From: frank.chang@sifive.com
To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org
Cc: Sagar Karandikar <sagark@eecs.berkeley.edu>,
Frank Chang <frank.chang@sifive.com>,
Bastian Koppelmann <kbastian@mail.uni-paderborn.de>,
Richard Henderson <richard.henderson@linaro.org>,
Alistair Francis <Alistair.Francis@wdc.com>,
Palmer Dabbelt <palmer@dabbelt.com>,
LIU Zhiwei <zhiwei_liu@c-sky.com>
Subject: [PATCH v7 51/75] target/riscv: rvv-1.0: narrowing fixed-point clip instructions
Date: Fri, 26 Feb 2021 11:18:35 +0800 [thread overview]
Message-ID: <20210226031902.23656-52-frank.chang@sifive.com> (raw)
In-Reply-To: <20210226031902.23656-1-frank.chang@sifive.com>
From: Frank Chang <frank.chang@sifive.com>
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/riscv/helper.h | 24 ++++++------
target/riscv/insn32.decode | 12 +++---
target/riscv/insn_trans/trans_rvv.c.inc | 12 +++---
target/riscv/vector_helper.c | 52 ++++++++++++-------------
4 files changed, 50 insertions(+), 50 deletions(-)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 1e1e35bf800..2e4ed26f89c 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -766,18 +766,18 @@ DEF_HELPER_6(vssra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssra_vx_d, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclip_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclip_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclip_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclip_vx_b, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclip_vx_h, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclip_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_wv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclip_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclip_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_wx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_wx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_wx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vfadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vfadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 06e4e4f74b4..ac1bcab9627 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -491,12 +491,12 @@ vssrl_vi 101010 . ..... ..... 011 ..... 1010111 @r_vm
vssra_vv 101011 . ..... ..... 000 ..... 1010111 @r_vm
vssra_vx 101011 . ..... ..... 100 ..... 1010111 @r_vm
vssra_vi 101011 . ..... ..... 011 ..... 1010111 @r_vm
-vnclipu_vv 101110 . ..... ..... 000 ..... 1010111 @r_vm
-vnclipu_vx 101110 . ..... ..... 100 ..... 1010111 @r_vm
-vnclipu_vi 101110 . ..... ..... 011 ..... 1010111 @r_vm
-vnclip_vv 101111 . ..... ..... 000 ..... 1010111 @r_vm
-vnclip_vx 101111 . ..... ..... 100 ..... 1010111 @r_vm
-vnclip_vi 101111 . ..... ..... 011 ..... 1010111 @r_vm
+vnclipu_wv 101110 . ..... ..... 000 ..... 1010111 @r_vm
+vnclipu_wx 101110 . ..... ..... 100 ..... 1010111 @r_vm
+vnclipu_wi 101110 . ..... ..... 011 ..... 1010111 @r_vm
+vnclip_wv 101111 . ..... ..... 000 ..... 1010111 @r_vm
+vnclip_wx 101111 . ..... ..... 100 ..... 1010111 @r_vm
+vnclip_wi 101111 . ..... ..... 011 ..... 1010111 @r_vm
vfadd_vv 000000 . ..... ..... 001 ..... 1010111 @r_vm
vfadd_vf 000000 . ..... ..... 101 ..... 1010111 @r_vm
vfsub_vv 000010 . ..... ..... 001 ..... 1010111 @r_vm
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 26652f044f8..731c4bdd04b 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -2267,12 +2267,12 @@ GEN_OPIVI_TRANS(vssrl_vi, IMM_ZX, vssrl_vx, opivx_check)
