[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[RFC PATCH 31/43] target/loongarch: Implement vpcnt
From: |
Song Gao |
Subject: |
[RFC PATCH 31/43] target/loongarch: Implement vpcnt |
Date: |
Sat, 24 Dec 2022 16:16:21 +0800 |
This patch includes:
- VPCNT.{B/H/W/D}.
Signed-off-by: Song Gao <gaosong@loongson.cn>
---
target/loongarch/disas.c | 5 +++
target/loongarch/helper.h | 5 +++
target/loongarch/insn_trans/trans_lsx.c.inc | 5 +++
target/loongarch/insns.decode | 5 +++
target/loongarch/lsx_helper.c | 39 +++++++++++++++++++++
5 files changed, 59 insertions(+)
diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index 865c293f43..e3d4d105fe 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -1238,3 +1238,8 @@ INSN_LSX(vclz_b, vv)
INSN_LSX(vclz_h, vv)
INSN_LSX(vclz_w, vv)
INSN_LSX(vclz_d, vv)
+
+INSN_LSX(vpcnt_b, vv)
+INSN_LSX(vpcnt_h, vv)
+INSN_LSX(vpcnt_w, vv)
+INSN_LSX(vpcnt_d, vv)
diff --git a/target/loongarch/helper.h b/target/loongarch/helper.h
index 0080890bf6..6869b05105 100644
--- a/target/loongarch/helper.h
+++ b/target/loongarch/helper.h
@@ -593,3 +593,8 @@ DEF_HELPER_3(vclz_b, void, env, i32, i32)
DEF_HELPER_3(vclz_h, void, env, i32, i32)
DEF_HELPER_3(vclz_w, void, env, i32, i32)
DEF_HELPER_3(vclz_d, void, env, i32, i32)
+
+DEF_HELPER_3(vpcnt_b, void, env, i32, i32)
+DEF_HELPER_3(vpcnt_h, void, env, i32, i32)
+DEF_HELPER_3(vpcnt_w, void, env, i32, i32)
+DEF_HELPER_3(vpcnt_d, void, env, i32, i32)
diff --git a/target/loongarch/insn_trans/trans_lsx.c.inc
b/target/loongarch/insn_trans/trans_lsx.c.inc
index 105b6fac6e..38493c98b0 100644
--- a/target/loongarch/insn_trans/trans_lsx.c.inc
+++ b/target/loongarch/insn_trans/trans_lsx.c.inc
@@ -509,3 +509,8 @@ TRANS(vclz_b, gen_vv, gen_helper_vclz_b)
TRANS(vclz_h, gen_vv, gen_helper_vclz_h)
TRANS(vclz_w, gen_vv, gen_helper_vclz_w)
TRANS(vclz_d, gen_vv, gen_helper_vclz_d)
+
+TRANS(vpcnt_b, gen_vv, gen_helper_vpcnt_b)
+TRANS(vpcnt_h, gen_vv, gen_helper_vpcnt_h)
+TRANS(vpcnt_w, gen_vv, gen_helper_vpcnt_w)
+TRANS(vpcnt_d, gen_vv, gen_helper_vpcnt_d)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index 27cfa306c9..812262ff78 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -967,3 +967,8 @@ vclz_b 0111 00101001 11000 00100 ..... .....
