From: frank.chang@sifive.com
To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org
Cc: Frank Chang <frank.chang@sifive.com>,
Palmer Dabbelt <palmer@dabbelt.com>,
Richard Henderson <richard.henderson@linaro.org>,
Bin Meng <bin.meng@windriver.com>,
Alistair Francis <alistair.francis@wdc.com>
Subject: [PATCH v8 35/78] target/riscv: rvv-1.0: register gather instructions
Date: Fri, 15 Oct 2021 15:45:43 +0800 [thread overview]
Message-ID: <20211015074627.3957162-43-frank.chang@sifive.com> (raw)
In-Reply-To: <20211015074627.3957162-1-frank.chang@sifive.com>
From: Frank Chang <frank.chang@sifive.com>
* Add vrgatherei16.vv instruction.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/helper.h | 4 ++++
target/riscv/insn32.decode | 1 +
target/riscv/insn_trans/trans_rvv.c.inc | 27 ++++++++++++++++++++++---
target/riscv/vector_helper.c | 23 ++++++++++++---------
4 files changed, 43 insertions(+), 12 deletions(-)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 7646567eb27..bd0768d048f 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1059,6 +1059,10 @@ DEF_HELPER_6(vrgather_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vrgather_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vrgather_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vrgather_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgatherei16_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgatherei16_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgatherei16_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgatherei16_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vrgather_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vrgather_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vrgather_vx_w, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index ab274dcde12..4653a9679ef 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -645,6 +645,7 @@ vslidedown_vx 001111 . ..... ..... 100 ..... 1010111 @r_vm
vslidedown_vi 001111 . ..... ..... 011 ..... 1010111 @r_vm
vslide1down_vx 001111 . ..... ..... 110 ..... 1010111 @r_vm
vrgather_vv 001100 . ..... ..... 000 ..... 1010111 @r_vm
+vrgatherei16_vv 001110 . ..... ..... 000 ..... 1010111 @r_vm
vrgather_vx 001100 . ..... ..... 100 ..... 1010111 @r_vm
vrgather_vi 001100 . ..... ..... 011 ..... 1010111 @r_vm
vcompress_vm 010111 - ..... ..... 010 ..... 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 31ea231b3be..43da36f4200 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -3089,7 +3089,25 @@ static bool vrgather_vv_check(DisasContext *s, arg_rmrr *a)
require_vm(a->vm, a->rd);
}
+static bool vrgatherei16_vv_check(DisasContext *s, arg_rmrr *a)
+{
+ int8_t emul = MO_16 - s->sew + s->lmul;
+ return require_rvv(s) &&
+ vext_check_isa_ill(s) &&
+ (emul >= -3 && emul <= 3) &&
+ require_align(a->rd, s->lmul) &&
+ require_align(a->rs1, emul) &&
+ require_align(a->rs2, s->lmul) &&
+ (a->rd != a->rs2 && a->rd != a->rs1) &&
+ !is_overlapped(a->rd, 1 << MAX(s->lmul, 0),
+ a->rs1, 1 << MAX(emul, 0)) &&
+ !is_overlapped(a->rd, 1 << MAX(s->lmul, 0),
+ a->rs2, 1 << MAX(s->lmul, 0)) &&
+ require_vm(a->vm, a->rd);
+}
+
GEN_OPIVV_TRANS(vrgather_vv, vrgather_vv_check)
+GEN_OPIVV_TRANS(vrgatherei16_vv, vrgatherei16_vv_check)
static bool vrgather_vx_check(DisasContext *s, arg_rmrr *a)
{
@@ -3109,7 +3127,8 @@ static bool trans_vrgather_vx(DisasContext *s, arg_rmrr *a)
