[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH 18/20] target/arm: Rewrite vector gather stores
|
From: |
Richard Henderson |
|
Subject: |
[Qemu-devel] [PATCH 18/20] target/arm: Rewrite vector gather stores |
|
Date: |
Wed, 8 Aug 2018 21:22:04 -0700 |
This fixes the endianness problem for softmmu, and does
move the main loop out of a macro and into an inlined function.
Signed-off-by: Richard Henderson <address@hidden>
---
target/arm/helper-sve.h | 52 ++++++++++----
target/arm/sve_helper.c | 139 ++++++++++++++++++++++++-------------
target/arm/translate-sve.c | 74 +++++++++++++-------
3 files changed, 177 insertions(+), 88 deletions(-)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 49d1c09e30..6b9b93af45 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -1468,41 +1468,67 @@ DEF_HELPER_FLAGS_6(sve_ldffsds_zd, TCG_CALL_NO_WG,
DEF_HELPER_FLAGS_6(sve_stbs_zsu, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_sths_zsu, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_sths_le_zsu, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_stss_zsu, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_sths_be_zsu, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stss_le_zsu, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stss_be_zsu, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_stbs_zss, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_sths_zss, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_sths_le_zss, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_stss_zss, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_sths_be_zss, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stss_le_zss, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stss_be_zss, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_stbd_zsu, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_sthd_zsu, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_sthd_le_zsu, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_stsd_zsu, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_sthd_be_zsu, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_stdd_zsu, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_stsd_le_zsu, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stsd_be_zsu, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stdd_le_zsu, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stdd_be_zsu, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_stbd_zss, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_sthd_zss, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_sthd_le_zss, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_stsd_zss, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_sthd_be_zss, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_stdd_zss, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_stsd_le_zss, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stsd_be_zss, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stdd_le_zss, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stdd_be_zss, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_stbd_zd, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_sthd_zd, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_sthd_le_zd, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_stsd_zd, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_sthd_be_zd, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
