From: LIU Zhiwei <zhiwei_liu@c-sky.com>
To: richard.henderson@linaro.org, alistair23@gmail.com,
chihmin.chao@sifive.com, palmer@dabbelt.com
Cc: guoren@linux.alibaba.com, qemu-riscv@nongnu.org,
qemu-devel@nongnu.org, wxy194768@alibaba-inc.com,
wenmeng_zhang@c-sky.com, LIU Zhiwei <zhiwei_liu@c-sky.com>
Subject: [PATCH v3 34/60] target/riscv: vector widening floating-point fused multiply-add instructions
Date: Mon, 9 Mar 2020 16:20:16 +0800 [thread overview]
Message-ID: <20200309082042.12967-35-zhiwei_liu@c-sky.com> (raw)
In-Reply-To: <20200309082042.12967-1-zhiwei_liu@c-sky.com>
Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
target/riscv/helper.h | 17 +++++
target/riscv/insn32.decode | 8 +++
target/riscv/insn_trans/trans_rvv.inc.c | 10 +++
target/riscv/vector_helper.c | 84 +++++++++++++++++++++++++
4 files changed, 119 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 3b6dd96918..57e0fee929 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -888,3 +888,20 @@ DEF_HELPER_6(vfmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfnmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfnmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32)
DEF_HELPER_6(vfnmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32)
+
+DEF_HELPER_6(vfwmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32)
+DEF_HELPER_6(vfwnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 9834091a86..b7cb116cf4 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -474,6 +474,14 @@ vfmsub_vv 101010 . ..... ..... 001 ..... 1010111 @r_vm
vfmsub_vf 101010 . ..... ..... 101 ..... 1010111 @r_vm
vfnmsub_vv 101011 . ..... ..... 001 ..... 1010111 @r_vm
vfnmsub_vf 101011 . ..... ..... 101 ..... 1010111 @r_vm
+vfwmacc_vv 111100 . ..... ..... 001 ..... 1010111 @r_vm
+vfwmacc_vf 111100 . ..... ..... 101 ..... 1010111 @r_vm
+vfwnmacc_vv 111101 . ..... ..... 001 ..... 1010111 @r_vm
+vfwnmacc_vf 111101 . ..... ..... 101 ..... 1010111 @r_vm
+vfwmsac_vv 111110 . ..... ..... 001 ..... 1010111 @r_vm
+vfwmsac_vf 111110 . ..... ..... 101 ..... 1010111 @r_vm
+vfwnmsac_vv 111111 . ..... ..... 001 ..... 1010111 @r_vm
+vfwnmsac_vf 111111 . ..... ..... 101 ..... 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 172de867ea..06d6e2625b 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1824,3 +1824,13 @@ GEN_OPFVF_TRANS(vfmadd_vf, opfvf_check)
GEN_OPFVF_TRANS(vfnmadd_vf, opfvf_check)
GEN_OPFVF_TRANS(vfmsub_vf, opfvf_check)
GEN_OPFVF_TRANS(vfnmsub_vf, opfvf_check)
+
+/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
+GEN_OPFVV_WIDEN_TRANS(vfwmacc_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwnmacc_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwmsac_vv, opfvv_widen_check)
+GEN_OPFVV_WIDEN_TRANS(vfwnmsac_vv, opfvv_widen_check)
+GEN_OPFVF_WIDEN_TRANS(vfwmacc_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwnmacc_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwmsac_vf)
+GEN_OPFVF_WIDEN_TRANS(vfwnmsac_vf)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 2e0341adb0..9bff516a15 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3404,3 +3404,87 @@ RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64)
GEN_VEXT_VF(vfnmsub_vf_h, 2, 2, clearh)
GEN_VEXT_VF(vfnmsub_vf_w, 4, 4, clearl)
GEN_VEXT_VF(vfnmsub_vf_d, 8, 8, clearq)
+
+/* Vector Widening Floating-Point Fused Multiply-Add Instructions */
+static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
+{
+ return float32_muladd(float16_to_float32(a, true, s),
+ float16_to_float32(b, true, s), d, 0, s);
+}
+static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
+{
+ return float64_muladd(float32_to_float64(a, s),
+ float32_to_float64(b, s), d, 0, s);
+}
+RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16)
+RVVCALL(OPFVV3, vfwmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwmacc32)
+GEN_VEXT_VV_ENV(vfwmacc_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwmacc_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF3, vfwmacc_vf_h, WOP_UUU_H, H4, H2, fwmacc16)
+RVVCALL(OPFVF3, vfwmacc_vf_w, WOP_UUU_W, H8, H4, fwmacc32)
+GEN_VEXT_VF(vfwmacc_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwmacc_vf_w, 4, 8, clearq)
+
+static uint32_t fwnmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
+{
+ return float32_muladd(float16_to_float32(a, true, s),
+ float16_to_float32(b, true, s), d,
+ float_muladd_negate_c | float_muladd_negate_product, s);
+}
+static uint64_t fwnmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
+{
+ return float64_muladd(float32_to_float64(a, s),
+ float32_to_float64(b, s), d,
+ float_muladd_negate_c | float_muladd_negate_product, s);
+}
+RVVCALL(OPFVV3, vfwnmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwnmacc16)
+RVVCALL(OPFVV3, vfwnmacc_vv_w, WOP_UUU_W, H8, H4, H4, fwnmacc32)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwnmacc_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF3, vfwnmacc_vf_h, WOP_UUU_H, H4, H2, fwnmacc16)
+RVVCALL(OPFVF3, vfwnmacc_vf_w, WOP_UUU_W, H8, H4, fwnmacc32)
+GEN_VEXT_VF(vfwnmacc_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwnmacc_vf_w, 4, 8, clearq)
+
+static uint32_t fwmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
+{
+ return float32_muladd(float16_to_float32(a, true, s),
+ float16_to_float32(b, true, s), d,
+ float_muladd_negate_c, s);
+}
+static uint64_t fwmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
+{
+ return float64_muladd(float32_to_float64(a, s),
+ float32_to_float64(b, s), d,
+ float_muladd_negate_c, s);
+}
+
+RVVCALL(OPFVV3, vfwmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwmsac16)
+RVVCALL(OPFVV3, vfwmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwmsac32)
+GEN_VEXT_VV_ENV(vfwmsac_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwmsac_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF3, vfwmsac_vf_h, WOP_UUU_H, H4, H2, fwmsac16)
+RVVCALL(OPFVF3, vfwmsac_vf_w, WOP_UUU_W, H8, H4, fwmsac32)
+GEN_VEXT_VF(vfwmsac_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwmsac_vf_w, 4, 8, clearq)
+
+static uint32_t fwnmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
+{