}
if (a->vm && s->vl_eq_vlmax) {
- int vlmax = s->vlen;
+ int scale = s->lmul - (s->sew + 3);
+ int vlmax = scale < 0 ? s->vlen >> -scale : s->vlen << scale;
TCGv_i64 dest = tcg_temp_new_i64();
if (a->rs1 == 0) {
@@ -3140,8 +3159,10 @@ static bool trans_vrgather_vi(DisasContext *s, arg_rmrr *a)
}
if (a->vm && s->vl_eq_vlmax) {
- if (a->rs1 >= s->vlen) {
- tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd),
+ int scale = s->lmul - (s->sew + 3);
+ int vlmax = scale < 0 ? s->vlen >> -scale : s->vlen << scale;
+ if (a->rs1 >= vlmax) {
+ tcg_gen_gvec_dup_imm(MO_64, vreg_ofs(s, a->rd),
MAXSZ(s), MAXSZ(s), 0);
} else {
tcg_gen_gvec_dup_mem(s->sew, vreg_ofs(s, a->rd),
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index b0dc971a860..86d03d8e395 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4460,11 +4460,11 @@ GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_w, uint32_t, H4)
GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_d, uint64_t, H8)
/* Vector Register Gather Instruction */
-#define GEN_VEXT_VRGATHER_VV(NAME, ETYPE, H) \
+#define GEN_VEXT_VRGATHER_VV(NAME, TS1, TS2, HS1, HS2) \
void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
CPURISCVState *env, uint32_t desc) \
{ \
- uint32_t vlmax = vext_max_elems(desc, ctzl(sizeof(ETYPE))); \
+ uint32_t vlmax = vext_max_elems(desc, ctzl(sizeof(TS1))); \
uint32_t vm = vext_vm(desc); \
uint32_t vl = env->vl; \
uint64_t index; \
@@ -4474,20 +4474,25 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \
if (!vm && !vext_elem_mask(v0, i)) { \
continue; \
} \
- index = *((ETYPE *)vs1 + H(i)); \
+ index = *((TS1 *)vs1 + HS1(i)); \
if (index >= vlmax) { \
- *((ETYPE *)vd + H(i)) = 0; \
+ *((TS2 *)vd + HS2(i)) = 0; \
} else { \
- *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(index)); \
+ *((TS2 *)vd + HS2(i)) = *((TS2 *)vs2 + HS2(index)); \
} \
} \
}
/* vd[i] = (vs1[i] >= VLMAX) ? 0 : vs2[vs1[i]]; */
-GEN_VEXT_VRGATHER_VV(vrgather_vv_b, uint8_t, H1)
-GEN_VEXT_VRGATHER_VV(vrgather_vv_h, uint16_t, H2)
-GEN_VEXT_VRGATHER_VV(vrgather_vv_w, uint32_t, H4)
-GEN_VEXT_VRGATHER_VV(vrgather_vv_d, uint64_t, H8)
+GEN_VEXT_VRGATHER_VV(vrgather_vv_b, uint8_t, uint8_t, H1, H1)
+GEN_VEXT_VRGATHER_VV(vrgather_vv_h, uint16_t, uint16_t, H2, H2)
+GEN_VEXT_VRGATHER_VV(vrgather_vv_w, uint32_t, uint32_t, H4, H4)
+GEN_VEXT_VRGATHER_VV(vrgather_vv_d, uint64_t, uint64_t, H8, H8)
+
+GEN_VEXT_VRGATHER_VV(vrgatherei16_vv_b, uint16_t, uint8_t, H2, H1)
+GEN_VEXT_VRGATHER_VV(vrgatherei16_vv_h, uint16_t, uint16_t, H2, H2)
+GEN_VEXT_VRGATHER_VV(vrgatherei16_vv_w, uint16_t, uint32_t, H2, H4)
+GEN_VEXT_VRGATHER_VV(vrgatherei16_vv_d, uint16_t, uint64_t, H2, H8)
#define GEN_VEXT_VRGATHER_VX(NAME, ETYPE, H) \
void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \
--
2.25.1
next prev parent reply other threads:[~2021-10-15 8:34 UTC|newest]
Thread overview: 120+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-15 7:45 [PATCH v8 00/78] support vector extension v1.0 frank.chang
2021-10-15 7:45 ` [PATCH v8 01/78] target/riscv: fix TB_FLAGS bits overlapping bug for rvv/rvh frank.chang
2021-10-16 3:04 ` Richard Henderson
2021-10-17 22:55 ` Alistair Francis
2021-10-18 5:38 ` Richard Henderson
2021-10-18 6:01 ` Alistair Francis
2021-10-15 7:45 ` [PATCH v8 02/78] target/riscv: drop vector 0.7.1 and add 1.0 support frank.chang
