg rn rm s
|
||||
@ -37,6 +38,12 @@
|
||||
# Named instruction formats. These are generally used to
|
||||
# reduce the amount of duplication between instruction patterns.
|
||||
|
||||
# Two operand with unused vector element size
|
||||
@pd_pn_e0 ........ ........ ....... rn:4 . rd:4 &rr_esz esz=0
|
||||
|
||||
# Two operand
|
||||
@pd_pn ........ esz:2 .. .... ....... rn:4 . rd:4 &rr_esz
|
||||
|
||||
# Three operand with unused vector element size
|
||||
@rd_rn_rm_e0 ........ ... rm:5 ... ... rn:5 rd:5 &rrr_esz esz=0
|
||||
|
||||
@ -77,6 +84,30 @@ NAND_pppp 00100101 1. 00 .... 01 .... 1 .... 1 .... @pd_pg_pn_pm_s
|
||||
# SVE predicate test
|
||||
PTEST 00100101 01 010000 11 pg:4 0 rn:4 0 0000
|
||||
|
||||
# SVE predicate initialize
|
||||
PTRUE 00100101 esz:2 01100 s:1 111000 pat:5 0 rd:4
|
||||
|
||||
# SVE initialize FFR
|
||||
SETFFR 00100101 0010 1100 1001 0000 0000 0000
|
||||
|
||||
# SVE zero predicate register
|
||||
PFALSE 00100101 0001 1000 1110 0100 0000 rd:4
|
||||
|
||||
# SVE predicate read from FFR (predicated)
|
||||
RDFFR_p 00100101 0 s:1 0110001111000 pg:4 0 rd:4
|
||||
|
||||
# SVE predicate read from FFR (unpredicated)
|
||||
RDFFR 00100101 0001 1001 1111 0000 0000 rd:4
|
||||
|
||||
# SVE FFR write from predicate (WRFFR)
|
||||
WRFFR 00100101 0010 1000 1001 000 rn:4 00000
|
||||
|
||||
# SVE predicate first active
|
||||
PFIRST 00100101 01 011 000 11000 00 .... 0 .... @pd_pn_e0
|
||||
|
||||
# SVE predicate next active
|
||||
PNEXT 00100101 .. 011 001 11000 10 .... 0 .... @pd_pn
|
||||
|
||||
### SVE Memory - 32-bit Gather and Unsized Contiguous Group
|
||||
|
||||
# SVE load predicate register
|
||||
|
||||
@ -115,3 +115,87 @@ LOGICAL_PPPP(sve_nand_pppp, DO_NAND)
|
||||
#undef DO_NAND
|
||||
#undef DO_SEL
|
||||
#undef LOGICAL_PPPP
|
||||
|
||||
/* Similar to the ARM LastActiveElement pseudocode function, except the
|
||||
result is multiplied by the element size. This includes the not found
|
||||
indication; e.g. not found for esz=3 is -8. */
|
||||
static intptr_t last_active_element(uint64_t *g, intptr_t words, intptr_t esz)
|
||||
{
|
||||
uint64_t mask = pred_esz_masks[esz];
|
||||
intptr_t i = words;
|
||||
|
||||
do {
|
||||
uint64_t this_g = g[--i] & mask;
|
||||
if (this_g) {
|
||||
return i * 64 + (63 - clz64(this_g));
|
||||
}
|
||||
} while (i > 0);
|
||||
return (intptr_t)-1 << esz;
|
||||
}
|
||||
|
||||
uint32_t HELPER(sve_pfirst)(void *vd, void *vg, uint32_t words)
|
||||
{
|
||||
uint32_t flags = PREDTEST_INIT;
|
||||
uint64_t *d = vd, *g = vg;
|
||||
intptr_t i = 0;
|
||||
|
||||
do {
|
||||
uint64_t this_d = d[i];
|
||||
uint64_t this_g = g[i];
|
||||
|
||||
if (this_g) {
|
||||
if (!(flags & 4)) {
|
||||
/* Set in D the first bit of G. */
|
||||
this_d |= this_g & -this_g;
|
||||
d[i] = this_d;
|
||||
}
|
||||
flags = iter_predtest_fwd(this_d, this_g, flags);
|
||||
}
|
||||
} while (++i < words);
|
||||
|
||||
return flags;
|
||||
}
|
||||
|
||||
uint32_t HELPER(sve_pnext)(void *vd, void *vg, uint32_t pred_desc)
|
||||
{
|
||||
intptr_t words = extract32(pred_desc, 0, SIMD_OPRSZ_BITS);
|
||||
intptr_t esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2);
|
