From: Huang Tao <eric.huang@linux.alibaba.com>
To: qemu-devel@nongnu.org
Cc: qemu-riscv@nongnu.org, zhiwei_liu@linux.alibaba.com,
dbarboza@ventanamicro.com, liwei1518@gmail.com,
bin.meng@windriver.com, alistair.francis@wdc.com,
palmer@dabbelt.com, Huang Tao <eric.huang@linux.alibaba.com>
Subject: [PATCH 23/65] target/riscv: Add integer min/max instructions for XTheadVector
Date: Fri, 12 Apr 2024 15:36:53 +0800 [thread overview]
Message-ID: <20240412073735.76413-24-eric.huang@linux.alibaba.com> (raw)
In-Reply-To: <20240412073735.76413-1-eric.huang@linux.alibaba.com>
The instructions have the same function as RVV1.0. Overall there are only
general differences between XTheadVector and RVV1.0.
Signed-off-by: Huang Tao <eric.huang@linux.alibaba.com>
---
target/riscv/helper.h | 33 +++++++++
.../riscv/insn_trans/trans_xtheadvector.c.inc | 18 ++---
target/riscv/xtheadvector_helper.c | 67 +++++++++++++++++++
3 files changed, 110 insertions(+), 8 deletions(-)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 8f2dec158b..f3e4ab0f1f 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1695,3 +1695,36 @@ DEF_HELPER_6(th_vmsgt_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(th_vmsgt_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(th_vmsgt_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(th_vmsgt_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(th_vminu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vminu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vminu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vminu_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmin_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmin_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmin_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmin_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmaxu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmaxu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmaxu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmaxu_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmax_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmax_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmax_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vmax_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(th_vminu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vminu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vminu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vminu_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmin_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmin_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmin_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmin_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmaxu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmaxu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmaxu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmaxu_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmax_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmax_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmax_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(th_vmax_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn_trans/trans_xtheadvector.c.inc b/target/riscv/insn_trans/trans_xtheadvector.c.inc