2021-10-15 7:45 ` [PATCH v8 03/78] target/riscv: Use FIELD_EX32() to extract wd field frank.chang
2021-10-15 7:45 ` [PATCH v8 04/78] target/riscv: rvv-1.0: add mstatus VS field frank.chang
2021-10-15 7:45 ` [PATCH v8 05/78] target/riscv: rvv-1.0: add sstatus " frank.chang
2021-10-15 7:45 ` [PATCH v8 06/78] target/riscv: rvv-1.0: introduce writable misa.v field frank.chang
2021-10-15 7:45 ` [PATCH v8 07/78] target/riscv: rvv-1.0: add translation-time vector context status frank.chang
2021-10-15 7:45 ` [PATCH v8 08/78] target/riscv: rvv-1.0: remove rvv related codes from fcsr registers frank.chang
2021-10-15 7:45 ` [PATCH v8 09/78] target/riscv: rvv-1.0: add vcsr register frank.chang
2021-10-15 7:45 ` [PATCH v8 10/78] target/riscv: rvv-1.0: add vlenb register frank.chang
2021-10-15 7:45 ` [PATCH v8 11/78] target/riscv: rvv-1.0: check MSTATUS_VS when accessing vector csr registers frank.chang
2021-10-15 7:45 ` [PATCH v8 12/78] target/riscv: rvv-1.0: remove MLEN calculations frank.chang
2021-10-15 7:45 ` [PATCH v8 13/78] target/riscv: rvv-1.0: add fractional LMUL frank.chang
2021-10-15 7:45 ` [PATCH v8 14/78] target/riscv: rvv-1.0: add VMA and VTA frank.chang
2021-10-15 7:45 ` [PATCH v8 15/78] target/riscv: rvv-1.0: update check functions frank.chang
2021-10-15 7:45 ` [PATCH v8 16/78] target/riscv: introduce more imm value modes in translator functions frank.chang
2021-10-15 7:45 ` [PATCH v8 17/78] target/riscv: rvv:1.0: add translation-time nan-box helper function frank.chang
2021-10-15 7:45 ` [PATCH 18/76] target/riscv: rvv-1.0: configure instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 18/78] target/riscv: rvv-1.0: remove amo operations instructions frank.chang
2021-10-18 5:44 ` Alistair Francis
2021-10-15 7:45 ` [PATCH v8 19/78] target/riscv: rvv-1.0: configure instructions frank.chang
2021-10-15 7:45 ` [PATCH 19/76] target/riscv: rvv-1.0: stride load and store instructions frank.chang
2021-10-15 7:45 ` [PATCH 20/76] target/riscv: rvv-1.0: index " frank.chang
2021-10-15 7:45 ` [PATCH v8 20/78] target/riscv: rvv-1.0: stride " frank.chang
2021-10-15 7:45 ` [PATCH 21/76] target/riscv: rvv-1.0: fix address index overflow bug of indexed load/store insns frank.chang
2021-10-15 7:45 ` [PATCH v8 21/78] target/riscv: rvv-1.0: index load and store instructions frank.chang
2021-10-15 7:45 ` [PATCH 22/76] target/riscv: rvv-1.0: fault-only-first unit stride load frank.chang
2021-10-15 7:45 ` [PATCH v8 22/78] target/riscv: rvv-1.0: fix address index overflow bug of indexed load/store insns frank.chang
2021-10-15 7:45 ` [PATCH 23/76] target/riscv: rvv-1.0: amo operations frank.chang
2021-10-15 7:45 ` [PATCH v8 23/78] target/riscv: rvv-1.0: fault-only-first unit stride load frank.chang
2021-10-15 7:45 ` [PATCH v8 24/78] target/riscv: rvv-1.0: load/store whole register instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 25/78] target/riscv: rvv-1.0: update vext_max_elems() for load/store insns frank.chang
2021-10-15 7:45 ` [PATCH v8 26/78] target/riscv: rvv-1.0: take fractional LMUL into vector max elements calculation frank.chang
2021-10-15 7:45 ` [PATCH v8 27/78] target/riscv: rvv-1.0: floating-point square-root instruction frank.chang
2021-10-15 7:45 ` [PATCH v8 28/78] target/riscv: rvv-1.0: floating-point classify instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 29/78] target/riscv: rvv-1.0: count population in mask instruction frank.chang