-DEF_HELPER_FLAGS_6(sve_stdd_zd, TCG_CALL_NO_WG,
+DEF_HELPER_FLAGS_6(sve_stsd_le_zd, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stsd_be_zd, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stdd_le_zd, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stdd_be_zd, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 76d3f021e4..0a4756bff9 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -5235,61 +5235,100 @@ DO_LDFF1_ZPZ_D(sve_ldffsds_zd, uint64_t, int32_t,
cpu_ldl_data_ra)
/* Stores with a vector index. */
-#define DO_ST1_ZPZ_S(NAME, TYPEI, FN) \
-void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \
- target_ulong base, uint32_t desc) \
-{ \
- intptr_t i, oprsz = simd_oprsz(desc); \
- unsigned scale = simd_data(desc); \
- uintptr_t ra = GETPC(); \
- for (i = 0; i < oprsz; ) { \
- uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \
- do { \
- if (likely(pg & 1)) { \
- target_ulong off = *(TYPEI *)(vm + H1_4(i)); \
- uint32_t d = *(uint32_t *)(vd + H1_4(i)); \
- FN(env, base + (off << scale), d, ra); \
- } \
- i += sizeof(uint32_t), pg >>= sizeof(uint32_t); \
- } while (i & 15); \
- } \
+static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
+ target_ulong base, uint32_t desc, uintptr_t ra,
+ zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn)
+{
+ const int mmu_idx = cpu_mmu_index(env, false);
+ intptr_t i, oprsz = simd_oprsz(desc);
+ unsigned scale = simd_data(desc);
+
+ set_helper_retaddr(ra);
+ for (i = 0; i < oprsz; ) {
+ uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
+ do {
+ if (pg & 1) {
+ target_ulong off = off_fn(vm, i);
+ tlb_fn(env, vd, i, base + (off << scale), mmu_idx, ra);
+ }
+ i += 4, pg >>= 4;
+ } while (i & 15);
+ }
+ set_helper_retaddr(0);
}
-#define DO_ST1_ZPZ_D(NAME, TYPEI, FN) \
-void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \
- target_ulong base, uint32_t desc) \
-{ \
- intptr_t i, oprsz = simd_oprsz(desc) / 8; \
- unsigned scale = simd_data(desc); \
- uintptr_t ra = GETPC(); \
- uint64_t *d = vd, *m = vm; uint8_t *pg = vg; \
- for (i = 0; i < oprsz; i++) { \
- if (likely(pg[H1(i)] & 1)) { \
- target_ulong off = (target_ulong)(TYPEI)m[i] << scale; \
- FN(env, base + off, d[i], ra); \
- } \
- } \
+static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
+ target_ulong base, uint32_t desc, uintptr_t ra,
+ zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn)
+{
+ const int mmu_idx = cpu_mmu_index(env, false);
+ intptr_t i, oprsz = simd_oprsz(desc) / 8;
+ unsigned scale = simd_data(desc);
+
+ set_helper_retaddr(ra);
+ for (i = 0; i < oprsz; i++) {
+ uint8_t pg = *(uint8_t *)(vg + H1(i));
+ if (pg & 1) {
+ target_ulong off = off_fn(vm, i * 8);
+ tlb_fn(env, vd, i * 8, base + (off << scale), mmu_idx, ra);
+ }
+ }
+ set_helper_retaddr(0);
}
-DO_ST1_ZPZ_S(sve_stbs_zsu, uint32_t, cpu_stb_data_ra)
-DO_ST1_ZPZ_S(sve_sths_zsu, uint32_t, cpu_stw_data_ra)
-DO_ST1_ZPZ_S(sve_stss_zsu, uint32_t, cpu_stl_data_ra)
+#define DO_ST1_ZPZ_S(MEM, OFS) \
+void __attribute__((flatten)) HELPER(sve_st##MEM##_##OFS) \
+ (CPUARMState *env, void *vd, void *vg, void *vm, \
+ target_ulong base, uint32_t desc) \
+{ \
+ sve_st1_zs(env, vd, vg, vm, base, desc, GETPC(), \
+ off_##OFS##_s, sve_st1##MEM##_tlb); \
+}
-DO_ST1_ZPZ_S(sve_stbs_zss, int32_t, cpu_stb_data_ra)