GEN_OPIVI_TRANS(vssra_vi, IMM_SX, vssra_vx, opivx_check)
/* Vector Narrowing Fixed-Point Clip Instructions */
-GEN_OPIVV_NARROW_TRANS(vnclipu_vv)
-GEN_OPIVV_NARROW_TRANS(vnclip_vv)
-GEN_OPIVX_NARROW_TRANS(vnclipu_vx)
-GEN_OPIVX_NARROW_TRANS(vnclip_vx)
-GEN_OPIVI_NARROW_TRANS(vnclipu_vi, IMM_ZX, vnclipu_vx)
-GEN_OPIVI_NARROW_TRANS(vnclip_vi, IMM_ZX, vnclip_vx)
+GEN_OPIWV_NARROW_TRANS(vnclipu_wv)
+GEN_OPIWV_NARROW_TRANS(vnclip_wv)
+GEN_OPIWX_NARROW_TRANS(vnclipu_wx)
+GEN_OPIWX_NARROW_TRANS(vnclip_wx)
+GEN_OPIWI_NARROW_TRANS(vnclipu_wi, IMM_ZX, vnclipu_wx)
+GEN_OPIWI_NARROW_TRANS(vnclip_wi, IMM_ZX, vnclip_wx)
/*
*** Vector Float Point Arithmetic Instructions
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index df4f0b2d6a7..c5048882e91 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3084,19 +3084,19 @@ vnclip32(CPURISCVState *env, int vxrm, int64_t a, int32_t b)
}
}
-RVVCALL(OPIVV2_RM, vnclip_vv_b, NOP_SSS_B, H1, H2, H1, vnclip8)
-RVVCALL(OPIVV2_RM, vnclip_vv_h, NOP_SSS_H, H2, H4, H2, vnclip16)
-RVVCALL(OPIVV2_RM, vnclip_vv_w, NOP_SSS_W, H4, H8, H4, vnclip32)
-GEN_VEXT_VV_RM(vnclip_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vnclip_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vnclip_vv_w, 4, 4)
-
-RVVCALL(OPIVX2_RM, vnclip_vx_b, NOP_SSS_B, H1, H2, vnclip8)
-RVVCALL(OPIVX2_RM, vnclip_vx_h, NOP_SSS_H, H2, H4, vnclip16)
-RVVCALL(OPIVX2_RM, vnclip_vx_w, NOP_SSS_W, H4, H8, vnclip32)
-GEN_VEXT_VX_RM(vnclip_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vnclip_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vnclip_vx_w, 4, 4)
+RVVCALL(OPIVV2_RM, vnclip_wv_b, NOP_SSS_B, H1, H2, H1, vnclip8)
+RVVCALL(OPIVV2_RM, vnclip_wv_h, NOP_SSS_H, H2, H4, H2, vnclip16)
+RVVCALL(OPIVV2_RM, vnclip_wv_w, NOP_SSS_W, H4, H8, H4, vnclip32)
+GEN_VEXT_VV_RM(vnclip_wv_b, 1, 1)
+GEN_VEXT_VV_RM(vnclip_wv_h, 2, 2)
+GEN_VEXT_VV_RM(vnclip_wv_w, 4, 4)
+
+RVVCALL(OPIVX2_RM, vnclip_wx_b, NOP_SSS_B, H1, H2, vnclip8)
+RVVCALL(OPIVX2_RM, vnclip_wx_h, NOP_SSS_H, H2, H4, vnclip16)
+RVVCALL(OPIVX2_RM, vnclip_wx_w, NOP_SSS_W, H4, H8, vnclip32)
+GEN_VEXT_VX_RM(vnclip_wx_b, 1, 1)
+GEN_VEXT_VX_RM(vnclip_wx_h, 2, 2)
+GEN_VEXT_VX_RM(vnclip_wx_w, 4, 4)
static inline uint8_t
vnclipu8(CPURISCVState *env, int vxrm, uint16_t a, uint8_t b)
@@ -3134,7 +3134,7 @@ static inline uint32_t
vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b)
{
uint8_t round, shift = b & 0x3f;
- int64_t res;
+ uint64_t res;
round = get_round(vxrm, a, shift);
res = (a >> shift) + round;
@@ -3146,19 +3146,19 @@ vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b)
}
}
-RVVCALL(OPIVV2_RM, vnclipu_vv_b, NOP_UUU_B, H1, H2, H1, vnclipu8)
-RVVCALL(OPIVV2_RM, vnclipu_vv_h, NOP_UUU_H, H2, H4, H2, vnclipu16)
-RVVCALL(OPIVV2_RM, vnclipu_vv_w, NOP_UUU_W, H4, H8, H4, vnclipu32)
-GEN_VEXT_VV_RM(vnclipu_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vnclipu_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vnclipu_vv_w, 4, 4)
+RVVCALL(OPIVV2_RM, vnclipu_wv_b, NOP_UUU_B, H1, H2, H1, vnclipu8)
+RVVCALL(OPIVV2_RM, vnclipu_wv_h, NOP_UUU_H, H2, H4, H2, vnclipu16)
+RVVCALL(OPIVV2_RM, vnclipu_wv_w, NOP_UUU_W, H4, H8, H4, vnclipu32)
+GEN_VEXT_VV_RM(vnclipu_wv_b, 1, 1)
+GEN_VEXT_VV_RM(vnclipu_wv_h, 2, 2)
+GEN_VEXT_VV_RM(vnclipu_wv_w, 4, 4)
-RVVCALL(OPIVX2_RM, vnclipu_vx_b, NOP_UUU_B, H1, H2, vnclipu8)
-RVVCALL(OPIVX2_RM, vnclipu_vx_h, NOP_UUU_H, H2, H4, vnclipu16)
-RVVCALL(OPIVX2_RM, vnclipu_vx_w, NOP_UUU_W, H4, H8, vnclipu32)