||||
uint32_t flags = PREDTEST_INIT;
|
||||
uint64_t *d = vd, *g = vg, esz_mask;
|
||||
intptr_t i, next;
|
||||
|
||||
next = last_active_element(vd, words, esz) + (1 << esz);
|
||||
esz_mask = pred_esz_masks[esz];
|
||||
|
||||
/* Similar to the pseudocode for pnext, but scaled by ESZ
|
||||
so that we find the correct bit. */
|
||||
if (next < words * 64) {
|
||||
uint64_t mask = -1;
|
||||
|
||||
if (next & 63) {
|
||||
mask = ~((1ull << (next & 63)) - 1);
|
||||
next &= -64;
|
||||
}
|
||||
do {
|
||||
uint64_t this_g = g[next / 64] & esz_mask & mask;
|
||||
if (this_g != 0) {
|
||||
next = (next & -64) + ctz64(this_g);
|
||||
break;
|
||||
}
|
||||
next += 64;
|
||||
mask = -1;
|
||||
} while (next < words * 64);
|
||||
}
|
||||
|
||||
i = 0;
|
||||
do {
|
||||
uint64_t this_d = 0;
|
||||
if (i == next / 64) {
|
||||
this_d = 1ull << (next & 63);
|
||||
}
|
||||
d[i] = this_d;
|
||||
flags = iter_predtest_fwd(this_d, g[i] & esz_mask, flags);
|
||||
} while (++i < words);
|
||||
|
||||
return flags;
|
||||
}
|
||||
|
||||
@ -22,6 +22,7 @@
|
||||
#include "exec/exec-all.h"
|
||||
#include "tcg-op.h"
|
||||
#include "tcg-op-gvec.h"
|
||||
#include "tcg-gvec-desc.h"
|
||||
#include "qemu/log.h"
|
||||
#include "arm_ldst.h"
|
||||
#include "translate.h"
|
||||
@ -192,6 +193,12 @@ static void do_predtest(DisasContext *s, int dofs, int gofs, int words)
|
||||
tcg_temp_free_i32(t);
|
||||
}
|
||||
|
||||
/* For each element size, the bits within a predicate word that are active. */
|
||||
const uint64_t pred_esz_masks[4] = {
|
||||
0xffffffffffffffffull, 0x5555555555555555ull,
|
||||
0x1111111111111111ull, 0x0101010101010101ull
|
||||
};
|
||||
|
||||
/*
|
||||
*** SVE Logical - Unpredicated Group
|
||||
*/
|
||||
@ -541,6 +548,208 @@ static bool trans_PTEST(DisasContext *s, arg_PTEST *a, uint32_t insn)
|
||||
return true;
|
||||
}
|
||||
|
||||
/* See the ARM pseudocode DecodePredCount. */
|
||||
static unsigned decode_pred_count(unsigned fullsz, int pattern, int esz)
|
||||
{
|
||||
unsigned elements = fullsz >> esz;
|
||||
unsigned bound;
|
||||
|
||||
switch (pattern) {
|
||||
case 0x0: /* POW2 */
|
||||
return pow2floor(elements);
|
||||
case 0x1: /* VL1 */
|
||||
case 0x2: /* VL2 */
|
||||
case 0x3: /* VL3 */
|
||||
case 0x4: /* VL4 */
|
||||
case 0x5: /* VL5 */
|
||||
case 0x6: /* VL6 */
|
||||
case 0x7: /* VL7 */
|
||||
case 0x8: /* VL8 */
|
||||
bound = pattern;
|
||||
break;
|
||||
case 0x9: /* VL16 */
|
||||
case 0xa: /* VL32 */
|
||||
case 0xb: /* VL64 */
|
||||
case 0xc: /* VL128 */
|
||||
case 0xd: /* VL256 */
|
||||
bound = 16 << (pattern - 9);
|
||||
break;
|
||||
case 0x1d: /* MUL4 */
|
||||
return elements - elements % 4;
|
||||
case 0x1e: /* MUL3 */
|
||||
return elements - elements % 3;
|
||||
case 0x1f: /* ALL */
|
||||
return elements;
|
||||
default: /* #uimm5 */
|
||||
return 0;
|
||||
}
|
||||
return elements >= bound ? bound : 0;
|
||||
}
|
||||
|
||||
/* This handles all of the predicate initialization instructions,
|
||||
* PTRUE, PFALSE, SETFFR. For PFALSE, we will have set PAT == 32
|
||||
* so that decode_pred_count returns 0. For SETFFR, we will have
|
||||
* set RD == 16 == FFR.
