From: LIU Zhiwei <zhiwei_liu@c-sky.com>
To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org
Cc: richard.henderson@linaro.org, wxy194768@alibaba-inc.com,
wenmeng_zhang@c-sky.com,
Alistair Francis <alistair.francis@wdc.com>,
palmer@dabbelt.com, LIU Zhiwei <zhiwei_liu@c-sky.com>
Subject: [PATCH v10 25/61] target/riscv: vector single-width averaging add and subtract
Date: Sat, 20 Jun 2020 12:36:25 +0800 [thread overview]
Message-ID: <20200620043701.1323-26-zhiwei_liu@c-sky.com> (raw)
In-Reply-To: <20200620043701.1323-1-zhiwei_liu@c-sky.com>
Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/riscv/helper.h | 17 ++++
target/riscv/insn32.decode | 5 ++
target/riscv/insn_trans/trans_rvv.inc.c | 7 ++
target/riscv/vector_helper.c | 100 ++++++++++++++++++++++++
4 files changed, 129 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 85bd4b91bc..db9e2024ae 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -725,3 +725,20 @@ DEF_HELPER_6(vssub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vaadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vasub_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vaadd_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vasub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 70df42de9a..57228242aa 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -419,6 +419,11 @@ vssubu_vv 100010 . ..... ..... 000 ..... 1010111 @r_vm
vssubu_vx 100010 . ..... ..... 100 ..... 1010111 @r_vm
vssub_vv 100011 . ..... ..... 000 ..... 1010111 @r_vm
vssub_vx 100011 . ..... ..... 100 ..... 1010111 @r_vm
+vaadd_vv 100100 . ..... ..... 000 ..... 1010111 @r_vm
+vaadd_vx 100100 . ..... ..... 100 ..... 1010111 @r_vm
+vaadd_vi 100100 . ..... ..... 011 ..... 1010111 @r_vm
+vasub_vv 100110 . ..... ..... 000 ..... 1010111 @r_vm
+vasub_vx 100110 . ..... ..... 100 ..... 1010111 @r_vm
vsetvli 0 ........... ..... 111 ..... 1010111 @r2_zimm
vsetvl 1000000 ..... ..... 111 ..... 1010111 @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 4d5eae8dde..ed1ee0f1b5 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1747,3 +1747,10 @@ GEN_OPIVX_TRANS(vssubu_vx, opivx_check)
GEN_OPIVX_TRANS(vssub_vx, opivx_check)
GEN_OPIVI_TRANS(vsaddu_vi, 1, vsaddu_vx, opivx_check)
GEN_OPIVI_TRANS(vsadd_vi, 0, vsadd_vx, opivx_check)
+
+/* Vector Single-Width Averaging Add and Subtract */
+GEN_OPIVV_TRANS(vaadd_vv, opivv_check)
+GEN_OPIVV_TRANS(vasub_vv, opivv_check)
+GEN_OPIVX_TRANS(vaadd_vx, opivx_check)
+GEN_OPIVX_TRANS(vasub_vx, opivx_check)
+GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 3d4212ea4a..ada95ab1e7 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2497,3 +2497,103 @@ GEN_VEXT_VX_RM(vssub_vx_b, 1, 1, clearb)
GEN_VEXT_VX_RM(vssub_vx_h, 2, 2, clearh)
GEN_VEXT_VX_RM(vssub_vx_w, 4, 4, clearl)
GEN_VEXT_VX_RM(vssub_vx_d, 8, 8, clearq)
+
+/* Vector Single-Width Averaging Add and Subtract */
+static inline uint8_t get_round(int vxrm, uint64_t v, uint8_t shift)
+{
+ uint8_t d = extract64(v, shift, 1);
+ uint8_t d1;
+ uint64_t D1, D2;
+
+ if (shift == 0 || shift > 64) {
+ return 0;
+ }
+
+ d1 = extract64(v, shift - 1, 1);
+ D1 = extract64(v, 0, shift);
+ if (vxrm == 0) { /* round-to-nearest-up (add +0.5 LSB) */
+ return d1;
+ } else if (vxrm == 1) { /* round-to-nearest-even */
+ if (shift > 1) {
+ D2 = extract64(v, 0, shift - 1);
+ return d1 & ((D2 != 0) | d);
+ } else {
+ return d1 & d;
+ }
+ } else if (vxrm == 3) { /* round-to-odd (OR bits into LSB, aka "jam") */
+ return !d & (D1 != 0);
+ }
+ return 0; /* round-down (truncate) */
+}
+
+static inline int32_t aadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+{
+ int64_t res = (int64_t)a + b;
+ uint8_t round = get_round(vxrm, res, 1);
+
+ return (res >> 1) + round;
+}
+
+static inline int64_t aadd64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+{
+ int64_t res = a + b;
+ uint8_t round = get_round(vxrm, res, 1);
+ int64_t over = (res ^ a) & (res ^ b) & INT64_MIN;
+
+ /* With signed overflow, bit 64 is inverse of bit 63. */
+ return ((res >> 1) ^ over) + round;
+}
+
+RVVCALL(OPIVV2_RM, vaadd_vv_b, OP_SSS_B, H1, H1, H1, aadd32)
+RVVCALL(OPIVV2_RM, vaadd_vv_h, OP_SSS_H, H2, H2, H2, aadd32)
+RVVCALL(OPIVV2_RM, vaadd_vv_w, OP_SSS_W, H4, H4, H4, aadd32)
+RVVCALL(OPIVV2_RM, vaadd_vv_d, OP_SSS_D, H8, H8, H8, aadd64)
+GEN_VEXT_VV_RM(vaadd_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_RM(vaadd_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_RM(vaadd_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_RM(vaadd_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2_RM, vaadd_vx_b, OP_SSS_B, H1, H1, aadd32)
+RVVCALL(OPIVX2_RM, vaadd_vx_h, OP_SSS_H, H2, H2, aadd32)