-GEN_VEXT_VX_RM(vnclipu_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vnclipu_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vnclipu_vx_w, 4, 4)
+RVVCALL(OPIVX2_RM, vnclipu_wx_b, NOP_UUU_B, H1, H2, vnclipu8)
+RVVCALL(OPIVX2_RM, vnclipu_wx_h, NOP_UUU_H, H2, H4, vnclipu16)
+RVVCALL(OPIVX2_RM, vnclipu_wx_w, NOP_UUU_W, H4, H8, vnclipu32)
+GEN_VEXT_VX_RM(vnclipu_wx_b, 1, 1)
+GEN_VEXT_VX_RM(vnclipu_wx_h, 2, 2)
+GEN_VEXT_VX_RM(vnclipu_wx_w, 4, 4)
/*
*** Vector Float Point Arithmetic Instructions
--
2.17.1
WARNING: multiple messages have this Message-ID (diff)
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>,
Alistair Francis <Alistair.Francis@wdc.com>,
Sagar Karandikar <sagark@eecs.berkeley.edu>,
Bastian Koppelmann <kbastian@mail.uni-paderborn.de>,
Richard Henderson <richard.henderson@linaro.org>,
LIU Zhiwei <zhiwei_liu@c-sky.com>
Subject: [PATCH v7 51/75] target/riscv: rvv-1.0: narrowing fixed-point clip instructions
Date: Fri, 26 Feb 2021 11:18:35 +0800 [thread overview]
Message-ID: <20210226031902.23656-52-frank.chang@sifive.com> (raw)
In-Reply-To: <20210226031902.23656-1-frank.chang@sifive.com>
From: Frank Chang <frank.chang@sifive.com>
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/riscv/helper.h | 24 ++++++------
target/riscv/insn32.decode | 12 +++---
target/riscv/insn_trans/trans_rvv.c.inc | 12 +++---
target/riscv/vector_helper.c | 52 ++++++++++++-------------
4 files changed, 50 insertions(+), 50 deletions(-)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 1e1e35bf800..2e4ed26f89c 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -766,18 +766,18 @@ DEF_HELPER_6(vssra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vssra_vx_d, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclip_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclip_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclip_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclipu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclip_vx_b, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclip_vx_h, void, ptr, ptr, tl, ptr, env, i32)
-DEF_HELPER_6(vnclip_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_wv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclip_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclip_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclipu_wx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_wx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_wx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_wx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vfadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vfadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 06e4e4f74b4..ac1bcab9627 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -491,12 +491,12 @@ vssrl_vi 101010 . ..... ..... 011 ..... 1010111 @r_vm
vssra_vv 101011 . ..... ..... 000 ..... 1010111 @r_vm
vssra_vx 101011 . ..... ..... 100 ..... 1010111 @r_vm
vssra_vi 101011 . ..... ..... 011 ..... 1010111 @r_vm
-vnclipu_vv 101110 . ..... ..... 000 ..... 1010111 @r_vm
-vnclipu_vx 101110 . ..... ..... 100 ..... 1010111 @r_vm
-vnclipu_vi 101110 . ..... ..... 011 ..... 1010111 @r_vm
-vnclip_vv 101111 . ..... ..... 000 ..... 1010111 @r_vm
-vnclip_vx 101111 . ..... ..... 100 ..... 1010111 @r_vm
-vnclip_vi 101111 . ..... ..... 011 ..... 1010111 @r_vm
+vnclipu_wv 101110 . ..... ..... 000 ..... 1010111 @r_vm
+vnclipu_wx 101110 . ..... ..... 100 ..... 1010111 @r_vm
+vnclipu_wi 101110 . ..... ..... 011 ..... 1010111 @r_vm
+vnclip_wv 101111 . ..... ..... 000 ..... 1010111 @r_vm
