[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[RFC 58/65] target/riscv: rvv-0.9: widening floating-point/integer type-
From: |
frank . chang |
Subject: |
[RFC 58/65] target/riscv: rvv-0.9: widening floating-point/integer type-convert |
Date: |
Fri, 10 Jul 2020 18:49:12 +0800 |
From: Frank Chang <frank.chang@sifive.com>
Signed-off-by: Frank Chang <frank.chang@sifive.com>
---
target/riscv/helper.h | 6 ++++
target/riscv/insn32.decode | 13 +++++---
target/riscv/insn_trans/trans_rvv.inc.c | 44 +++++++++++++++++++++++--
target/riscv/vector_helper.c | 29 +++++++++++++++-
4 files changed, 84 insertions(+), 8 deletions(-)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index e9655453bc..0cd5979288 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -977,12 +977,18 @@ DEF_HELPER_5(vfwcvt_xu_f_v_h, void, ptr, ptr, ptr, env,
i32)
DEF_HELPER_5(vfwcvt_xu_f_v_w, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfwcvt_x_f_v_h, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfwcvt_x_f_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_f_xu_v_b, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfwcvt_f_xu_v_h, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfwcvt_f_xu_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_f_x_v_b, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfwcvt_f_x_v_h, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfwcvt_f_x_v_w, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfwcvt_f_f_v_h, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfwcvt_f_f_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_rtz_xu_f_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_rtz_xu_f_v_w, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_rtz_x_f_v_h, void, ptr, ptr, ptr, env, i32)
+DEF_HELPER_5(vfwcvt_rtz_x_f_v_w, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfncvt_xu_f_v_h, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_5(vfncvt_xu_f_v_w, void, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index bc0e44b8ab..55d7a6f338 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -545,11 +545,14 @@ vfcvt_f_xu_v 010010 . ..... 00010 001 ..... 1010111
@r2_vm
vfcvt_f_x_v 010010 . ..... 00011 001 ..... 1010111 @r2_vm
vfcvt_rtz_xu_f_v 010010 . ..... 00110 001 ..... 1010111 @r2_vm
vfcvt_rtz_x_f_v 010010 . ..... 00111 001 ..... 1010111 @r2_vm
-vfwcvt_xu_f_v 100010 . ..... 01000 001 ..... 1010111 @r2_vm
-vfwcvt_x_f_v 100010 . ..... 01001 001 ..... 1010111 @r2_vm
-vfwcvt_f_xu_v 100010 . ..... 01010 001 ..... 1010111 @r2_vm
-vfwcvt_f_x_v 100010 . ..... 01011 001 ..... 1010111 @r2_vm
-vfwcvt_f_f_v 100010 . ..... 01100 001 ..... 1010111 @r2_vm
+
+vfwcvt_xu_f_v 010010 . ..... 01000 001 ..... 1010111 @r2_vm
+vfwcvt_x_f_v 010010 . ..... 01001 001 ..... 1010111 @r2_vm
+vfwcvt_f_xu_v 010010 . ..... 01010 001 ..... 1010111 @r2_vm
+vfwcvt_f_x_v 010010 . ..... 01011 001 ..... 1010111 @r2_vm
+vfwcvt_f_f_v 010010 . ..... 01100 001 ..... 1010111 @r2_vm
+vfwcvt_rtz_xu_f_v 010010 . ..... 01110 001 ..... 1010111 @r2_vm
+vfwcvt_rtz_x_f_v 010010 . ..... 01111 001 ..... 1010111 @r2_vm
vfncvt_xu_f_v 100010 . ..... 10000 001 ..... 1010111 @r2_vm
vfncvt_x_f_v 100010 . ..... 10001 001 ..... 1010111 @r2_vm
vfncvt_f_xu_v 100010 . ..... 10010 001 ..... 1010111 @r2_vm
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c
b/target/riscv/insn_trans/trans_rvv.inc.c
index fb2c119e13..4840200f01 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2674,9 +2674,49 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)
\
GEN_OPFV_WIDEN_TRANS(vfwcvt_xu_f_v)