+RVVCALL(OPIVX2_RM, vaadd_vx_w, OP_SSS_W, H4, H4, aadd32)
+RVVCALL(OPIVX2_RM, vaadd_vx_d, OP_SSS_D, H8, H8, aadd64)
+GEN_VEXT_VX_RM(vaadd_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_RM(vaadd_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_RM(vaadd_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_RM(vaadd_vx_d, 8, 8, clearq)
+
+static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+{
+ int64_t res = (int64_t)a - b;
+ uint8_t round = get_round(vxrm, res, 1);
+
+ return (res >> 1) + round;
+}
+
+static inline int64_t asub64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+{
+ int64_t res = (int64_t)a - b;
+ uint8_t round = get_round(vxrm, res, 1);
+ int64_t over = (res ^ a) & (a ^ b) & INT64_MIN;
+
+ /* With signed overflow, bit 64 is inverse of bit 63. */
+ return ((res >> 1) ^ over) + round;
+}
+
+RVVCALL(OPIVV2_RM, vasub_vv_b, OP_SSS_B, H1, H1, H1, asub32)
+RVVCALL(OPIVV2_RM, vasub_vv_h, OP_SSS_H, H2, H2, H2, asub32)
+RVVCALL(OPIVV2_RM, vasub_vv_w, OP_SSS_W, H4, H4, H4, asub32)
+RVVCALL(OPIVV2_RM, vasub_vv_d, OP_SSS_D, H8, H8, H8, asub64)
+GEN_VEXT_VV_RM(vasub_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_RM(vasub_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_RM(vasub_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_RM(vasub_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2_RM, vasub_vx_b, OP_SSS_B, H1, H1, asub32)
+RVVCALL(OPIVX2_RM, vasub_vx_h, OP_SSS_H, H2, H2, asub32)
+RVVCALL(OPIVX2_RM, vasub_vx_w, OP_SSS_W, H4, H4, asub32)
+RVVCALL(OPIVX2_RM, vasub_vx_d, OP_SSS_D, H8, H8, asub64)
+GEN_VEXT_VX_RM(vasub_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_RM(vasub_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_RM(vasub_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_RM(vasub_vx_d, 8, 8, clearq)
--
2.23.0
next prev parent reply other threads:[~2020-06-20 5:28 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-20 4:36 [PATCH v10 00/61] target/riscv: support vector extension v0.7.1 LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 01/61] target/riscv: add vector extension field in CPURISCVState LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 02/61] target/riscv: implementation-defined constant parameters LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 03/61] target/riscv: support vector extension csr LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 04/61] target/riscv: add vector configure instruction LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 05/61] target/riscv: add an internals.h header LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 06/61] target/riscv: add vector stride load and store instructions LIU Zhiwei
2020-06-23 16:52 ` Alistair Francis
2020-06-23 21:32 ` LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 07/61] target/riscv: add vector index " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 08/61] target/riscv: add fault-only-first unit stride load LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 09/61] target/riscv: add vector amo operations LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 10/61] target/riscv: vector single-width integer add and subtract LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 11/61] target/riscv: vector widening " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 12/61] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 13/61] target/riscv: vector bitwise logical instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 14/61] target/riscv: vector single-width bit shift instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 15/61] target/riscv: vector narrowing integer right " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 16/61] target/riscv: vector integer comparison instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 17/61] target/riscv: vector integer min/max instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 18/61] target/riscv: vector single-width integer multiply instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 19/61] target/riscv: vector integer divide instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 20/61] target/riscv: vector widening integer multiply instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 21/61] target/riscv: vector single-width integer multiply-add instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 22/61] target/riscv: vector widening " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 23/61] target/riscv: vector integer merge and move instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 24/61] target/riscv: vector single-width saturating add and subtract LIU Zhiwei