index 049d9da0a5..f19a771b61 100644
--- a/target/riscv/insn_trans/trans_xtheadvector.c.inc
+++ b/target/riscv/insn_trans/trans_xtheadvector.c.inc
@@ -1519,20 +1519,22 @@ GEN_OPIVI_TRANS_TH(th_vmsle_vi, IMM_SX, th_vmsle_vx, opivx_cmp_check_th)
GEN_OPIVI_TRANS_TH(th_vmsgtu_vi, IMM_ZX, th_vmsgtu_vx, opivx_cmp_check_th)
GEN_OPIVI_TRANS_TH(th_vmsgt_vi, IMM_SX, th_vmsgt_vx, opivx_cmp_check_th)
+/* Vector Integer Min/Max Instructions */
+GEN_OPIVV_GVEC_TRANS_TH(th_vminu_vv, umin)
+GEN_OPIVV_GVEC_TRANS_TH(th_vmin_vv, smin)
+GEN_OPIVV_GVEC_TRANS_TH(th_vmaxu_vv, umax)
+GEN_OPIVV_GVEC_TRANS_TH(th_vmax_vv, smax)
+GEN_OPIVX_TRANS_TH(th_vminu_vx, opivx_check_th)
+GEN_OPIVX_TRANS_TH(th_vmin_vx, opivx_check_th)
+GEN_OPIVX_TRANS_TH(th_vmaxu_vx, opivx_check_th)
+GEN_OPIVX_TRANS_TH(th_vmax_vx, opivx_check_th)
+
#define TH_TRANS_STUB(NAME) \
static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \
{ \
return require_xtheadvector(s); \
}
-TH_TRANS_STUB(th_vminu_vv)
-TH_TRANS_STUB(th_vminu_vx)
-TH_TRANS_STUB(th_vmin_vv)
-TH_TRANS_STUB(th_vmin_vx)
-TH_TRANS_STUB(th_vmaxu_vv)
-TH_TRANS_STUB(th_vmaxu_vx)
-TH_TRANS_STUB(th_vmax_vv)
-TH_TRANS_STUB(th_vmax_vx)
TH_TRANS_STUB(th_vmul_vv)
TH_TRANS_STUB(th_vmul_vx)
TH_TRANS_STUB(th_vmulh_vv)
diff --git a/target/riscv/xtheadvector_helper.c b/target/riscv/xtheadvector_helper.c
index 827650b325..da869e1069 100644
--- a/target/riscv/xtheadvector_helper.c
+++ b/target/riscv/xtheadvector_helper.c
@@ -1542,3 +1542,70 @@ GEN_TH_CMP_VX(th_vmsgt_vx_b, int8_t, H1, TH_MSGT)
GEN_TH_CMP_VX(th_vmsgt_vx_h, int16_t, H2, TH_MSGT)
GEN_TH_CMP_VX(th_vmsgt_vx_w, int32_t, H4, TH_MSGT)
GEN_TH_CMP_VX(th_vmsgt_vx_d, int64_t, H8, TH_MSGT)
+
+/* Vector Integer Min/Max Instructions */
+THCALL(TH_OPIVV2, th_vminu_vv_b, OP_UUU_B, H1, H1, H1, TH_MIN)
+THCALL(TH_OPIVV2, th_vminu_vv_h, OP_UUU_H, H2, H2, H2, TH_MIN)
+THCALL(TH_OPIVV2, th_vminu_vv_w, OP_UUU_W, H4, H4, H4, TH_MIN)
+THCALL(TH_OPIVV2, th_vminu_vv_d, OP_UUU_D, H8, H8, H8, TH_MIN)
+THCALL(TH_OPIVV2, th_vmin_vv_b, OP_SSS_B, H1, H1, H1, TH_MIN)
+THCALL(TH_OPIVV2, th_vmin_vv_h, OP_SSS_H, H2, H2, H2, TH_MIN)
+THCALL(TH_OPIVV2, th_vmin_vv_w, OP_SSS_W, H4, H4, H4, TH_MIN)
+THCALL(TH_OPIVV2, th_vmin_vv_d, OP_SSS_D, H8, H8, H8, TH_MIN)
+THCALL(TH_OPIVV2, th_vmaxu_vv_b, OP_UUU_B, H1, H1, H1, TH_MAX)
+THCALL(TH_OPIVV2, th_vmaxu_vv_h, OP_UUU_H, H2, H2, H2, TH_MAX)
+THCALL(TH_OPIVV2, th_vmaxu_vv_w, OP_UUU_W, H4, H4, H4, TH_MAX)
+THCALL(TH_OPIVV2, th_vmaxu_vv_d, OP_UUU_D, H8, H8, H8, TH_MAX)
+THCALL(TH_OPIVV2, th_vmax_vv_b, OP_SSS_B, H1, H1, H1, TH_MAX)
+THCALL(TH_OPIVV2, th_vmax_vv_h, OP_SSS_H, H2, H2, H2, TH_MAX)
