[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH 23/65] target/riscv: Add integer min/max instructions for XTheadV
From: |
Huang Tao |
Subject: |
[PATCH 23/65] target/riscv: Add integer min/max instructions for XTheadVector |
Date: |
Fri, 12 Apr 2024 15:36:53 +0800 |
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
- [PATCH 13/65] target/riscv: Add indexed store instructions for XTheadVector, (continued)
- [PATCH 13/65] target/riscv: Add indexed store instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 14/65] target/riscv: Add unit-stride fault-only-first instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 15/65] target/riscv: Add vector amo operations for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 16/65] target/riscv: Add single-width integer add and subtract instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 17/65] target/riscv: Add widening integer add/subtract instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 18/65] target/riscv: Add integer add-with-carry/sub-with-borrow instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 19/65] target/riscv: Add bitwise logical instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 20/65] target/riscv: Add single-width bit shift instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 21/65] target/riscv: Add narrowing integer right shift instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 22/65] target/riscv: Add integer compare instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 23/65] target/riscv: Add integer min/max instructions for XTheadVector,
Huang Tao <=
- [PATCH 24/65] target/riscv: Add single-width integer multiply instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 25/65] target/riscv: Add integer divide instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 26/65] target/riscv: Add widening integer multiply instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 27/65] target/riscv: Add single-width integer multiply-add instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 28/65] target/riscv: Add widening integer multiply-add instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 29/65] target/riscv: Add integer merge and move instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 30/65] target/riscv: Add single-width saturating add and sub instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 31/65] target/riscv: Add single-width average add and sub instructions for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 32/65] target/riscv: Add single-width fractional mul with rounding and saturation for XTheadVector, Huang Tao, 2024/04/12
- [PATCH 33/65] target/riscv: Add widening saturating scaled multiply-add instructions for XTheadVector, Huang Tao, 2024/04/12