@vv
vclz_h 0111 00101001 11000 00101 ..... ..... @vv
vclz_w 0111 00101001 11000 00110 ..... ..... @vv
vclz_d 0111 00101001 11000 00111 ..... ..... @vv
+
+vpcnt_b 0111 00101001 11000 01000 ..... ..... @vv
+vpcnt_h 0111 00101001 11000 01001 ..... ..... @vv
+vpcnt_w 0111 00101001 11000 01010 ..... ..... @vv
+vpcnt_d 0111 00101001 11000 01011 ..... ..... @vv
diff --git a/target/loongarch/lsx_helper.c b/target/loongarch/lsx_helper.c
index 0abb06781f..c9913dec54 100644
--- a/target/loongarch/lsx_helper.c
+++ b/target/loongarch/lsx_helper.c
@@ -3197,3 +3197,42 @@ DO_HELPER_VV(vclz_b, 8, helper_vv, do_vclz)
DO_HELPER_VV(vclz_h, 16, helper_vv, do_vclz)
DO_HELPER_VV(vclz_w, 32, helper_vv, do_vclz)
DO_HELPER_VV(vclz_d, 64, helper_vv, do_vclz)
+
+static uint64_t vpcnt(int64_t s1, int bit)
+{
+ uint64_t u1 = s1 & MAKE_64BIT_MASK(0, bit);
+
+ u1 = (u1 & 0x5555555555555555ULL) + ((u1 >> 1) & 0x5555555555555555ULL);
+ u1 = (u1 & 0x3333333333333333ULL) + ((u1 >> 2) & 0x3333333333333333ULL);
+ u1 = (u1 & 0x0F0F0F0F0F0F0F0FULL) + ((u1 >> 4) & 0x0F0F0F0F0F0F0F0FULL);
+ u1 = (u1 & 0x00FF00FF00FF00FFULL) + ((u1 >> 8) & 0x00FF00FF00FF00FFULL);
+ u1 = (u1 & 0x0000FFFF0000FFFFULL) + ((u1 >> 16) & 0x0000FFFF0000FFFFULL);
+ u1 = (u1 & 0x00000000FFFFFFFFULL) + ((u1 >> 32));
+
+ return u1;
+}
+
+static void do_vpcnt(vec_t *Vd, vec_t *Vj, int bit, int n)
+{
+ switch (bit) {
+ case 8:
+ Vd->B[n] = vpcnt(Vj->B[n], bit);
+ break;
+ case 16:
+ Vd->H[n] = vpcnt(Vj->H[n], bit);
+ break;
+ case 32:
+ Vd->W[n] = vpcnt(Vj->W[n], bit);
+ break;
+ case 64:
+ Vd->D[n] = vpcnt(Vj->D[n], bit);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
+DO_HELPER_VV(vpcnt_b, 8, helper_vv, do_vpcnt)
+DO_HELPER_VV(vpcnt_h, 16, helper_vv, do_vpcnt)
+DO_HELPER_VV(vpcnt_w, 32, helper_vv, do_vpcnt)
+DO_HELPER_VV(vpcnt_d, 64, helper_vv, do_vpcnt)
--
2.31.1
- [RFC PATCH 30/43] target/loongarch: Implement vclo vclz, (continued)
- [RFC PATCH 30/43] target/loongarch: Implement vclo vclz, Song Gao, 2022/12/24
- [RFC PATCH 38/43] target/loongarch: Implement vbitsel vset, Song Gao, 2022/12/24
- [RFC PATCH 35/43] target/loongarch: Implement LSX fpu fcvt instructions, Song Gao, 2022/12/24
- [RFC PATCH 39/43] target/loongarch: Implement vinsgr2vr vpickve2gr vreplgr2vr, Song Gao, 2022/12/24
- [RFC PATCH 41/43] target/loongarch: Implement vilvl vilvh vextrins vshuf, Song Gao, 2022/12/24
- [RFC PATCH 42/43] target/loongarch: Implement vld vst, Song Gao, 2022/12/24
- [RFC PATCH 43/43] target/loongarch: Implement vldi, Song Gao, 2022/12/24
- [RFC PATCH 18/43] target/loongarch: Implement vsat, Song Gao, 2022/12/24
- [RFC PATCH 19/43] target/loongarch: Implement vexth, Song Gao, 2022/12/24
- [RFC PATCH 31/43] target/loongarch: Implement vpcnt,
Song Gao <=
- [RFC PATCH 22/43] target/loongarch: Implement LSX logic instructions, Song Gao, 2022/12/24
- [RFC PATCH 15/43] target/loongarch: Implement vmul/vmuh/vmulw{ev/od}, Song Gao, 2022/12/24
- [RFC PATCH 12/43] target/loongarch: Implement vabsd, Song Gao, 2022/12/24
- [RFC PATCH 10/43] target/loongarch: Implement vaddw/vsubw, Song Gao, 2022/12/24
- [RFC PATCH 16/43] target/loongarch: Implement vmadd/vmsub/vmaddw{ev/od}, Song Gao, 2022/12/24