GEN_OPFV_WIDEN_TRANS(vfwcvt_x_f_v)
-GEN_OPFV_WIDEN_TRANS(vfwcvt_f_xu_v)
-GEN_OPFV_WIDEN_TRANS(vfwcvt_f_x_v)
GEN_OPFV_WIDEN_TRANS(vfwcvt_f_f_v)
+GEN_OPFV_WIDEN_TRANS(vfwcvt_rtz_xu_f_v)
+GEN_OPFV_WIDEN_TRANS(vfwcvt_rtz_x_f_v)
+
+static bool opfxv_widen_check(DisasContext *s, arg_rmr *a)
+{
+ REQUIRE_RVV;
+ VEXT_CHECK_ISA_ILL(s);
+ /* OPFV widening instructions ignore vs1 check */
+ VEXT_CHECK_DSS(s, a->rd, 0, a->rs2, a->vm, false);
+ return true;
+}
+
+#define GEN_OPFXV_WIDEN_TRANS(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_rmr *a) \
+{ \
+ if (opfxv_widen_check(s, a)) { \
+ uint32_t data = 0; \
+ static gen_helper_gvec_3_ptr * const fns[3] = { \
+ gen_helper_##NAME##_b, \
+ gen_helper_##NAME##_h, \
+ gen_helper_##NAME##_w, \
+ }; \
+ TCGLabel *over = gen_new_label(); \
+ gen_set_rm(s, 7); \
+ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ \
+ data = FIELD_DP32(data, VDATA, VM, a->vm); \
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
+ data = FIELD_DP32(data, VDATA, VMA, s->vma); \
+ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \
+ vreg_ofs(s, a->rs2), cpu_env, 0, \
+ s->vlen / 8, data, fns[s->sew]); \
+ mark_vs_dirty(s); \
+ gen_set_label(over); \
+ return true; \
+ } \
+ return false; \
+}
+
+GEN_OPFXV_WIDEN_TRANS(vfwcvt_f_xu_v)
+GEN_OPFXV_WIDEN_TRANS(vfwcvt_f_x_v)
/* Narrowing Floating-Point/Integer Type-Convert Instructions */
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d617d0dfbd..0b6dd4c93f 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4295,6 +4295,7 @@ GEN_VEXT_V_ENV(vfcvt_rtz_x_f_v_d, 8, 8, clearq)
/* Widening Floating-Point/Integer Type-Convert Instructions */
/* (TD, T2, TX2) */
+#define WOP_UU_B uint16_t, uint8_t, uint8_t
#define WOP_UU_H uint32_t, uint16_t, uint16_t
#define WOP_UU_W uint64_t, uint32_t, uint32_t
/* vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned
integer.*/
@@ -4310,19 +4311,45 @@ GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 2, 4, clearl)
GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 4, 8, clearq)
/* vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float
*/
+RVVCALL(OPFVV1, vfwcvt_f_xu_v_b, WOP_UU_B, H2, H1, uint8_to_float16)
RVVCALL(OPFVV1, vfwcvt_f_xu_v_h, WOP_UU_H, H4, H2, uint16_to_float32)
RVVCALL(OPFVV1, vfwcvt_f_xu_v_w, WOP_UU_W, H8, H4, uint32_to_float64)
+GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b, 1, 2, clearh)
GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h, 2, 4, clearl)
GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w, 4, 8, clearq)
/* vfwcvt.f.x.v vd, vs2, vm # Convert integer to double-width float. */
+RVVCALL(OPFVV1, vfwcvt_f_x_v_b, WOP_UU_B, H2, H1, int8_to_float16)
RVVCALL(OPFVV1, vfwcvt_f_x_v_h, WOP_UU_H, H4, H2, int16_to_float32)
RVVCALL(OPFVV1, vfwcvt_f_x_v_w, WOP_UU_W, H8, H4, int32_to_float64)
+GEN_VEXT_V_ENV(vfwcvt_f_x_v_b, 1, 2, clearh)
GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 2, 4, clearl)
GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 4, 8, clearq)
/*
- * vfwcvt.f.f.v vd, vs2, vm #
+ * vfwcvt.rtz.xu.f.v vd, vs2, vm
+ * Convert float to double-width unsigned integer, truncating
+ */
+FCVT_RTZ_F_V(float16, uint32)
+FCVT_RTZ_F_V(float32, uint64)
+RVVCALL(OPFVV1, vfwcvt_rtz_xu_f_v_h, WOP_UU_H, H4, H2, float16_to_uint32_rtz)
+RVVCALL(OPFVV1, vfwcvt_rtz_xu_f_v_w, WOP_UU_W, H8, H4, float32_to_uint64_rtz)
+GEN_VEXT_V_ENV(vfwcvt_rtz_xu_f_v_h, 2, 4, clearl)
+GEN_VEXT_V_ENV(vfwcvt_rtz_xu_f_v_w, 4, 8, clearq)
+
+/*
+ * vfwcvt.rtz.x.f.v vd, vs2, vm
+ * Convert float to double-width signed integer, truncating.
