[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PULL v2 20/64] target/riscv: vector integer min/max instructions
|
From: |
Alistair Francis |
|
Subject: |
[PULL v2 20/64] target/riscv: vector integer min/max instructions |
|
Date: |
Thu, 2 Jul 2020 09:23:10 -0700 |
From: LIU Zhiwei <zhiwei_liu@c-sky.com>
Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20200701152549.1218-18-zhiwei_liu@c-sky.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
target/riscv/helper.h | 33 ++++++++++++
target/riscv/insn32.decode | 8 +++
target/riscv/insn_trans/trans_rvv.inc.c | 10 ++++
target/riscv/vector_helper.c | 71 +++++++++++++++++++++++++
4 files changed, 122 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 2bcb6c7889..9c576e1220 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -502,3 +502,36 @@ DEF_HELPER_6(vmsgt_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vmsgt_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vmsgt_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vmsgt_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vminu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 5d022ff414..3d8986c74d 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -357,6 +357,14 @@ vmsgtu_vx 011110 . ..... ..... 100 ..... 1010111
@r_vm
vmsgtu_vi 011110 . ..... ..... 011 ..... 1010111 @r_vm
vmsgt_vx 011111 . ..... ..... 100 ..... 1010111 @r_vm
vmsgt_vi 011111 . ..... ..... 011 ..... 1010111 @r_vm
+vminu_vv 000100 . ..... ..... 000 ..... 1010111 @r_vm
+vminu_vx 000100 . ..... ..... 100 ..... 1010111 @r_vm
+vmin_vv 000101 . ..... ..... 000 ..... 1010111 @r_vm
+vmin_vx 000101 . ..... ..... 100 ..... 1010111 @r_vm
+vmaxu_vv 000110 . ..... ..... 000 ..... 1010111 @r_vm
+vmaxu_vx 000110 . ..... ..... 100 ..... 1010111 @r_vm
+vmax_vv 000111 . ..... ..... 000 ..... 1010111 @r_vm
+vmax_vx 000111 . ..... ..... 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 7d7e3d4cd8..861fd3bf1a 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1561,3 +1561,13 @@ GEN_OPIVI_TRANS(vmsleu_vi, 1, vmsleu_vx, opivx_cmp_check)
GEN_OPIVI_TRANS(vmsle_vi, 0, vmsle_vx, opivx_cmp_check)
GEN_OPIVI_TRANS(vmsgtu_vi, 1, vmsgtu_vx, opivx_cmp_check)
GEN_OPIVI_TRANS(vmsgt_vi, 0, vmsgt_vx, opivx_cmp_check)
+
+/* Vector Integer Min/Max Instructions */
+GEN_OPIVV_GVEC_TRANS(vminu_vv, umin)
+GEN_OPIVV_GVEC_TRANS(vmin_vv, smin)
+GEN_OPIVV_GVEC_TRANS(vmaxu_vv, umax)
+GEN_OPIVV_GVEC_TRANS(vmax_vv, smax)
+GEN_OPIVX_TRANS(vminu_vx, opivx_check)
+GEN_OPIVX_TRANS(vmin_vx, opivx_check)
+GEN_OPIVX_TRANS(vmaxu_vx, opivx_check)
+GEN_OPIVX_TRANS(vmax_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 71f27146b3..b1ff767209 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -855,6 +855,10 @@ GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w,
clearl)
#define OP_SSS_H int16_t, int16_t, int16_t, int16_t, int16_t
#define OP_SSS_W int32_t, int32_t, int32_t, int32_t, int32_t
#define OP_SSS_D int64_t, int64_t, int64_t, int64_t, int64_t
+#define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t
+#define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t
+#define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
+#define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t
/* operation of two vector elements */
typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
@@ -1532,3 +1536,70 @@ GEN_VEXT_CMP_VX(vmsgt_vx_b, int8_t, H1, DO_MSGT)
GEN_VEXT_CMP_VX(vmsgt_vx_h, int16_t, H2, DO_MSGT)
GEN_VEXT_CMP_VX(vmsgt_vx_w, int32_t, H4, DO_MSGT)
GEN_VEXT_CMP_VX(vmsgt_vx_d, int64_t, H8, DO_MSGT)
+
+/* Vector Integer Min/Max Instructions */
+RVVCALL(OPIVV2, vminu_vv_b, OP_UUU_B, H1, H1, H1, DO_MIN)
+RVVCALL(OPIVV2, vminu_vv_h, OP_UUU_H, H2, H2, H2, DO_MIN)
+RVVCALL(OPIVV2, vminu_vv_w, OP_UUU_W, H4, H4, H4, DO_MIN)
+RVVCALL(OPIVV2, vminu_vv_d, OP_UUU_D, H8, H8, H8, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_b, OP_SSS_B, H1, H1, H1, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_h, OP_SSS_H, H2, H2, H2, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_w, OP_SSS_W, H4, H4, H4, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_d, OP_SSS_D, H8, H8, H8, DO_MIN)
+RVVCALL(OPIVV2, vmaxu_vv_b, OP_UUU_B, H1, H1, H1, DO_MAX)
+RVVCALL(OPIVV2, vmaxu_vv_h, OP_UUU_H, H2, H2, H2, DO_MAX)
+RVVCALL(OPIVV2, vmaxu_vv_w, OP_UUU_W, H4, H4, H4, DO_MAX)
+RVVCALL(OPIVV2, vmaxu_vv_d, OP_UUU_D, H8, H8, H8, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_b, OP_SSS_B, H1, H1, H1, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_h, OP_SSS_H, H2, H2, H2, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_w, OP_SSS_W, H4, H4, H4, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_d, OP_SSS_D, H8, H8, H8, DO_MAX)