+THCALL(TH_OPIVV2, th_vmax_vv_w, OP_SSS_W, H4, H4, H4, TH_MAX)
+THCALL(TH_OPIVV2, th_vmax_vv_d, OP_SSS_D, H8, H8, H8, TH_MAX)
+GEN_TH_VV(th_vminu_vv_b, 1, 1, clearb_th)
+GEN_TH_VV(th_vminu_vv_h, 2, 2, clearh_th)
+GEN_TH_VV(th_vminu_vv_w, 4, 4, clearl_th)
+GEN_TH_VV(th_vminu_vv_d, 8, 8, clearq_th)
+GEN_TH_VV(th_vmin_vv_b, 1, 1, clearb_th)
+GEN_TH_VV(th_vmin_vv_h, 2, 2, clearh_th)
+GEN_TH_VV(th_vmin_vv_w, 4, 4, clearl_th)
+GEN_TH_VV(th_vmin_vv_d, 8, 8, clearq_th)
+GEN_TH_VV(th_vmaxu_vv_b, 1, 1, clearb_th)
+GEN_TH_VV(th_vmaxu_vv_h, 2, 2, clearh_th)
+GEN_TH_VV(th_vmaxu_vv_w, 4, 4, clearl_th)
+GEN_TH_VV(th_vmaxu_vv_d, 8, 8, clearq_th)
+GEN_TH_VV(th_vmax_vv_b, 1, 1, clearb_th)
+GEN_TH_VV(th_vmax_vv_h, 2, 2, clearh_th)
+GEN_TH_VV(th_vmax_vv_w, 4, 4, clearl_th)
+GEN_TH_VV(th_vmax_vv_d, 8, 8, clearq_th)
+
+THCALL(TH_OPIVX2, th_vminu_vx_b, OP_UUU_B, H1, H1, TH_MIN)
+THCALL(TH_OPIVX2, th_vminu_vx_h, OP_UUU_H, H2, H2, TH_MIN)
+THCALL(TH_OPIVX2, th_vminu_vx_w, OP_UUU_W, H4, H4, TH_MIN)
+THCALL(TH_OPIVX2, th_vminu_vx_d, OP_UUU_D, H8, H8, TH_MIN)
+THCALL(TH_OPIVX2, th_vmin_vx_b, OP_SSS_B, H1, H1, TH_MIN)
+THCALL(TH_OPIVX2, th_vmin_vx_h, OP_SSS_H, H2, H2, TH_MIN)
+THCALL(TH_OPIVX2, th_vmin_vx_w, OP_SSS_W, H4, H4, TH_MIN)
+THCALL(TH_OPIVX2, th_vmin_vx_d, OP_SSS_D, H8, H8, TH_MIN)
+THCALL(TH_OPIVX2, th_vmaxu_vx_b, OP_UUU_B, H1, H1, TH_MAX)
+THCALL(TH_OPIVX2, th_vmaxu_vx_h, OP_UUU_H, H2, H2, TH_MAX)
+THCALL(TH_OPIVX2, th_vmaxu_vx_w, OP_UUU_W, H4, H4, TH_MAX)
+THCALL(TH_OPIVX2, th_vmaxu_vx_d, OP_UUU_D, H8, H8, TH_MAX)
+THCALL(TH_OPIVX2, th_vmax_vx_b, OP_SSS_B, H1, H1, TH_MAX)
+THCALL(TH_OPIVX2, th_vmax_vx_h, OP_SSS_H, H2, H2, TH_MAX)
+THCALL(TH_OPIVX2, th_vmax_vx_w, OP_SSS_W, H4, H4, TH_MAX)
+THCALL(TH_OPIVX2, th_vmax_vx_d, OP_SSS_D, H8, H8, TH_MAX)
+GEN_TH_VX(th_vminu_vx_b, 1, 1, clearb_th)
+GEN_TH_VX(th_vminu_vx_h, 2, 2, clearh_th)
+GEN_TH_VX(th_vminu_vx_w, 4, 4, clearl_th)
+GEN_TH_VX(th_vminu_vx_d, 8, 8, clearq_th)
+GEN_TH_VX(th_vmin_vx_b, 1, 1, clearb_th)
+GEN_TH_VX(th_vmin_vx_h, 2, 2, clearh_th)
+GEN_TH_VX(th_vmin_vx_w, 4, 4, clearl_th)
+GEN_TH_VX(th_vmin_vx_d, 8, 8, clearq_th)
+GEN_TH_VX(th_vmaxu_vx_b, 1, 1, clearb_th)
+GEN_TH_VX(th_vmaxu_vx_h, 2, 2, clearh_th)
+GEN_TH_VX(th_vmaxu_vx_w, 4, 4, clearl_th)
+GEN_TH_VX(th_vmaxu_vx_d, 8, 8, clearq_th)
+GEN_TH_VX(th_vmax_vx_b, 1, 1, clearb_th)
+GEN_TH_VX(th_vmax_vx_h, 2, 2, clearh_th)
+GEN_TH_VX(th_vmax_vx_w, 4, 4, clearl_th)
+GEN_TH_VX(th_vmax_vx_d, 8, 8, clearq_th)
--
2.44.0
next prev parent reply other threads:[~2024-04-12 8:25 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-12 7:36 [PATCH 00/65]target/riscv: Support XTheadVector extension Huang Tao
2024-04-12 7:36 ` [PATCH 01/65] riscv: thead: Add th.sxstatus CSR emulation Huang Tao
2024-04-12 7:36 ` [PATCH 02/65] target/riscv: Reuse th_csr.c to add user-mode csrs Huang Tao
2024-04-12 7:36 ` [PATCH 03/65] target/riscv: Add properties for XTheadVector extension Huang Tao
