[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-arm] [PATCH v2 37/67] target/arm: Implement SVE Integer Compare -
|
From: |
Richard Henderson |
|
Subject: |
[Qemu-arm] [PATCH v2 37/67] target/arm: Implement SVE Integer Compare - Immediate Group |
|
Date: |
Sat, 17 Feb 2018 10:22:53 -0800 |
Signed-off-by: Richard Henderson <address@hidden>
---
target/arm/helper-sve.h | 44 +++++++++++++++++++++++
target/arm/sve_helper.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++
target/arm/translate-sve.c | 63 +++++++++++++++++++++++++++++++++
target/arm/sve.decode | 23 ++++++++++++
4 files changed, 218 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 6ffd1fbe8e..ae38c0a4be 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -605,6 +605,50 @@ DEF_HELPER_FLAGS_5(sve_cmplo_ppzw_s, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(sve_cmpls_ppzw_s, TCG_CALL_NO_RWG,
i32, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpeq_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpne_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpgt_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpge_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmplt_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmple_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmphs_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmphi_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmplo_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpls_ppzi_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve_cmpeq_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpne_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpgt_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpge_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmplt_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmple_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmphs_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmphi_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmplo_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpls_ppzi_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve_cmpeq_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpne_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpgt_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpge_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmplt_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmple_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmphs_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmphi_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmplo_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpls_ppzi_s, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve_cmpeq_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpne_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpgt_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpge_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmplt_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmple_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmphs_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmphi_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmplo_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_cmpls_ppzi_d, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr,
i32)
DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr,
i32)
DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr,
i32)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index ae433861f8..b74db681f2 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -2367,3 +2367,91 @@ DO_CMP_PPZW_S(sve_cmpls_ppzw_s, uint32_t, uint64_t, <=)
#undef DO_CMP_PPZW_H
#undef DO_CMP_PPZW_S
#undef DO_CMP_PPZW
+
+/* Similar, but the second source is immediate. */
+#define DO_CMP_PPZI(NAME, TYPE, OP, H, MASK) \
+uint32_t HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc) \
+{ \
+ intptr_t opr_sz = simd_oprsz(desc); \
+ uint32_t flags = PREDTEST_INIT; \
+ TYPE mm = simd_data(desc); \
+ intptr_t i = opr_sz; \
+ do { \
+ uint64_t out = 0, pg; \
+ do { \
+ i -= sizeof(TYPE), out <<= sizeof(TYPE); \
+ TYPE nn = *(TYPE *)(vn + H(i)); \
+ out |= nn OP mm; \
+ } while (i & 63); \
+ pg = *(uint64_t *)(vg + (i >> 3)) & MASK; \
+ out &= pg; \
+ *(uint64_t *)(vd + (i >> 3)) = out; \
+ flags = iter_predtest_bwd(out, pg, flags); \
+ } while (i > 0); \
+ return flags; \
+}
+
+#define DO_CMP_PPZI_B(NAME, TYPE, OP) \
+ DO_CMP_PPZI(NAME, TYPE, OP, H1, 0xffffffffffffffffull)
+#define DO_CMP_PPZI_H(NAME, TYPE, OP) \
+ DO_CMP_PPZI(NAME, TYPE, OP, H1_2, 0x5555555555555555ull)