|
||||
*/
|
||||
static bool do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag)
|
||||
{
|
||||
if (!sve_access_check(s)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
unsigned fullsz = vec_full_reg_size(s);
|
||||
unsigned ofs = pred_full_reg_offset(s, rd);
|
||||
unsigned numelem, setsz, i;
|
||||
uint64_t word, lastword;
|
||||
TCGv_i64 t;
|
||||
|
||||
numelem = decode_pred_count(fullsz, pat, esz);
|
||||
|
||||
/* Determine what we must store into each bit, and how many. */
|
||||
if (numelem == 0) {
|
||||
lastword = word = 0;
|
||||
setsz = fullsz;
|
||||
} else {
|
||||
setsz = numelem << esz;
|
||||
lastword = word = pred_esz_masks[esz];
|
||||
if (setsz % 64) {
|
||||
lastword &= ~(-1ull << (setsz % 64));
|
||||
}
|
||||
}
|
||||
|
||||
t = tcg_temp_new_i64();
|
||||
if (fullsz <= 64) {
|
||||
tcg_gen_movi_i64(t, lastword);
|
||||
tcg_gen_st_i64(t, cpu_env, ofs);
|
||||
goto done;
|
||||
}
|
||||
|
||||
if (word == lastword) {
|
||||
unsigned maxsz = size_for_gvec(fullsz / 8);
|
||||
unsigned oprsz = size_for_gvec(setsz / 8);
|
||||
|
||||
if (oprsz * 8 == setsz) {
|
||||
tcg_gen_gvec_dup64i(ofs, oprsz, maxsz, word);
|
||||
goto done;
|
||||
}
|
||||
if (oprsz * 8 == setsz + 8) {
|
||||
tcg_gen_gvec_dup64i(ofs, oprsz, maxsz, word);
|
||||
tcg_gen_movi_i64(t, 0);
|
||||
tcg_gen_st_i64(t, cpu_env, ofs + oprsz - 8);
|
||||
goto done;
|
||||
}
|
||||
}
|
||||
|
||||
setsz /= 8;
|
||||
fullsz /= 8;
|
||||
|
||||
tcg_gen_movi_i64(t, word);
|
||||
for (i = 0; i < setsz; i += 8) {
|
||||
tcg_gen_st_i64(t, cpu_env, ofs + i);
|
||||
}
|
||||
if (lastword != word) {
|
||||
tcg_gen_movi_i64(t, lastword);
|
||||
tcg_gen_st_i64(t, cpu_env, ofs + i);
|
||||
i += 8;
|
||||
}
|
||||
if (i < fullsz) {
|
||||
tcg_gen_movi_i64(t, 0);
|
||||
for (; i < fullsz; i += 8) {
|
||||
tcg_gen_st_i64(t, cpu_env, ofs + i);
|
||||
}
|
||||
}
|
||||
|
||||
done:
|
||||
tcg_temp_free_i64(t);
|
||||
|
||||
/* PTRUES */
|
||||
if (setflag) {
|
||||
tcg_gen_movi_i32(cpu_NF, -(word != 0));
|
||||
tcg_gen_movi_i32(cpu_CF, word == 0);
|
||||
tcg_gen_movi_i32(cpu_VF, 0);
|
||||
tcg_gen_mov_i32(cpu_ZF, cpu_NF);
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
static bool trans_PTRUE(DisasContext *s, arg_PTRUE *a, uint32_t insn)
|
||||
{
|
||||
return do_predset(s, a->esz, a->rd, a->pat, a->s);
|
||||
}
|
||||
|
||||
static bool trans_SETFFR(DisasContext *s, arg_SETFFR *a, uint32_t insn)
|
||||