2024-04-12 7:36 ` [PATCH 04/65] target/riscv: Override some csr ops for XTheadVector Huang Tao
2024-04-12 7:36 ` [PATCH 05/65] target/riscv: Add mlen in DisasContext Huang Tao
2024-04-12 7:36 ` [PATCH 06/65] target/riscv: Implement insns decode rules for XTheadVector Huang Tao
2024-04-12 7:36 ` [PATCH 07/65] target/riscv: implement th.vsetvl{i} " Huang Tao
2024-04-12 7:36 ` [PATCH 08/65] target/riscv: Add strided load instructions " Huang Tao
2024-04-12 7:36 ` [PATCH 09/65] target/riscv: Add strided store " Huang Tao
2024-04-12 7:36 ` [PATCH 10/65] target/riscv: Add unit-stride load " Huang Tao
2024-04-12 7:36 ` [PATCH 11/65] target/riscv: Add unit-stride store " Huang Tao
2024-04-12 7:36 ` [PATCH 12/65] target/riscv: Add indexed load " Huang Tao
2024-04-12 7:36 ` [PATCH 13/65] target/riscv: Add indexed store " Huang Tao
2024-04-12 7:36 ` [PATCH 14/65] target/riscv: Add unit-stride fault-only-first " Huang Tao
2024-04-12 7:36 ` [PATCH 15/65] target/riscv: Add vector amo operations " Huang Tao
2024-04-12 7:36 ` [PATCH 16/65] target/riscv: Add single-width integer add and subtract instructions " Huang Tao
2024-04-12 7:36 ` [PATCH 17/65] target/riscv: Add widening integer add/subtract " Huang Tao
2024-04-12 7:36 ` [PATCH 18/65] target/riscv: Add integer add-with-carry/sub-with-borrow " Huang Tao
2024-04-12 7:36 ` [PATCH 19/65] target/riscv: Add bitwise logical " Huang Tao
2024-04-12 7:36 ` [PATCH 20/65] target/riscv: Add single-width bit shift " Huang Tao
2024-04-12 7:36 ` [PATCH 21/65] target/riscv: Add narrowing integer right " Huang Tao
2024-04-12 7:36 ` [PATCH 22/65] target/riscv: Add integer compare " Huang Tao
2024-04-12 7:36 ` Huang Tao [this message]
2024-04-12 7:36 ` [PATCH 24/65] target/riscv: Add single-width integer multiply " Huang Tao
2024-04-12 7:36 ` [PATCH 25/65] target/riscv: Add integer divide " Huang Tao
2024-04-12 7:36 ` [PATCH 26/65] target/riscv: Add widening integer multiply " Huang Tao
2024-04-12 7:36 ` [PATCH 27/65] target/riscv: Add single-width integer multiply-add " Huang Tao
2024-04-12 7:36 ` [PATCH 28/65] target/riscv: Add widening " Huang Tao
2024-04-12 7:36 ` [PATCH 29/65] target/riscv: Add integer merge and move " Huang Tao
2024-04-12 7:37 ` [PATCH 30/65] target/riscv: Add single-width saturating add and sub " Huang Tao
2024-04-12 7:37 ` [PATCH 31/65] target/riscv: Add single-width average " Huang Tao
2024-04-12 7:37 ` [PATCH 32/65] target/riscv: Add single-width fractional mul with rounding and saturation " Huang Tao
2024-04-12 7:37 ` [PATCH 33/65] target/riscv: Add widening saturating scaled multiply-add instructions " Huang Tao
2024-04-12 7:37 ` [PATCH 34/65] target/riscv: Add single-width scaling shift " Huang Tao
2024-04-12 7:37 ` [PATCH 35/65] target/riscv: Add narrowing fixed-point clip " Huang Tao
2024-04-12 7:37 ` [PATCH 36/65] target/riscv: Add single-width floating-point add/sub " Huang Tao
2024-04-12 7:37 ` [PATCH 37/65] target/riscv: Add widening " Huang Tao