+#define DO_CMP_PPZI_S(NAME, TYPE, OP) \
+ DO_CMP_PPZI(NAME, TYPE, OP, H1_4, 0x1111111111111111ull)
+#define DO_CMP_PPZI_D(NAME, TYPE, OP) \
+ DO_CMP_PPZI(NAME, TYPE, OP, , 0x0101010101010101ull)
+
+DO_CMP_PPZI_B(sve_cmpeq_ppzi_b, uint8_t, ==)
+DO_CMP_PPZI_H(sve_cmpeq_ppzi_h, uint16_t, ==)
+DO_CMP_PPZI_S(sve_cmpeq_ppzi_s, uint32_t, ==)
+DO_CMP_PPZI_D(sve_cmpeq_ppzi_d, uint64_t, ==)
+
+DO_CMP_PPZI_B(sve_cmpne_ppzi_b, uint8_t, !=)
+DO_CMP_PPZI_H(sve_cmpne_ppzi_h, uint16_t, !=)
+DO_CMP_PPZI_S(sve_cmpne_ppzi_s, uint32_t, !=)
+DO_CMP_PPZI_D(sve_cmpne_ppzi_d, uint64_t, !=)
+
+DO_CMP_PPZI_B(sve_cmpgt_ppzi_b, int8_t, >)
+DO_CMP_PPZI_H(sve_cmpgt_ppzi_h, int16_t, >)
+DO_CMP_PPZI_S(sve_cmpgt_ppzi_s, int32_t, >)
+DO_CMP_PPZI_D(sve_cmpgt_ppzi_d, int64_t, >)
+
+DO_CMP_PPZI_B(sve_cmpge_ppzi_b, int8_t, >=)
+DO_CMP_PPZI_H(sve_cmpge_ppzi_h, int16_t, >=)
+DO_CMP_PPZI_S(sve_cmpge_ppzi_s, int32_t, >=)
+DO_CMP_PPZI_D(sve_cmpge_ppzi_d, int64_t, >=)
+
+DO_CMP_PPZI_B(sve_cmphi_ppzi_b, uint8_t, >)
+DO_CMP_PPZI_H(sve_cmphi_ppzi_h, uint16_t, >)
+DO_CMP_PPZI_S(sve_cmphi_ppzi_s, uint32_t, >)
+DO_CMP_PPZI_D(sve_cmphi_ppzi_d, uint64_t, >)
+
+DO_CMP_PPZI_B(sve_cmphs_ppzi_b, uint8_t, >=)
+DO_CMP_PPZI_H(sve_cmphs_ppzi_h, uint16_t, >=)
+DO_CMP_PPZI_S(sve_cmphs_ppzi_s, uint32_t, >=)
+DO_CMP_PPZI_D(sve_cmphs_ppzi_d, uint64_t, >=)
+
+DO_CMP_PPZI_B(sve_cmplt_ppzi_b, int8_t, <)
+DO_CMP_PPZI_H(sve_cmplt_ppzi_h, int16_t, <)
+DO_CMP_PPZI_S(sve_cmplt_ppzi_s, int32_t, <)
+DO_CMP_PPZI_D(sve_cmplt_ppzi_d, int64_t, <)
+
+DO_CMP_PPZI_B(sve_cmple_ppzi_b, int8_t, <=)
+DO_CMP_PPZI_H(sve_cmple_ppzi_h, int16_t, <=)
+DO_CMP_PPZI_S(sve_cmple_ppzi_s, int32_t, <=)
+DO_CMP_PPZI_D(sve_cmple_ppzi_d, int64_t, <=)
+
+DO_CMP_PPZI_B(sve_cmplo_ppzi_b, uint8_t, <)
+DO_CMP_PPZI_H(sve_cmplo_ppzi_h, uint16_t, <)
+DO_CMP_PPZI_S(sve_cmplo_ppzi_s, uint32_t, <)
+DO_CMP_PPZI_D(sve_cmplo_ppzi_d, uint64_t, <)
+
+DO_CMP_PPZI_B(sve_cmpls_ppzi_b, uint8_t, <=)
+DO_CMP_PPZI_H(sve_cmpls_ppzi_h, uint16_t, <=)
+DO_CMP_PPZI_S(sve_cmpls_ppzi_s, uint32_t, <=)
+DO_CMP_PPZI_D(sve_cmpls_ppzi_d, uint64_t, <=)
+
+#undef DO_CMP_PPZI_B
+#undef DO_CMP_PPZI_H
+#undef DO_CMP_PPZI_S
+#undef DO_CMP_PPZI_D
+#undef DO_CMP_PPZI
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index cb54777108..a7eeb122e3 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -39,6 +39,8 @@ typedef void GVecGen2iFn(unsigned, uint32_t, uint32_t,
typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t,
uint32_t, uint32_t, uint32_t);
+typedef void gen_helper_gvec_flags_3(TCGv_i32, TCGv_ptr, TCGv_ptr,
+ TCGv_ptr, TCGv_i32);
typedef void gen_helper_gvec_flags_4(TCGv_i32, TCGv_ptr, TCGv_ptr,
TCGv_ptr, TCGv_ptr, TCGv_i32);
@@ -2572,6 +2574,67 @@ DO_PPZW(CMPLS, cmpls)
#undef DO_PPZW
+/*
+ *** SVE Integer Compare - Immediate Groups
+ */
+
+static void do_ppzi_flags(DisasContext *s, arg_rpri_esz *a,
+ gen_helper_gvec_flags_3 *gen_fn)
+{
+ TCGv_ptr pd, zn, pg;
+ unsigned vsz;
+ TCGv_i32 t;
+
+ if (gen_fn == NULL) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ vsz = vec_full_reg_size(s);
+ t = tcg_const_i32(simd_desc(vsz, vsz, a->imm));
+ pd = tcg_temp_new_ptr();
+ zn = tcg_temp_new_ptr();
+ pg = tcg_temp_new_ptr();
+
+ tcg_gen_addi_ptr(pd, cpu_env, pred_full_reg_offset(s, a->rd));
+ tcg_gen_addi_ptr(zn, cpu_env, vec_full_reg_offset(s, a->rn));
+ tcg_gen_addi_ptr(pg, cpu_env, pred_full_reg_offset(s, a->pg));
+
+ gen_fn(t, pd, zn, pg, t);
+
+ tcg_temp_free_ptr(pd);
+ tcg_temp_free_ptr(zn);
+ tcg_temp_free_ptr(pg);
+
+ do_pred_flags(t);
+
+ tcg_temp_free_i32(t);
+}
+
+#define DO_PPZI(NAME, name) \
+static void trans_##NAME##_ppzi(DisasContext *s, arg_rpri_esz *a, \
+ uint32_t insn) \
+{ \
+ static gen_helper_gvec_flags_3 * const fns[4] = { \
+ gen_helper_sve_##name##_ppzi_b, gen_helper_sve_##name##_ppzi_h, \
+ gen_helper_sve_##name##_ppzi_s, gen_helper_sve_##name##_ppzi_d, \
+ }; \
+ do_ppzi_flags(s, a, fns[a->esz]); \
+}
+
+DO_PPZI(CMPEQ, cmpeq)
+DO_PPZI(CMPNE, cmpne)
+DO_PPZI(CMPGT, cmpgt)
+DO_PPZI(CMPGE, cmpge)
+DO_PPZI(CMPHI, cmphi)
+DO_PPZI(CMPHS, cmphs)
+DO_PPZI(CMPLT, cmplt)
+DO_PPZI(CMPLE, cmple)
+DO_PPZI(CMPLO, cmplo)
+DO_PPZI(CMPLS, cmpls)
+
+#undef DO_PPZI
+
/*
*** SVE Memory - 32-bit Gather and Unsized Contiguous Group
*/
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index deedc9163b..0e317d7d48 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -132,6 +132,11 @@
@rdn_dbm ........ .. .... dbm:13 rd:5 \
&rr_dbm rn=%reg_movprfx
+# Predicate output, vector and immediate input,
+# controlling predicate, element size.