{
|
||||
/* Note pat == 31 is #all, to set all elements. */
|
||||
return do_predset(s, 0, FFR_PRED_NUM, 31, false);
|
||||
}
|
||||
|
||||
static bool trans_PFALSE(DisasContext *s, arg_PFALSE *a, uint32_t insn)
|
||||
{
|
||||
/* Note pat == 32 is #unimp, to set no elements. */
|
||||
return do_predset(s, 0, a->rd, 32, false);
|
||||
}
|
||||
|
||||
static bool trans_RDFFR_p(DisasContext *s, arg_RDFFR_p *a, uint32_t insn)
|
||||
{
|
||||
/* The path through do_pppp_flags is complicated enough to want to avoid
|
||||
* duplication. Frob the arguments into the form of a predicated AND.
|
||||
*/
|
||||
arg_rprr_s alt_a = {
|
||||
.rd = a->rd, .pg = a->pg, .s = a->s,
|
||||
.rn = FFR_PRED_NUM, .rm = FFR_PRED_NUM,
|
||||
};
|
||||
return trans_AND_pppp(s, &alt_a, insn);
|
||||
}
|
||||
|
||||
static bool trans_RDFFR(DisasContext *s, arg_RDFFR *a, uint32_t insn)
|
||||
{
|
||||
return do_mov_p(s, a->rd, FFR_PRED_NUM);
|
||||
}
|
||||
|
||||
static bool trans_WRFFR(DisasContext *s, arg_WRFFR *a, uint32_t insn)
|
||||
{
|
||||
return do_mov_p(s, FFR_PRED_NUM, a->rn);
|
||||
}
|
||||
|
||||
static bool do_pfirst_pnext(DisasContext *s, arg_rr_esz *a,
|
||||
void (*gen_fn)(TCGv_i32, TCGv_ptr,
|
||||
TCGv_ptr, TCGv_i32))
|
||||
{
|
||||
if (!sve_access_check(s)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
TCGv_ptr t_pd = tcg_temp_new_ptr();
|
||||
TCGv_ptr t_pg = tcg_temp_new_ptr();
|
||||
TCGv_i32 t;
|
||||
unsigned desc;
|
||||
|
||||
desc = DIV_ROUND_UP(pred_full_reg_size(s), 8);
|
||||
desc = deposit32(desc, SIMD_DATA_SHIFT, 2, a->esz);
|
||||
|
||||
tcg_gen_addi_ptr(t_pd, cpu_env, pred_full_reg_offset(s, a->rd));
|
||||
tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, a->rn));
|
||||
t = tcg_const_i32(desc);
|
||||
|
||||
gen_fn(t, t_pd, t_pg, t);
|
||||
tcg_temp_free_ptr(t_pd);
|
||||
tcg_temp_free_ptr(t_pg);
|
||||
|
||||
do_pred_flags(t);
|
||||
tcg_temp_free_i32(t);
|
||||
return true;
|
||||
}
|
||||
|
||||
static bool trans_PFIRST(DisasContext *s, arg_rr_esz *a, uint32_t insn)
|
||||
{
|
||||
return do_pfirst_pnext(s, a, gen_helper_sve_pfirst);
|
||||
}
|
||||
|
||||
static bool trans_PNEXT(DisasContext *s, arg_rr_esz *a, uint32_t insn)
|
||||
{
|
||||
return do_pfirst_pnext(s, a, gen_helper_sve_pnext);
|
||||
}
|
||||
|
||||
/*
|
||||
*** SVE Memory - 32-bit Gather and Unsized Contiguous Group
|
||||
*/
|
||||
|
||||
Loading…
Reference in New Issue
Block a user