+vnclip_wx 101111 . ..... ..... 100 ..... 1010111 @r_vm
+vnclip_wi 101111 . ..... ..... 011 ..... 1010111 @r_vm
vfadd_vv 000000 . ..... ..... 001 ..... 1010111 @r_vm
vfadd_vf 000000 . ..... ..... 101 ..... 1010111 @r_vm
vfsub_vv 000010 . ..... ..... 001 ..... 1010111 @r_vm
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 26652f044f8..731c4bdd04b 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -2267,12 +2267,12 @@ GEN_OPIVI_TRANS(vssrl_vi, IMM_ZX, vssrl_vx, opivx_check)
GEN_OPIVI_TRANS(vssra_vi, IMM_SX, vssra_vx, opivx_check)
/* Vector Narrowing Fixed-Point Clip Instructions */
-GEN_OPIVV_NARROW_TRANS(vnclipu_vv)
-GEN_OPIVV_NARROW_TRANS(vnclip_vv)
-GEN_OPIVX_NARROW_TRANS(vnclipu_vx)
-GEN_OPIVX_NARROW_TRANS(vnclip_vx)
-GEN_OPIVI_NARROW_TRANS(vnclipu_vi, IMM_ZX, vnclipu_vx)
-GEN_OPIVI_NARROW_TRANS(vnclip_vi, IMM_ZX, vnclip_vx)
+GEN_OPIWV_NARROW_TRANS(vnclipu_wv)
+GEN_OPIWV_NARROW_TRANS(vnclip_wv)
+GEN_OPIWX_NARROW_TRANS(vnclipu_wx)
+GEN_OPIWX_NARROW_TRANS(vnclip_wx)
+GEN_OPIWI_NARROW_TRANS(vnclipu_wi, IMM_ZX, vnclipu_wx)
+GEN_OPIWI_NARROW_TRANS(vnclip_wi, IMM_ZX, vnclip_wx)
/*
*** Vector Float Point Arithmetic Instructions
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index df4f0b2d6a7..c5048882e91 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -3084,19 +3084,19 @@ vnclip32(CPURISCVState *env, int vxrm, int64_t a, int32_t b)
}
}
-RVVCALL(OPIVV2_RM, vnclip_vv_b, NOP_SSS_B, H1, H2, H1, vnclip8)
-RVVCALL(OPIVV2_RM, vnclip_vv_h, NOP_SSS_H, H2, H4, H2, vnclip16)
-RVVCALL(OPIVV2_RM, vnclip_vv_w, NOP_SSS_W, H4, H8, H4, vnclip32)
-GEN_VEXT_VV_RM(vnclip_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vnclip_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vnclip_vv_w, 4, 4)
-
-RVVCALL(OPIVX2_RM, vnclip_vx_b, NOP_SSS_B, H1, H2, vnclip8)
-RVVCALL(OPIVX2_RM, vnclip_vx_h, NOP_SSS_H, H2, H4, vnclip16)
-RVVCALL(OPIVX2_RM, vnclip_vx_w, NOP_SSS_W, H4, H8, vnclip32)
-GEN_VEXT_VX_RM(vnclip_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vnclip_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vnclip_vx_w, 4, 4)
+RVVCALL(OPIVV2_RM, vnclip_wv_b, NOP_SSS_B, H1, H2, H1, vnclip8)
+RVVCALL(OPIVV2_RM, vnclip_wv_h, NOP_SSS_H, H2, H4, H2, vnclip16)
+RVVCALL(OPIVV2_RM, vnclip_wv_w, NOP_SSS_W, H4, H8, H4, vnclip32)
+GEN_VEXT_VV_RM(vnclip_wv_b, 1, 1)
+GEN_VEXT_VV_RM(vnclip_wv_h, 2, 2)
+GEN_VEXT_VV_RM(vnclip_wv_w, 4, 4)
+
+RVVCALL(OPIVX2_RM, vnclip_wx_b, NOP_SSS_B, H1, H2, vnclip8)
+RVVCALL(OPIVX2_RM, vnclip_wx_h, NOP_SSS_H, H2, H4, vnclip16)
+RVVCALL(OPIVX2_RM, vnclip_wx_w, NOP_SSS_W, H4, H8, vnclip32)
+GEN_VEXT_VX_RM(vnclip_wx_b, 1, 1)
+GEN_VEXT_VX_RM(vnclip_wx_h, 2, 2)
+GEN_VEXT_VX_RM(vnclip_wx_w, 4, 4)
static inline uint8_t
vnclipu8(CPURISCVState *env, int vxrm, uint16_t a, uint8_t b)
@@ -3134,7 +3134,7 @@ static inline uint32_t
vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b)
{
uint8_t round, shift = b & 0x3f;
- int64_t res;
+ uint64_t res;
round = get_round(vxrm, a, shift);
res = (a >> shift) + round;
@@ -3146,19 +3146,19 @@ vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b)
}
}
-RVVCALL(OPIVV2_RM, vnclipu_vv_b, NOP_UUU_B, H1, H2, H1, vnclipu8)
-RVVCALL(OPIVV2_RM, vnclipu_vv_h, NOP_UUU_H, H2, H4, H2, vnclipu16)
-RVVCALL(OPIVV2_RM, vnclipu_vv_w, NOP_UUU_W, H4, H8, H4, vnclipu32)
-GEN_VEXT_VV_RM(vnclipu_vv_b, 1, 1)
-GEN_VEXT_VV_RM(vnclipu_vv_h, 2, 2)
-GEN_VEXT_VV_RM(vnclipu_vv_w, 4, 4)
+RVVCALL(OPIVV2_RM, vnclipu_wv_b, NOP_UUU_B, H1, H2, H1, vnclipu8)
+RVVCALL(OPIVV2_RM, vnclipu_wv_h, NOP_UUU_H, H2, H4, H2, vnclipu16)