address@hidden ........ esz:2 . imm:7 . pg:3 rn:5 . rd:4 &rpri_esz
address@hidden ........ esz:2 . imm:s5 ... pg:3 rn:5 . rd:4 &rpri_esz
+
# Basic Load/Store with 9-bit immediate offset
@pd_rn_i9 ........ ........ ...... rn:5 . rd:4 \
&rri imm=%imm9_16_10
@@ -497,6 +502,24 @@ CMPHI_ppzw 00100100 .. 0 ..... 110 ... ..... 1 ....
@pd_pg_rn_rm
CMPLO_ppzw 00100100 .. 0 ..... 111 ... ..... 0 .... @pd_pg_rn_rm
CMPLS_ppzw 00100100 .. 0 ..... 111 ... ..... 1 .... @pd_pg_rn_rm
+### SVE Integer Compare - Unsigned Immediate Group
+
+# SVE integer compare with unsigned immediate
+CMPHS_ppzi 00100100 .. 1 ....... 0 ... ..... 0 .... @pd_pg_rn_i7
+CMPHI_ppzi 00100100 .. 1 ....... 0 ... ..... 1 .... @pd_pg_rn_i7
+CMPLO_ppzi 00100100 .. 1 ....... 1 ... ..... 0 .... @pd_pg_rn_i7
+CMPLS_ppzi 00100100 .. 1 ....... 1 ... ..... 1 .... @pd_pg_rn_i7
+
+### SVE Integer Compare - Signed Immediate Group
+
+# SVE integer compare with signed immediate
+CMPGE_ppzi 00100101 .. 0 ..... 000 ... ..... 0 .... @pd_pg_rn_i5
+CMPGT_ppzi 00100101 .. 0 ..... 000 ... ..... 1 .... @pd_pg_rn_i5
+CMPLT_ppzi 00100101 .. 0 ..... 001 ... ..... 0 .... @pd_pg_rn_i5
+CMPLE_ppzi 00100101 .. 0 ..... 001 ... ..... 1 .... @pd_pg_rn_i5
+CMPEQ_ppzi 00100101 .. 0 ..... 100 ... ..... 0 .... @pd_pg_rn_i5
+CMPNE_ppzi 00100101 .. 0 ..... 100 ... ..... 1 .... @pd_pg_rn_i5
+
### SVE Predicate Logical Operations Group
# SVE predicate logical operations
--
2.14.3
- [Qemu-arm] [PATCH v2 31/67] target/arm: Implement SVE conditionally broadcast/extract element, (continued)
- [Qemu-arm] [PATCH v2 31/67] target/arm: Implement SVE conditionally broadcast/extract element, Richard Henderson, 2018/02/17
- [Qemu-arm] [PATCH v2 33/67] target/arm: Implement SVE reverse within elements, Richard Henderson, 2018/02/17
- [Qemu-arm] [PATCH v2 35/67] target/arm: Implement SVE Select Vectors Group, Richard Henderson, 2018/02/17
- [Qemu-arm] [PATCH v2 34/67] target/arm: Implement SVE vector splice (predicated), Richard Henderson, 2018/02/17
- [Qemu-arm] [PATCH v2 37/67] target/arm: Implement SVE Integer Compare - Immediate Group,
Richard Henderson <=
- [Qemu-arm] [PATCH v2 36/67] target/arm: Implement SVE Integer Compare - Vectors Group, Richard Henderson, 2018/02/17
- [Qemu-arm] [PATCH v2 38/67] target/arm: Implement SVE Partition Break Group, Richard Henderson, 2018/02/17
- [Qemu-arm] [PATCH v2 39/67] target/arm: Implement SVE Predicate Count Group, Richard Henderson, 2018/02/17
- [Qemu-arm] [PATCH v2 40/67] target/arm: Implement SVE Integer Compare - Scalars Group, Richard Henderson, 2018/02/17