From: Frank Chang <frank.ch...@sifive.com>
Add the following instructions:
* vqmaccu.vv
* vqmaccu.vx
* vqmacc.vv
* vqmacc.vx
* vqmaccsu.vv
* vqmaccsu.vx
* vqmaccus.vx
Signed-off-by: Frank Chang <frank.ch...@sifive.com>
---
target/riscv/helper.h | 15 ++++
target/riscv/insn32.decode | 7 ++
target/riscv/insn_trans/trans_rvv.inc.c | 109 ++++++++++++++++++++++++
target/riscv/vector_helper.c | 40 +++++++++
4 files changed, 171 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index fe37bd2f4af..6825c15e025 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -640,6 +640,21 @@ DEF_HELPER_6(vwmaccus_vx_b, void, ptr, ptr, tl, ptr, env,
i32)
DEF_HELPER_6(vwmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vwmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vqmaccu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vqmaccu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vqmacc_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vqmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vqmaccsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vqmaccsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vqmaccu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vqmaccu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vqmacc_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vqmacc_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vqmaccsu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vqmaccsu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vqmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vqmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+
DEF_HELPER_6(vmerge_vvm_b, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vmerge_vvm_h, void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_6(vmerge_vvm_w, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 2e305d492d8..b2ecc8dd4d1 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -441,6 +441,13 @@ vwmacc_vx 111101 . ..... ..... 110 ..... 1010111
@r_vm
vwmaccsu_vv 111111 . ..... ..... 010 ..... 1010111 @r_vm
vwmaccsu_vx 111111 . ..... ..... 110 ..... 1010111 @r_vm
vwmaccus_vx 111110 . ..... ..... 110 ..... 1010111 @r_vm
+vqmaccu_vv 111100 . ..... ..... 000 ..... 1010111 @r_vm
+vqmaccu_vx 111100 . ..... ..... 100 ..... 1010111 @r_vm
+vqmacc_vv 111101 . ..... ..... 000 ..... 1010111 @r_vm
+vqmacc_vx 111101 . ..... ..... 100 ..... 1010111 @r_vm
+vqmaccsu_vv 111111 . ..... ..... 000 ..... 1010111 @r_vm
+vqmaccsu_vx 111111 . ..... ..... 100 ..... 1010111 @r_vm
+vqmaccus_vx 111110 . ..... ..... 100 ..... 1010111 @r_vm
vmv_v_v 010111 1 00000 ..... 000 ..... 1010111 @r2
vmv_v_x 010111 1 00000 ..... 100 ..... 1010111 @r2
vmv_v_i 010111 1 00000 ..... 011 ..... 1010111 @r2
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index 11dddc3252c..809280f4c5c 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -64,6 +64,11 @@ static bool require_rvv(DisasContext *s)
return true;
}
+static bool require_ext_vqmac(DisasContext *s)
+{
+ return s->ext_vqmac;
+}
+
/* Destination vector register group cannot overlap source mask register. */
static bool require_vm(int vm, int rd)
{
@@ -461,6 +466,53 @@ static bool vext_check_dss(DisasContext *s, int vd, int
vs1, int vs2,
return ret;
}
+/*
+ * Check function for vector instruction with format:
+ * quad-width result and single-width sources (4*SEW = SEW op SEW)
+ *
+ * is_vs1: indicates whether insn[19:15] is a vs1 field or not.
+ *
+ * Rules to be checked here:
+ * 1. The largest vector register group used by an instruction
+ * can not be greater than 8 vector registers (Section 5.2):
+ * => LMUL < 4.
+ * => SEW < 32.
+ * 2. Destination vector register number is multiples of 4 * LMUL.
+ * (Section 3.3.2)
+ * 3. Source (vs2, vs1) vector register number are multiples of LMUL.
+ * (Section 3.3.2)
+ * 4. Destination vector register cannot overlap a source vector
+ * register (vs2, vs1) group.
+ * (Section 5.2)
+ * 5. Destination vector register group for a masked vector
+ * instruction cannot overlap the source mask register (v0).