2021-10-18 5:46 ` Alistair Francis
2021-10-15 7:45 ` [PATCH 29/76] target/riscv: rvv-1.0: mask population count instruction frank.chang
2021-10-15 7:45 ` [PATCH v8 30/78] target/riscv: rvv-1.0: find-first-set mask bit instruction frank.chang
2021-10-18 5:47 ` Alistair Francis
2021-10-15 7:45 ` [PATCH v8 31/78] target/riscv: rvv-1.0: set-X-first mask bit instructions frank.chang
2021-10-18 5:53 ` Alistair Francis
2021-10-15 7:45 ` [PATCH v8 32/78] target/riscv: rvv-1.0: iota instruction frank.chang
2021-10-18 5:49 ` Alistair Francis
2021-10-15 7:45 ` [PATCH v8 33/78] target/riscv: rvv-1.0: element index instruction frank.chang
2021-10-18 5:54 ` Alistair Francis
2021-10-15 7:45 ` [PATCH v8 34/78] target/riscv: rvv-1.0: allow load element with sign-extended frank.chang
2021-10-21 4:28 ` Alistair Francis
2021-10-15 7:45 ` frank.chang [this message]
2021-10-15 7:45 ` [PATCH v8 36/78] target/riscv: rvv-1.0: integer scalar move instructions frank.chang
2021-10-21 4:24 ` Alistair Francis
2021-10-15 7:45 ` [PATCH v8 37/78] target/riscv: rvv-1.0: floating-point move instruction frank.chang
2021-10-15 7:45 ` [PATCH v8 38/78] target/riscv: rvv-1.0: floating-point scalar move instructions frank.chang
2021-10-21 4:26 ` Alistair Francis
2021-10-15 7:45 ` [PATCH v8 39/78] target/riscv: rvv-1.0: whole register " frank.chang
2021-10-21 4:27 ` Alistair Francis
2021-10-15 7:45 ` [PATCH v8 40/78] target/riscv: rvv-1.0: integer extension instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 41/78] target/riscv: rvv-1.0: single-width averaging add and subtract instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 42/78] target/riscv: rvv-1.0: single-width bit shift instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 43/78] target/riscv: rvv-1.0: integer add-with-carry/subtract-with-borrow frank.chang
2021-10-25 6:08 ` Alistair Francis
2021-10-15 7:45 ` [PATCH v8 44/78] target/riscv: rvv-1.0: narrowing integer right shift instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 45/78] target/riscv: rvv-1.0: widening integer multiply-add instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 46/78] target/riscv: rvv-1.0: single-width saturating add and subtract instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 47/78] target/riscv: rvv-1.0: integer comparison instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 48/78] target/riscv: rvv-1.0: floating-point compare instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 49/78] target/riscv: rvv-1.0: mask-register logical instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 50/78] target/riscv: rvv-1.0: slide instructions frank.chang
2021-10-15 7:45 ` [PATCH v8 51/78] target/riscv: rvv-1.0: floating-point " frank.chang
2021-10-25 6:13 ` Alistair Francis
2021-10-15 7:46 ` [PATCH v8 52/78] target/riscv: rvv-1.0: narrowing fixed-point clip instructions frank.chang
2021-10-15 7:46 ` [PATCH v8 53/78] target/riscv: rvv-1.0: single-width floating-point reduction frank.chang
2021-10-15 7:46 ` [PATCH v8 54/78] target/riscv: rvv-1.0: widening floating-point reduction instructions frank.chang
2021-10-15 7:46 ` [PATCH v8 55/78] target/riscv: rvv-1.0: single-width scaling shift instructions frank.chang
2021-10-15 7:46 ` [PATCH v8 56/78] target/riscv: rvv-1.0: remove widening saturating scaled multiply-add frank.chang