+RVVCALL(OPIVV2_RM, vnclipu_wv_w, NOP_UUU_W, H4, H8, H4, vnclipu32)
+GEN_VEXT_VV_RM(vnclipu_wv_b, 1, 1)
+GEN_VEXT_VV_RM(vnclipu_wv_h, 2, 2)
+GEN_VEXT_VV_RM(vnclipu_wv_w, 4, 4)
-RVVCALL(OPIVX2_RM, vnclipu_vx_b, NOP_UUU_B, H1, H2, vnclipu8)
-RVVCALL(OPIVX2_RM, vnclipu_vx_h, NOP_UUU_H, H2, H4, vnclipu16)
-RVVCALL(OPIVX2_RM, vnclipu_vx_w, NOP_UUU_W, H4, H8, vnclipu32)
-GEN_VEXT_VX_RM(vnclipu_vx_b, 1, 1)
-GEN_VEXT_VX_RM(vnclipu_vx_h, 2, 2)
-GEN_VEXT_VX_RM(vnclipu_vx_w, 4, 4)
+RVVCALL(OPIVX2_RM, vnclipu_wx_b, NOP_UUU_B, H1, H2, vnclipu8)
+RVVCALL(OPIVX2_RM, vnclipu_wx_h, NOP_UUU_H, H2, H4, vnclipu16)
+RVVCALL(OPIVX2_RM, vnclipu_wx_w, NOP_UUU_W, H4, H8, vnclipu32)
+GEN_VEXT_VX_RM(vnclipu_wx_b, 1, 1)
+GEN_VEXT_VX_RM(vnclipu_wx_h, 2, 2)
+GEN_VEXT_VX_RM(vnclipu_wx_w, 4, 4)
/*
*** Vector Float Point Arithmetic Instructions
--
2.17.1
next prev parent reply other threads:[~2021-02-26 4:03 UTC|newest]
Thread overview: 151+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-26 3:17 [PATCH v7 00/75] support vector extension v1.0 frank.chang
2021-02-26 3:17 ` [PATCH v7 01/75] target/riscv: drop vector 0.7.1 and add 1.0 support frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 02/75] target/riscv: Use FIELD_EX32() to extract wd field frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 03/75] target/riscv: rvv-1.0: add mstatus VS field frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 04/75] target/riscv: rvv-1.0: add sstatus " frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 05/75] target/riscv: rvv-1.0: introduce writable misa.v field frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 06/75] target/riscv: rvv-1.0: add translation-time vector context status frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 07/75] target/riscv: rvv-1.0: remove rvv related codes from fcsr registers frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 08/75] target/riscv: rvv-1.0: add vcsr register frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 09/75] target/riscv: rvv-1.0: add vlenb register frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 10/75] target/riscv: rvv-1.0: check MSTATUS_VS when accessing vector csr registers frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 11/75] target/riscv: rvv-1.0: remove MLEN calculations frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 12/75] target/riscv: rvv-1.0: add fractional LMUL frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 13/75] target/riscv: rvv-1.0: add VMA and VTA frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 14/75] target/riscv: rvv-1.0: update check functions frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:17 ` [PATCH v7 15/75] target/riscv: introduce more imm value modes in translator functions frank.chang
2021-02-26 3:17 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 16/75] target/riscv: rvv:1.0: add translation-time nan-box helper function frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 17/75] target/riscv: rvv-1.0: configure instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 18/75] target/riscv: rvv-1.0: stride load and store instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 19/75] target/riscv: rvv-1.0: index " frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 20/75] target/riscv: rvv-1.0: fix address index overflow bug of indexed load/store insns frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 21/75] target/riscv: rvv-1.0: fault-only-first unit