-DO_ST1_ZPZ_S(sve_sths_zss, int32_t, cpu_stw_data_ra)
-DO_ST1_ZPZ_S(sve_stss_zss, int32_t, cpu_stl_data_ra)
+#define DO_ST1_ZPZ_D(MEM, OFS) \
+void __attribute__((flatten)) HELPER(sve_st##MEM##_##OFS) \
+ (CPUARMState *env, void *vd, void *vg, void *vm, \
+ target_ulong base, uint32_t desc) \
+{ \
+ sve_st1_zd(env, vd, vg, vm, base, desc, GETPC(), \
+ off_##OFS##_d, sve_st1##MEM##_tlb); \
+}
-DO_ST1_ZPZ_D(sve_stbd_zsu, uint32_t, cpu_stb_data_ra)
-DO_ST1_ZPZ_D(sve_sthd_zsu, uint32_t, cpu_stw_data_ra)
-DO_ST1_ZPZ_D(sve_stsd_zsu, uint32_t, cpu_stl_data_ra)
-DO_ST1_ZPZ_D(sve_stdd_zsu, uint32_t, cpu_stq_data_ra)
+DO_ST1_ZPZ_S(bs, zsu)
+DO_ST1_ZPZ_S(hs_le, zsu)
+DO_ST1_ZPZ_S(hs_be, zsu)
+DO_ST1_ZPZ_S(ss_le, zsu)
+DO_ST1_ZPZ_S(ss_be, zsu)
-DO_ST1_ZPZ_D(sve_stbd_zss, int32_t, cpu_stb_data_ra)
-DO_ST1_ZPZ_D(sve_sthd_zss, int32_t, cpu_stw_data_ra)
-DO_ST1_ZPZ_D(sve_stsd_zss, int32_t, cpu_stl_data_ra)
-DO_ST1_ZPZ_D(sve_stdd_zss, int32_t, cpu_stq_data_ra)
+DO_ST1_ZPZ_S(bs, zss)
+DO_ST1_ZPZ_S(hs_le, zss)
+DO_ST1_ZPZ_S(hs_be, zss)
+DO_ST1_ZPZ_S(ss_le, zss)
+DO_ST1_ZPZ_S(ss_be, zss)
-DO_ST1_ZPZ_D(sve_stbd_zd, uint64_t, cpu_stb_data_ra)
-DO_ST1_ZPZ_D(sve_sthd_zd, uint64_t, cpu_stw_data_ra)
-DO_ST1_ZPZ_D(sve_stsd_zd, uint64_t, cpu_stl_data_ra)
-DO_ST1_ZPZ_D(sve_stdd_zd, uint64_t, cpu_stq_data_ra)
+DO_ST1_ZPZ_D(bd, zsu)
+DO_ST1_ZPZ_D(hd_le, zsu)
+DO_ST1_ZPZ_D(hd_be, zsu)
+DO_ST1_ZPZ_D(sd_le, zsu)
+DO_ST1_ZPZ_D(sd_be, zsu)
+DO_ST1_ZPZ_D(dd_le, zsu)
+DO_ST1_ZPZ_D(dd_be, zsu)
+
+DO_ST1_ZPZ_D(bd, zss)
+DO_ST1_ZPZ_D(hd_le, zss)
+DO_ST1_ZPZ_D(hd_be, zss)
+DO_ST1_ZPZ_D(sd_le, zss)
+DO_ST1_ZPZ_D(sd_be, zss)
+DO_ST1_ZPZ_D(dd_le, zss)
+DO_ST1_ZPZ_D(dd_be, zss)
+
+DO_ST1_ZPZ_D(bd, zd)
+DO_ST1_ZPZ_D(hd_le, zd)
+DO_ST1_ZPZ_D(hd_be, zd)
+DO_ST1_ZPZ_D(sd_le, zd)
+DO_ST1_ZPZ_D(sd_be, zd)
+DO_ST1_ZPZ_D(dd_le, zd)
+DO_ST1_ZPZ_D(dd_be, zd)
+
+#undef DO_ST1_ZPZ_S
+#undef DO_ST1_ZPZ_D
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index d4d7e9d3ae..fdd9b9b3a0 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -5299,35 +5299,58 @@ static bool trans_LD1_zpiz(DisasContext *s,
arg_LD1_zpiz *a, uint32_t insn)
return true;
}
-/* Indexed by [xs][msz]. */
-static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][3] = {
- { gen_helper_sve_stbs_zsu,
- gen_helper_sve_sths_zsu,
- gen_helper_sve_stss_zsu, },
- { gen_helper_sve_stbs_zss,
- gen_helper_sve_sths_zss,
- gen_helper_sve_stss_zss, },
+/* Indexed by [be][xs][msz]. */
+static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][2][3] = {
+ /* Little-endian */
+ { { gen_helper_sve_stbs_zsu,
+ gen_helper_sve_sths_le_zsu,
+ gen_helper_sve_stss_le_zsu, },
+ { gen_helper_sve_stbs_zss,
+ gen_helper_sve_sths_le_zss,
+ gen_helper_sve_stss_le_zss, } },
+ /* Big-endian */
+ { { gen_helper_sve_stbs_zsu,
+ gen_helper_sve_sths_be_zsu,
+ gen_helper_sve_stss_be_zsu, },
+ { gen_helper_sve_stbs_zss,
+ gen_helper_sve_sths_be_zss,
+ gen_helper_sve_stss_be_zss, } },
};
/* Note that we overload xs=2 to indicate 64-bit offset. */
-static gen_helper_gvec_mem_scatter * const scatter_store_fn64[3][4] = {
- { gen_helper_sve_stbd_zsu,
- gen_helper_sve_sthd_zsu,
- gen_helper_sve_stsd_zsu,
- gen_helper_sve_stdd_zsu, },
- { gen_helper_sve_stbd_zss,
- gen_helper_sve_sthd_zss,
- gen_helper_sve_stsd_zss,
- gen_helper_sve_stdd_zss, },
- { gen_helper_sve_stbd_zd,
- gen_helper_sve_sthd_zd,