2021-10-15 7:46 ` [PATCH v8 57/78] target/riscv: rvv-1.0: remove vmford.vv and vmford.vf frank.chang
2021-10-15 7:46 ` [PATCH v8 58/78] target/riscv: rvv-1.0: remove integer extract instruction frank.chang
2021-10-15 7:46 ` [PATCH v8 59/78] target/riscv: rvv-1.0: floating-point min/max instructions frank.chang
2021-10-15 7:46 ` [PATCH v8 60/78] target/riscv: introduce floating-point rounding mode enum frank.chang
2021-10-15 7:46 ` [PATCH v8 61/78] target/riscv: rvv-1.0: floating-point/integer type-convert instructions frank.chang
2021-10-25 6:16 ` Alistair Francis
2021-10-15 7:46 ` [PATCH v8 62/78] target/riscv: rvv-1.0: widening floating-point/integer type-convert frank.chang
2021-10-26 6:29 ` Alistair Francis
2021-10-15 7:46 ` [PATCH v8 63/78] target/riscv: add "set round to odd" rounding mode helper function frank.chang
2021-10-26 6:30 ` Alistair Francis
2021-10-15 7:46 ` [PATCH v8 64/78] target/riscv: rvv-1.0: narrowing floating-point/integer type-convert frank.chang
2021-10-26 6:32 ` Alistair Francis
2021-10-15 7:46 ` [PATCH v8 65/78] target/riscv: rvv-1.0: relax RV_VLEN_MAX to 1024-bits frank.chang
2021-10-25 6:43 ` Alistair Francis
2021-10-15 7:46 ` [PATCH v8 66/78] target/riscv: rvv-1.0: implement vstart CSR frank.chang
2021-10-15 7:46 ` [PATCH v8 67/78] target/riscv: rvv-1.0: trigger illegal instruction exception if frm is not valid frank.chang
2021-10-15 7:46 ` [PATCH v8 68/78] target/riscv: rvv-1.0: set mstatus.SD bit when writing vector CSRs frank.chang
2021-10-15 7:46 ` [PATCH v8 69/78] target/riscv: gdb: support vector registers for rv64 & rv32 frank.chang
2021-10-15 7:46 ` [PATCH v8 70/78] target/riscv: rvv-1.0: floating-point reciprocal square-root estimate instruction frank.chang
2021-10-15 7:46 ` [PATCH v8 71/78] target/riscv: rvv-1.0: floating-point reciprocal " frank.chang
2021-10-15 7:46 ` [PATCH v8 72/78] target/riscv: set mstatus.SD bit when writing fp CSRs frank.chang
2021-10-25 6:42 ` Alistair Francis
2021-10-15 7:46 ` [PATCH v8 73/78] target/riscv: rvv-1.0: rename r2_zimm to r2_zimm11 frank.chang
2021-10-26 6:50 ` Alistair Francis
2021-10-15 7:46 ` [PATCH v8 74/78] target/riscv: rvv-1.0: add vsetivli instruction frank.chang
2021-10-26 6:52 ` Alistair Francis
2021-10-15 7:46 ` [PATCH v8 75/78] target/riscv: rvv-1.0: add evl parameter to vext_ldst_us() frank.chang
2021-10-15 7:46 ` [PATCH v8 76/78] target/riscv: rvv-1.0: add vector unit-stride mask load/store insns frank.chang
2021-10-15 7:46 ` [PATCH v8 77/78] target/riscv: rvv-1.0: rename vmandnot.mm and vmornot.mm to vmandn.mm and vmorn.mm frank.chang
2021-10-26 6:55 ` Alistair Francis
2021-10-15 7:46 ` [PATCH v8 78/78] target/riscv: rvv-1.0: update opivv_vadc_check() comment frank.chang
2021-10-26 6:49 ` Alistair Francis
2021-10-15 9:02 ` [PATCH v8 00/78] support vector extension v1.0 Frank Chang
2021-10-18 6:00 ` Alistair Francis
2021-10-18 6:09 ` Frank Chang
2021-10-18 6:12 ` Alistair Francis
2021-10-18 6:17 ` Frank Chang
2021-10-18 9:01 ` LIU Zhiwei
2021-10-18 9:34 ` LIU Zhiwei
2021-10-20 5:28 ` Alistair Francis
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=20211015074627.3957162-43-frank.chang@sifive.com \
--to=frank.chang@sifive.com \
--cc=alistair.francis@wdc.com \
--cc=bin.meng@windriver.com \
--cc=palmer@dabbelt.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-riscv@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).