2020-06-20 4:36 ` LIU Zhiwei [this message]
2020-06-20 4:36 ` [PATCH v10 26/61] target/riscv: vector single-width fractional multiply with rounding and saturation LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 27/61] target/riscv: vector widening saturating scaled multiply-add LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 28/61] target/riscv: vector single-width scaling shift instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 29/61] target/riscv: vector narrowing fixed-point clip instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 30/61] target/riscv: vector single-width floating-point add/subtract instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 31/61] target/riscv: vector widening " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 32/61] target/riscv: vector single-width floating-point multiply/divide instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 33/61] target/riscv: vector widening floating-point multiply LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 34/61] target/riscv: vector single-width floating-point fused multiply-add instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 35/61] target/riscv: vector widening " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 36/61] target/riscv: vector floating-point square-root instruction LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 37/61] target/riscv: vector floating-point min/max instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 38/61] target/riscv: vector floating-point sign-injection instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 39/61] target/riscv: vector floating-point compare instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 40/61] target/riscv: vector floating-point classify instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 41/61] target/riscv: vector floating-point merge instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 42/61] target/riscv: vector floating-point/integer type-convert instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 43/61] target/riscv: widening " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 44/61] target/riscv: narrowing " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 45/61] target/riscv: vector single-width integer reduction instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 46/61] target/riscv: vector wideing " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 47/61] target/riscv: vector single-width floating-point " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 48/61] target/riscv: vector widening " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 49/61] target/riscv: vector mask-register logical instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 50/61] target/riscv: vector mask population count vmpopc LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 51/61] target/riscv: vmfirst find-first-set mask bit LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 52/61] target/riscv: set-X-first " LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 53/61] target/riscv: vector iota instruction LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 54/61] target/riscv: vector element index instruction LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 55/61] target/riscv: integer extract instruction LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 56/61] target/riscv: integer scalar move instruction LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 57/61] target/riscv: floating-point scalar move instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 58/61] target/riscv: vector slide instructions LIU Zhiwei
2020-06-20 4:36 ` [PATCH v10 59/61] target/riscv: vector register gather instruction LIU Zhiwei
2020-06-20 4:37 ` [PATCH v10 60/61] target/riscv: vector compress instruction LIU Zhiwei
2020-06-20 4:37 ` [PATCH v10 61/61] target/riscv: configure and turn on vector extension from command line LIU Zhiwei
-- strict thread matches above, loose matches on Subject: below --
2020-06-20 2:54 [PATCH v10 00/61] target/riscv: support vector extension v0.7.1 LIU Zhiwei
2020-06-20 2:55 ` [PATCH v10 25/61] target/riscv: vector single-width averaging add and subtract LIU Zhiwei
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=20200620043701.1323-26-zhiwei_liu@c-sky.com \
--to=zhiwei_liu@c-sky.com \
--cc=alistair.francis@wdc.com \
--cc=palmer@dabbelt.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-riscv@nongnu.org \
--cc=richard.henderson@linaro.org \
--cc=wenmeng_zhang@c-sky.com \
--cc=wxy194768@alibaba-inc.com \
/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).