+ return float32_muladd(float16_to_float32(a, true, s),
+ float16_to_float32(b, true, s), d,
+ float_muladd_negate_product, s);
+}
+static uint64_t fwnmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
+{
+ return float64_muladd(float32_to_float64(a, s),
+ float32_to_float64(b, s), d,
+ float_muladd_negate_product, s);
+}
+RVVCALL(OPFVV3, vfwnmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwnmsac16)
+RVVCALL(OPFVV3, vfwnmsac_vv_w, WOP_UUU_W, H8, H4, H4, fwnmsac32)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_h, 2, 4, clearl)
+GEN_VEXT_VV_ENV(vfwnmsac_vv_w, 4, 8, clearq)
+RVVCALL(OPFVF3, vfwnmsac_vf_h, WOP_UUU_H, H4, H2, fwnmsac16)
+RVVCALL(OPFVF3, vfwnmsac_vf_w, WOP_UUU_W, H8, H4, fwnmsac32)
+GEN_VEXT_VF(vfwnmsac_vf_h, 2, 4, clearl)
+GEN_VEXT_VF(vfwnmsac_vf_w, 4, 8, clearq)
--
2.23.0
next prev parent reply other threads:[~2020-03-09 8:32 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-09 8:19 [PATCH v3 00/60] target/riscv: support vector extension v0.7.1 LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 01/60] target/riscv: add vector extension field in CPURISCVState LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 02/60] target/riscv: implementation-defined constant parameters LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 03/60] target/riscv: support vector extension csr LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 04/60] target/riscv: add vector configure instruction LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 05/60] target/riscv: add vector stride load and store instructions LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 06/60] target/riscv: add vector index " LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 07/60] target/riscv: add fault-only-first unit stride load LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 08/60] target/riscv: add vector amo operations LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 09/60] target/riscv: vector single-width integer add and subtract LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 10/60] target/riscv: vector widening " LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 11/60] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 12/60] target/riscv: vector bitwise logical instructions LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 13/60] target/riscv: vector single-width bit shift instructions LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 14/60] target/riscv: vector narrowing integer right " LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 15/60] target/riscv: vector integer comparison instructions LIU Zhiwei
2020-03-09 8:19 ` [PATCH v3 17/60] target/riscv: vector single-width integer multiply instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 18/60] target/riscv: vector integer divide instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 19/60] target/riscv: vector widening integer multiply instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 20/60] target/riscv: vector single-width integer multiply-add instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 21/60] target/riscv: vector widening " LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 22/60] target/riscv: vector integer merge and move instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 23/60] target/riscv: vector single-width saturating add and subtract LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 24/60] target/riscv: vector single-width averaging " LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 25/60] target/riscv: vector single-width fractional multiply with rounding and saturation LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 26/60] target/riscv: vector widening saturating scaled multiply-add LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 27/60] target/riscv: vector single-width scaling shift instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 28/60] target/riscv: vector narrowing fixed-point clip instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 29/60] target/riscv: vector single-width floating-point add/subtract instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 30/60] target/riscv: vector widening " LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 31/60] target/riscv: vector single-width floating-point multiply/divide instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 32/60] target/riscv: vector widening floating-point multiply LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 33/60] target/riscv: vector single-width floating-point fused multiply-add instructions LIU Zhiwei
2020-03-09 8:20 ` LIU Zhiwei [this message]
2020-03-09 8:20 ` [PATCH v3 35/60] target/riscv: vector floating-point square-root instruction LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 36/60] target/riscv: vector floating-point min/max instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 37/60] target/riscv: vector floating-point sign-injection instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 38/60] target/riscv: vector floating-point compare instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 39/60] target/riscv: vector floating-point classify instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 40/60] target/riscv: vector floating-point merge instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 41/60] target/riscv: vector floating-point/integer type-convert instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 42/60] target/riscv: widening " LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 43/60] target/riscv: narrowing " LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 45/60] target/riscv: vector wideing integer reduction instructions LIU Zhiwei
2020-03-09 8:20 ` [PATCH v3 48/60] target/riscv: vector mask-register logical instructions 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=20200309082042.12967-35-zhiwei_liu@c-sky.com \
--to=zhiwei_liu@c-sky.com \
--cc=alistair23@gmail.com \
--cc=chihmin.chao@sifive.com \
--cc=guoren@linux.alibaba.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).