+ * (Section 5.3)
+ */
+static bool vext_check_qss(DisasContext *s, int vd, int vs1, int vs2,
+ int vm, bool is_vs1)
+{
+ bool ret = (s->lmul <= 1) &&
+ (s->sew < 2) &&
+ require_align(vd, 1 << (s->lmul + 2)) &&
+ require_align(vs2, 1 << s->lmul) &&
+ require_vm(vm, vd);
+ if (s->lmul < 0) {
+ ret &= require_noover(vd, 1 << (s->lmul + 2), vs2, 1 << s->lmul);
+ } else {
+ ret &= require_noover_widen(vd, 1 << (s->lmul + 2), vs2, 1 << s->lmul);
+ }
+ if (is_vs1) {
+ ret &= require_align(vs1, 1 << s->lmul);
+ if (s->lmul < 0) {
+ ret &= require_noover(vd, 1 << (s->lmul + 2), vs1, 1 << s->lmul);
+ } else {
+ ret &= require_noover_widen(vd, 1 << (s->lmul + 2),
+ vs1, 1 << s->lmul);
+ }
+ }
+ return ret;
+}
+
/*
* Check function for vector instruction with format:
* double-width result and double-width source1 and single-width
@@ -2100,6 +2152,63 @@ GEN_OPIVX_WIDEN_TRANS(vwmacc_vx)
GEN_OPIVX_WIDEN_TRANS(vwmaccsu_vx)
GEN_OPIVX_WIDEN_TRANS(vwmaccus_vx)
+/* Vector Quad-Widening Integer Multiply-Add Instructions (Extension Zvqmac) */
+/* OPIVV with QUAD-WIDEN */
+static bool opivv_quad_widen_check(DisasContext *s, arg_rmrr *a)
+{
+ return require_rvv(s) &&
+ require_ext_vqmac(s) &&
+ vext_check_isa_ill(s) &&
+ vext_check_qss(s, a->rd, a->rs1, a->rs2, a->vm, true);
+}
+
+#define GEN_OPIVV_QUAD_WIDEN_TRANS(NAME, CHECK) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+ static gen_helper_gvec_4_ptr * const fns[2] = { \
+ gen_helper_##NAME##_b, \
+ gen_helper_##NAME##_h \
+ }; \
+ return do_opivv_widen(s, a, fns[s->sew], CHECK); \
+}
+
+GEN_OPIVV_QUAD_WIDEN_TRANS(vqmaccu_vv, opivv_quad_widen_check)
+GEN_OPIVV_QUAD_WIDEN_TRANS(vqmacc_vv, opivv_quad_widen_check)
+GEN_OPIVV_QUAD_WIDEN_TRANS(vqmaccsu_vv, opivv_quad_widen_check)
+
+/* OPIVX with QUAD-WIDEN */
+static bool opivx_quad_widen_check(DisasContext *s, arg_rmrr *a)
+{
+ return require_rvv(s) &&
+ require_ext_vqmac(s) &&
+ vext_check_isa_ill(s) &&
+ vext_check_qss(s, a->rd, a->rs1, a->rs2, a->vm, false);
+}
+
+static bool do_opivx_quad_widen(DisasContext *s, arg_rmrr *a,
+ gen_helper_opivx *fn)
+{
+ if (opivx_quad_widen_check(s, a)) {
+ return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s);
+ }
+ return false;
+}
+
+#define GEN_OPIVX_QUAD_WIDEN_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \
+{ \
+ static gen_helper_opivx * const fns[3] = { \
+ gen_helper_##NAME##_b, \
+ gen_helper_##NAME##_h \
+ }; \
+ return do_opivx_quad_widen(s, a, fns[s->sew]); \
+}
+
+GEN_OPIVX_QUAD_WIDEN_TRANS(vqmaccu_vx)
+GEN_OPIVX_QUAD_WIDEN_TRANS(vqmacc_vx)