- gen_helper_sve_stsd_zd,
- gen_helper_sve_stdd_zd, },
+static gen_helper_gvec_mem_scatter * const scatter_store_fn64[2][3][4] = {
+ /* Little-endian */
+ { { gen_helper_sve_stbd_zsu,
+ gen_helper_sve_sthd_le_zsu,
+ gen_helper_sve_stsd_le_zsu,
+ gen_helper_sve_stdd_le_zsu, },
+ { gen_helper_sve_stbd_zss,
+ gen_helper_sve_sthd_le_zss,
+ gen_helper_sve_stsd_le_zss,
+ gen_helper_sve_stdd_le_zss, },
+ { gen_helper_sve_stbd_zd,
+ gen_helper_sve_sthd_le_zd,
+ gen_helper_sve_stsd_le_zd,
+ gen_helper_sve_stdd_le_zd, } },
+ /* Big-endian */
+ { { gen_helper_sve_stbd_zsu,
+ gen_helper_sve_sthd_be_zsu,
+ gen_helper_sve_stsd_be_zsu,
+ gen_helper_sve_stdd_be_zsu, },
+ { gen_helper_sve_stbd_zss,
+ gen_helper_sve_sthd_be_zss,
+ gen_helper_sve_stsd_be_zss,
+ gen_helper_sve_stdd_be_zss, },
+ { gen_helper_sve_stbd_zd,
+ gen_helper_sve_sthd_be_zd,
+ gen_helper_sve_stsd_be_zd,
+ gen_helper_sve_stdd_be_zd, } },
};
static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn)
{
gen_helper_gvec_mem_scatter *fn;
+ int be = s->be_data == MO_BE;
if (a->esz < a->msz || (a->msz == 0 && a->scale)) {
return false;
@@ -5337,10 +5360,10 @@ static bool trans_ST1_zprz(DisasContext *s,
arg_ST1_zprz *a, uint32_t insn)
}
switch (a->esz) {
case MO_32:
- fn = scatter_store_fn32[a->xs][a->msz];
+ fn = scatter_store_fn32[be][a->xs][a->msz];
break;
case MO_64:
- fn = scatter_store_fn64[a->xs][a->msz];
+ fn = scatter_store_fn64[be][a->xs][a->msz];
break;
default:
g_assert_not_reached();
@@ -5353,6 +5376,7 @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz
*a, uint32_t insn)
static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a, uint32_t insn)
{
gen_helper_gvec_mem_scatter *fn = NULL;
+ int be = s->be_data == MO_BE;
TCGv_i64 imm;
if (a->esz < a->msz) {
@@ -5364,10 +5388,10 @@ static bool trans_ST1_zpiz(DisasContext *s,
arg_ST1_zpiz *a, uint32_t insn)
switch (a->esz) {
case MO_32:
- fn = scatter_store_fn32[0][a->msz];
+ fn = scatter_store_fn32[be][0][a->msz];
break;
case MO_64:
- fn = scatter_store_fn64[2][a->msz];
+ fn = scatter_store_fn64[be][2][a->msz];
break;
}
assert(fn != NULL);
--
2.17.1
- Re: [Qemu-devel] [PATCH 12/20] target/arm: Rewrite helper_sve_ld1*_r using pages, (continued)
- [Qemu-devel] [PATCH 14/20] target/arm: Rewrite helper_sve_st[1234]*_r, Richard Henderson, 2018/08/09
- [Qemu-devel] [PATCH 16/20] target/arm: Split contiguous stores for endianness, Richard Henderson, 2018/08/09
- [Qemu-devel] [PATCH 13/20] target/arm: Rewrite helper_sve_ld[234]*_r, Richard Henderson, 2018/08/09
- [Qemu-devel] [PATCH 15/20] target/arm: Split contiguous loads for endianness, Richard Henderson, 2018/08/09
- [Qemu-devel] [PATCH 18/20] target/arm: Rewrite vector gather stores,
Richard Henderson <=
- [Qemu-devel] [PATCH 17/20] target/arm: Rewrite vector gather loads, Richard Henderson, 2018/08/09
- [Qemu-devel] [PATCH 19/20] target/arm: Rewrite vector gather first-fault loads, Richard Henderson, 2018/08/09
- [Qemu-devel] [PATCH 20/20] target/arm: Pass TCGMemOpIdx to sve memory helpers, Richard Henderson, 2018/08/09
- Re: [Qemu-devel] [PATCH 00/20] target/arm: sve system mode patches, Laurent Desnogues, 2018/08/09
- Re: [Qemu-devel] [PATCH 00/20] target/arm: sve system mode patches, no-reply, 2018/08/18
- Re: [Qemu-devel] [PATCH 00/20] target/arm: sve system mode patches, no-reply, 2018/08/18