stride load frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 22/75] target/riscv: rvv-1.0: amo operations frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 23/75] target/riscv: rvv-1.0: load/store whole register instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 24/75] target/riscv: rvv-1.0: update vext_max_elems() for load/store insns frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 25/75] target/riscv: rvv-1.0: take fractional LMUL into vector max elements calculation frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 26/75] target/riscv: rvv-1.0: floating-point square-root instruction frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 27/75] target/riscv: rvv-1.0: floating-point classify instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 28/75] target/riscv: rvv-1.0: mask population count instruction frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 29/75] target/riscv: rvv-1.0: find-first-set mask bit instruction frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 30/75] target/riscv: rvv-1.0: set-X-first mask bit instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 31/75] target/riscv: rvv-1.0: iota instruction frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 32/75] target/riscv: rvv-1.0: element index instruction frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 33/75] target/riscv: rvv-1.0: allow load element with sign-extended frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 34/75] target/riscv: rvv-1.0: register gather instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 35/75] target/riscv: rvv-1.0: integer scalar move instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 36/75] target/riscv: rvv-1.0: floating-point move instruction frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 37/75] target/riscv: rvv-1.0: floating-point scalar move instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 38/75] target/riscv: rvv-1.0: whole register " frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 39/75] target/riscv: rvv-1.0: integer extension instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 40/75] target/riscv: rvv-1.0: single-width averaging add and subtract instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 41/75] target/riscv: rvv-1.0: single-width bit shift instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 42/75] target/riscv: rvv-1.0: integer add-with-carry/subtract-with-borrow frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 43/75] target/riscv: rvv-1.0: narrowing integer right shift instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 44/75] target/riscv: rvv-1.0: widening integer multiply-add instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 45/75] target/riscv: rvv-1.0: single-width saturating add and subtract instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 46/75] target/riscv: rvv-1.0: integer comparison instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 47/75] target/riscv: rvv-1.0: floating-point compare instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 48/75] target/riscv: rvv-1.0: mask-register logical instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 49/75] target/riscv: rvv-1.0: slide instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 50/75] target/riscv: rvv-1.0: floating-point " frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` frank.chang [this message]
2021-02-26 3:18 ` [PATCH v7 51/75] target/riscv: rvv-1.0: narrowing fixed-point clip instructions frank.chang