+GEN_OPIVX_QUAD_WIDEN_TRANS(vqmaccsu_vx)
+GEN_OPIVX_QUAD_WIDEN_TRANS(vqmaccus_vx)
+
/* Vector Integer Merge and Move Instructions */
static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
{
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 4734ff88ae6..544c8e38fca 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -1983,6 +1983,46 @@ GEN_VEXT_VX(vwmaccus_vx_b, 1, 2)
GEN_VEXT_VX(vwmaccus_vx_h, 2, 4)
GEN_VEXT_VX(vwmaccus_vx_w, 4, 8)
+/* Vector Quad-Widening Integer Multiply-Add Instructions */
+#define QOP_UUU_B uint32_t, uint8_t, uint8_t, uint32_t, uint32_t
+#define QOP_UUU_H uint64_t, uint16_t, uint16_t, uint64_t, uint64_t
+#define QOP_SSS_B int32_t, int8_t, int8_t, int32_t, int32_t
+#define QOP_SSS_H int64_t, int16_t, int16_t, int64_t, int64_t
+#define QOP_SUS_B int32_t, uint8_t, int8_t, uint32_t, int32_t
+#define QOP_SUS_H int64_t, uint16_t, int16_t, uint64_t, int64_t
+#define QOP_SSU_B int32_t, int8_t, uint8_t, int32_t, uint32_t
+#define QOP_SSU_H int64_t, int16_t, uint16_t, int64_t, uint64_t
+
+RVVCALL(OPIVV3, vqmaccu_vv_b, QOP_UUU_B, H4, H1, H1, DO_MACC)
+RVVCALL(OPIVV3, vqmaccu_vv_h, QOP_UUU_H, H8, H2, H2, DO_MACC)
+RVVCALL(OPIVV3, vqmacc_vv_b, QOP_SSS_B, H4, H1, H1, DO_MACC)
+RVVCALL(OPIVV3, vqmacc_vv_h, QOP_SSS_H, H8, H2, H2, DO_MACC)
+RVVCALL(OPIVV3, vqmaccsu_vv_b, QOP_SSU_B, H4, H1, H1, DO_MACC)
+RVVCALL(OPIVV3, vqmaccsu_vv_h, QOP_SSU_H, H8, H2, H2, DO_MACC)
+GEN_VEXT_VV(vqmaccu_vv_b, 1, 4)
+GEN_VEXT_VV(vqmaccu_vv_h, 2, 8)
+GEN_VEXT_VV(vqmacc_vv_b, 1, 4)
+GEN_VEXT_VV(vqmacc_vv_h, 2, 8)
+GEN_VEXT_VV(vqmaccsu_vv_b, 1, 4)
+GEN_VEXT_VV(vqmaccsu_vv_h, 2, 8)
+
+RVVCALL(OPIVX3, vqmaccu_vx_b, QOP_UUU_B, H4, H1, DO_MACC)
+RVVCALL(OPIVX3, vqmaccu_vx_h, QOP_UUU_H, H8, H2, DO_MACC)
+RVVCALL(OPIVX3, vqmacc_vx_b, QOP_SSS_B, H4, H1, DO_MACC)
+RVVCALL(OPIVX3, vqmacc_vx_h, QOP_SSS_H, H8, H2, DO_MACC)
+RVVCALL(OPIVX3, vqmaccsu_vx_b, QOP_SSU_B, H4, H1, DO_MACC)
+RVVCALL(OPIVX3, vqmaccsu_vx_h, QOP_SSU_H, H8, H2, DO_MACC)
+RVVCALL(OPIVX3, vqmaccus_vx_b, QOP_SUS_B, H4, H1, DO_MACC)
+RVVCALL(OPIVX3, vqmaccus_vx_h, QOP_SUS_H, H8, H2, DO_MACC)
+GEN_VEXT_VX(vqmaccu_vx_b, 1, 4)
+GEN_VEXT_VX(vqmaccu_vx_h, 2, 8)
+GEN_VEXT_VX(vqmacc_vx_b, 1, 4)
+GEN_VEXT_VX(vqmacc_vx_h, 2, 8)
+GEN_VEXT_VX(vqmaccsu_vx_b, 1, 4)
+GEN_VEXT_VX(vqmaccsu_vx_h, 2, 8)
+GEN_VEXT_VX(vqmaccus_vx_b, 1, 4)
+GEN_VEXT_VX(vqmaccus_vx_h, 2, 8)
+
/* Vector Integer Merge and Move Instructions */
#define GEN_VEXT_VMV_VV(NAME, ETYPE, H) \
void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \
--
2.17.1