2024-04-12 7:37 ` [PATCH 38/65] target/riscv: Add single-width floating-point multiply/divide " Huang Tao
2024-04-12 7:37 ` [PATCH 39/65] target/riscv: Add widening floating-point multiply " Huang Tao
2024-04-12 7:37 ` [PATCH 40/65] target/riscv: Add single-width floating-point fused multiply-add " Huang Tao
2024-04-12 7:37 ` [PATCH 41/65] target/riscv: Add widening floating-point fused mul-add " Huang Tao
2024-04-12 7:37 ` [PATCH 42/65] target/riscv: Add floating-pointing square-root " Huang Tao
2024-04-12 7:37 ` [PATCH 43/65] target/riscv: Add floating-point MIN/MAX " Huang Tao
2024-04-12 7:37 ` [PATCH 44/65] target/riscv: Add floating-point sign-injection " Huang Tao
2024-04-12 7:37 ` [PATCH 45/65] target/riscv: Add floating-point compare " Huang Tao
2024-04-12 7:37 ` [PATCH 46/65] target/riscv: Add floating-point classify and merge " Huang Tao
2024-04-12 7:37 ` [PATCH 47/65] target/riscv: Add single-width floating-point/integer type-convert " Huang Tao
2024-04-12 7:37 ` [PATCH 48/65] target/riscv: Add widening " Huang Tao
2024-04-12 7:37 ` [PATCH 49/65] target/riscv: Add narrowing " Huang Tao
2024-04-12 7:37 ` [PATCH 50/65] target/riscv: Add single-width integer reduction " Huang Tao
2024-04-12 7:37 ` [PATCH 51/65] target/riscv: Add widening " Huang Tao
2024-04-12 7:37 ` [PATCH 52/65] target/riscv: Add single-width floating-point " Huang Tao
2024-04-12 7:37 ` [PATCH 53/65] target/riscv: Add widening " Huang Tao
2024-04-12 7:37 ` [PATCH 54/65] target/riscv: Add mask-register logical " Huang Tao
2024-04-12 7:37 ` [PATCH 55/65] target/riscv: Add vector mask population count vmpopc " Huang Tao
2024-04-12 7:37 ` [PATCH 56/65] target/riscv: Add th.vmfirst.m " Huang Tao
2024-04-12 7:37 ` [PATCH 57/65] target/riscv: Add set-X-first mask bit instructrions " Huang Tao
2024-04-12 7:37 ` [PATCH 58/65] target/riscv: Add vector iota instruction " Huang Tao
2024-04-12 7:37 ` [PATCH 59/65] target/riscv: Add vector element index " Huang Tao
2024-04-12 7:37 ` [PATCH 60/65] target/riscv: Add integer extract and scalar move instructions " Huang Tao
2024-04-12 7:37 ` [PATCH 61/65] target/riscv: Add floating-point " Huang Tao
2024-04-12 7:37 ` [PATCH 62/65] target/riscv: Add vector slide " Huang Tao
2024-04-12 7:37 ` [PATCH 63/65] target/riscv: Add vector register gather " Huang Tao
2024-04-12 7:37 ` [PATCH 64/65] target/riscv: Add vector compress instruction " Huang Tao
2024-04-12 7:37 ` [PATCH 65/65] target/riscv: Enable XTheadVector extension for c906 Huang Tao
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=20240412073735.76413-24-eric.huang@linux.alibaba.com \
--to=eric.huang@linux.alibaba.com \
--cc=alistair.francis@wdc.com \
--cc=bin.meng@windriver.com \
--cc=dbarboza@ventanamicro.com \
--cc=liwei1518@gmail.com \
--cc=palmer@dabbelt.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-riscv@nongnu.org \
--cc=zhiwei_liu@linux.alibaba.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).