+ */
+FCVT_RTZ_F_V(float16, int32)
+FCVT_RTZ_F_V(float32, int64)
+RVVCALL(OPFVV1, vfwcvt_rtz_x_f_v_h, WOP_UU_H, H4, H2, float16_to_int32_rtz)
+RVVCALL(OPFVV1, vfwcvt_rtz_x_f_v_w, WOP_UU_W, H8, H4, float32_to_int64_rtz)
+GEN_VEXT_V_ENV(vfwcvt_rtz_x_f_v_h, 2, 4, clearl)
+GEN_VEXT_V_ENV(vfwcvt_rtz_x_f_v_w, 4, 8, clearq)
+
+/*
+ * vfwcvt.f.f.v vd, vs2, vm
* Convert single-width float to double-width float.
*/
static uint32_t vfwcvtffv16(uint16_t a, float_status *s)
--
2.17.1
- [RFC 19/65] target/riscv: rvv-0.9: load/store whole register instructions, (continued)
- [RFC 19/65] target/riscv: rvv-0.9: load/store whole register instructions, frank . chang, 2020/07/10
- [RFC 20/65] target/riscv: rvv-0.9: update vext_max_elems() for load/store insns, frank . chang, 2020/07/10
- [RFC 30/65] target/riscv: rvv-0.9: floating-point scalar move instructions, frank . chang, 2020/07/10
- [RFC 32/65] target/riscv: rvv-0.9: integer extension instructions, frank . chang, 2020/07/10
- [RFC 34/65] target/riscv: rvv-0.9: integer add-with-carry/subtract-with-borrow, frank . chang, 2020/07/10
- [RFC 37/65] target/riscv: rvv-0.9: quad-widening integer multiply-add instructions, frank . chang, 2020/07/10
- [RFC 46/65] target/riscv: rvv-0.9: slide instructions, frank . chang, 2020/07/10
- [RFC 47/65] target/riscv: rvv-0.9: floating-point slide instructions, frank . chang, 2020/07/10
- [RFC 52/65] target/riscv: rvv-0.9: widening floating-point reduction instructions, frank . chang, 2020/07/10
- [RFC 56/65] target/riscv: rvv-0.9: remove integer extract instruction, frank . chang, 2020/07/10
- [RFC 58/65] target/riscv: rvv-0.9: widening floating-point/integer type-convert,
frank . chang <=
- [RFC 61/65] fpu: fix float16 nan check, frank . chang, 2020/07/10
- [RFC 04/65] target/riscv: fix vill bit index in vtype register, frank . chang, 2020/07/10
- [RFC 22/65] target/riscv: rvv-0.9: floating-point square-root instruction, frank . chang, 2020/07/10
- [RFC 23/65] target/riscv: rvv-0.9: floating-point classify instructions, frank . chang, 2020/07/10
- [RFC 24/65] target/riscv: rvv-0.9: mask population count instruction, frank . chang, 2020/07/10
- [RFC 44/65] target/riscv: rvv-0.9: mask-register logical instructions, frank . chang, 2020/07/10
- [RFC 57/65] target/riscv: rvv-0.9: floating-point min/max instructions, frank . chang, 2020/07/10
- [RFC 54/65] target/riscv: rvv-0.9: remove widening saturating scaled multiply-add, frank . chang, 2020/07/10