[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PULL 14/39] tcg/loongarch64: Lower vector min max ops
From: |
Richard Henderson |
Subject: |
[PULL 14/39] tcg/loongarch64: Lower vector min max ops |
Date: |
Fri, 15 Sep 2023 20:29:46 -0700 |
From: Jiajie Chen <c@jia.je>
Lower the following ops:
- smin_vec
- smax_vec
- umin_vec
- umax_vec
Signed-off-by: Jiajie Chen <c@jia.je>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230908022302.180442-10-c@jia.je>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
tcg/loongarch64/tcg-target.h | 2 +-
tcg/loongarch64/tcg-target.c.inc | 32 ++++++++++++++++++++++++++++++++
2 files changed, 33 insertions(+), 1 deletion(-)
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 2c2266ed31..ec725aaeaa 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -193,7 +193,7 @@ extern bool use_lsx_instructions;
#define TCG_TARGET_HAS_rots_vec 0
#define TCG_TARGET_HAS_rotv_vec 0
#define TCG_TARGET_HAS_sat_vec 0
-#define TCG_TARGET_HAS_minmax_vec 0
+#define TCG_TARGET_HAS_minmax_vec 1
#define TCG_TARGET_HAS_bitsel_vec 0
#define TCG_TARGET_HAS_cmpsel_vec 0
diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 0814f62905..bdf22d8807 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1701,6 +1701,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
static const LoongArchInsn mul_vec_insn[4] = {
OPC_VMUL_B, OPC_VMUL_H, OPC_VMUL_W, OPC_VMUL_D
};
+ static const LoongArchInsn smin_vec_insn[4] = {
+ OPC_VMIN_B, OPC_VMIN_H, OPC_VMIN_W, OPC_VMIN_D
+ };
+ static const LoongArchInsn umin_vec_insn[4] = {
+ OPC_VMIN_BU, OPC_VMIN_HU, OPC_VMIN_WU, OPC_VMIN_DU
+ };
+ static const LoongArchInsn smax_vec_insn[4] = {
+ OPC_VMAX_B, OPC_VMAX_H, OPC_VMAX_W, OPC_VMAX_D
+ };
+ static const LoongArchInsn umax_vec_insn[4] = {
+ OPC_VMAX_BU, OPC_VMAX_HU, OPC_VMAX_WU, OPC_VMAX_DU
+ };
a0 = args[0];
a1 = args[1];
@@ -1805,6 +1817,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
case INDEX_op_mul_vec:
tcg_out32(s, encode_vdvjvk_insn(mul_vec_insn[vece], a0, a1, a2));
break;
+ case INDEX_op_smin_vec:
+ tcg_out32(s, encode_vdvjvk_insn(smin_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_smax_vec:
+ tcg_out32(s, encode_vdvjvk_insn(smax_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_umin_vec:
+ tcg_out32(s, encode_vdvjvk_insn(umin_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_umax_vec:
+ tcg_out32(s, encode_vdvjvk_insn(umax_vec_insn[vece], a0, a1, a2));
+ break;
case INDEX_op_dupm_vec:
tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
break;
@@ -1832,6 +1856,10 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type,
unsigned vece)
case INDEX_op_not_vec:
case INDEX_op_neg_vec:
case INDEX_op_mul_vec:
+ case INDEX_op_smin_vec:
+ case INDEX_op_smax_vec:
+ case INDEX_op_umin_vec:
+ case INDEX_op_umax_vec:
return 1;
default:
return 0;
@@ -2007,6 +2035,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode
op)
case INDEX_op_xor_vec:
case INDEX_op_nor_vec:
case INDEX_op_mul_vec:
+ case INDEX_op_smin_vec:
+ case INDEX_op_smax_vec:
+ case INDEX_op_umin_vec:
+ case INDEX_op_umax_vec:
return C_O1_I2(w, w, w);
case INDEX_op_not_vec:
--
2.34.1
- [PULL 08/39] tcg: pass vece to tcg_target_const_match(), (continued)
- [PULL 08/39] tcg: pass vece to tcg_target_const_match(), Richard Henderson, 2023/09/15
- [PULL 10/39] tcg/loongarch64: Lower add/sub_vec to vadd/vsub, Richard Henderson, 2023/09/15
- [PULL 11/39] tcg/loongarch64: Lower vector bitwise operations, Richard Henderson, 2023/09/15
- [PULL 09/39] tcg/loongarch64: Lower cmp_vec to vseq/vsle/vslt, Richard Henderson, 2023/09/15
- [PULL 12/39] tcg/loongarch64: Lower neg_vec to vneg, Richard Henderson, 2023/09/15
- [PULL 13/39] tcg/loongarch64: Lower mul_vec to vmul, Richard Henderson, 2023/09/15
- [PULL 15/39] tcg/loongarch64: Lower vector saturated ops, Richard Henderson, 2023/09/15
- [PULL 16/39] tcg/loongarch64: Lower vector shift vector ops, Richard Henderson, 2023/09/15
- [PULL 18/39] tcg/loongarch64: Lower vector shift integer ops, Richard Henderson, 2023/09/15
- [PULL 06/39] tcg/loongarch64: Import LSX instructions, Richard Henderson, 2023/09/15
- [PULL 14/39] tcg/loongarch64: Lower vector min max ops,
Richard Henderson <=
- [PULL 17/39] tcg/loongarch64: Lower bitsel_vec to vbitsel, Richard Henderson, 2023/09/15
- [PULL 19/39] tcg/loongarch64: Lower rotv_vec ops to LSX, Richard Henderson, 2023/09/15
- [PULL 20/39] tcg/loongarch64: Lower rotli_vec to vrotri, Richard Henderson, 2023/09/15
- [PULL 21/39] tcg/loongarch64: Implement 128-bit load & store, Richard Henderson, 2023/09/15
- [PULL 22/39] tcg: Add gvec compare with immediate and scalar operand, Richard Henderson, 2023/09/15
- [PULL 23/39] target/arm: Use tcg_gen_gvec_cmpi for compare vs 0, Richard Henderson, 2023/09/15
- [PULL 24/39] accel/tcg: Simplify tlb_plugin_lookup, Richard Henderson, 2023/09/15
- [PULL 25/39] accel/tcg: Split out io_prepare and io_failed, Richard Henderson, 2023/09/15
- [PULL 27/39] plugin: Simplify struct qemu_plugin_hwaddr, Richard Henderson, 2023/09/15
- [PULL 28/39] accel/tcg: Merge cpu_transaction_failed into io_failed, Richard Henderson, 2023/09/15