+GEN_VEXT_VV(vminu_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vminu_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vminu_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vminu_vv_d, 8, 8, clearq)
+GEN_VEXT_VV(vmin_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vmin_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vmin_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vmin_vv_d, 8, 8, clearq)
+GEN_VEXT_VV(vmaxu_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vmaxu_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vmaxu_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vmaxu_vv_d, 8, 8, clearq)
+GEN_VEXT_VV(vmax_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vmax_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vmax_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vmax_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2, vminu_vx_b, OP_UUU_B, H1, H1, DO_MIN)
+RVVCALL(OPIVX2, vminu_vx_h, OP_UUU_H, H2, H2, DO_MIN)
+RVVCALL(OPIVX2, vminu_vx_w, OP_UUU_W, H4, H4, DO_MIN)
+RVVCALL(OPIVX2, vminu_vx_d, OP_UUU_D, H8, H8, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_b, OP_SSS_B, H1, H1, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_h, OP_SSS_H, H2, H2, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_w, OP_SSS_W, H4, H4, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_d, OP_SSS_D, H8, H8, DO_MIN)
+RVVCALL(OPIVX2, vmaxu_vx_b, OP_UUU_B, H1, H1, DO_MAX)
+RVVCALL(OPIVX2, vmaxu_vx_h, OP_UUU_H, H2, H2, DO_MAX)
+RVVCALL(OPIVX2, vmaxu_vx_w, OP_UUU_W, H4, H4, DO_MAX)
+RVVCALL(OPIVX2, vmaxu_vx_d, OP_UUU_D, H8, H8, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_b, OP_SSS_B, H1, H1, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_h, OP_SSS_H, H2, H2, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_w, OP_SSS_W, H4, H4, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_d, OP_SSS_D, H8, H8, DO_MAX)
+GEN_VEXT_VX(vminu_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vminu_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vminu_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vminu_vx_d, 8, 8, clearq)
+GEN_VEXT_VX(vmin_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vmin_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vmin_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vmin_vx_d, 8, 8, clearq)
+GEN_VEXT_VX(vmaxu_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vmaxu_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vmaxu_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vmaxu_vx_d, 8, 8, clearq)
+GEN_VEXT_VX(vmax_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vmax_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vmax_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vmax_vx_d, 8, 8, clearq)
--
2.27.0
- Re: [PULL v2 12/64] target/riscv: add vector amo operations, (continued)
[PULL v2 09/64] target/riscv: add vector stride load and store instructions, Alistair Francis, 2020/07/02
[PULL v2 17/64] target/riscv: vector single-width bit shift instructions, Alistair Francis, 2020/07/02
[PULL v2 13/64] target/riscv: vector single-width integer add and subtract, Alistair Francis, 2020/07/02
[PULL v2 15/64] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions, Alistair Francis, 2020/07/02
[PULL v2 19/64] target/riscv: vector integer comparison instructions, Alistair Francis, 2020/07/02
[PULL v2 18/64] target/riscv: vector narrowing integer right shift instructions, Alistair Francis, 2020/07/02
[PULL v2 11/64] target/riscv: add fault-only-first unit stride load, Alistair Francis, 2020/07/02
[PULL v2 20/64] target/riscv: vector integer min/max instructions,
Alistair Francis <=
[PULL v2 21/64] target/riscv: vector single-width integer multiply instructions, Alistair Francis, 2020/07/02
[PULL v2 29/64] target/riscv: vector single-width fractional multiply with rounding and saturation, Alistair Francis, 2020/07/02
[PULL v2 24/64] target/riscv: vector single-width integer multiply-add instructions, Alistair Francis, 2020/07/02
[PULL v2 16/64] target/riscv: vector bitwise logical instructions, Alistair Francis, 2020/07/02
[PULL v2 26/64] target/riscv: vector integer merge and move instructions, Alistair Francis, 2020/07/02
[PULL v2 25/64] target/riscv: vector widening integer multiply-add instructions, Alistair Francis, 2020/07/02
[PULL v2 27/64] target/riscv: vector single-width saturating add and subtract, Alistair Francis, 2020/07/02
[PULL v2 28/64] target/riscv: vector single-width averaging add and subtract, Alistair Francis, 2020/07/02
[PULL v2 23/64] target/riscv: vector widening integer multiply instructions, Alistair Francis, 2020/07/02
[PULL v2 33/64] target/riscv: vector single-width floating-point add/subtract instructions, Alistair Francis, 2020/07/02