2021-02-26 3:18 ` [PATCH v7 52/75] target/riscv: rvv-1.0: single-width floating-point reduction frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 53/75] target/riscv: rvv-1.0: widening floating-point reduction instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 54/75] target/riscv: rvv-1.0: single-width scaling shift instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 55/75] target/riscv: rvv-1.0: remove widening saturating scaled multiply-add frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 56/75] target/riscv: rvv-1.0: remove vmford.vv and vmford.vf frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 57/75] target/riscv: rvv-1.0: remove integer extract instruction frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 58/75] target/riscv: rvv-1.0: floating-point min/max instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 59/75] target/riscv: introduce floating-point rounding mode enum frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 60/75] target/riscv: rvv-1.0: floating-point/integer type-convert instructions frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 61/75] target/riscv: rvv-1.0: widening floating-point/integer type-convert frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 62/75] target/riscv: add "set round to odd" rounding mode helper function frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 63/75] target/riscv: rvv-1.0: narrowing floating-point/integer type-convert frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 64/75] target/riscv: rvv-1.0: relax RV_VLEN_MAX to 1024-bits frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 65/75] target/riscv: rvv-1.0: implement vstart CSR frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 66/75] target/riscv: rvv-1.0: trigger illegal instruction exception if frm is not valid frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 67/75] target/riscv: rvv-1.0: set mstatus.SD bit when writing vector CSRs frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 68/75] target/riscv: gdb: support vector registers for rv64 & rv32 frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 69/75] target/riscv: rvv-1.0: floating-point reciprocal square-root estimate instruction frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 70/75] target/riscv: rvv-1.0: floating-point reciprocal " frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 71/75] target/riscv: set mstatus.SD bit when writing fp CSRs frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 72/75] target/riscv: rvv-1.0: rename r2_zimm to r2_zimm11 frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 73/75] target/riscv: rvv-1.0: add vsetivli instruction frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 74/75] target/riscv: rvv-1.0: add evl parameter to vext_ldst_us() frank.chang
2021-02-26 3:18 ` frank.chang
2021-02-26 3:18 ` [PATCH v7 75/75] target/riscv: rvv-1.0: add vector unit-stride mask load/store insns frank.chang
2021-02-26 3:18 ` frank.chang
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=20210226031902.23656-52-frank.chang@sifive.com \
--to=frank.chang@sifive.com \
--cc=Alistair.Francis@wdc.com \
--cc=kbastian@mail.uni-paderborn.de \
--cc=palmer@dabbelt.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-riscv@nongnu.org \
--cc=richard.henderson@linaro.org \
--cc=sagark@eecs.berkeley.edu \
--cc=zhiwei_liu@c-sky.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.