[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH 07/18] tcg: add vector addition operations
|
From: |
Kirill Batuzov |
|
Subject: |
[Qemu-devel] [PATCH 07/18] tcg: add vector addition operations |
|
Date: |
Tue, 17 Jan 2017 12:07:47 +0300 |
Signed-off-by: Kirill Batuzov <address@hidden>
---
tcg/tcg-op.h | 169 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
tcg/tcg-opc.h | 12 +++++
tcg/tcg.h | 29 ++++++++++
3 files changed, 210 insertions(+)
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index c469ea3..5de74d3 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -1153,6 +1153,8 @@ void tcg_gen_atomic_xor_fetch_i64(TCGv_i64, TCGv,
TCGv_i64, TCGArg, TCGMemOp);
tcg_gen_add_i32(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), TCGV_PTR_TO_NAT(B))
# define tcg_gen_addi_ptr(R, A, B) \
tcg_gen_addi_i32(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), (B))
+# define tcg_gen_movi_ptr(R, B) \
+ tcg_gen_movi_i32(TCGV_PTR_TO_NAT(R), (B))
# define tcg_gen_ext_i32_ptr(R, A) \
tcg_gen_mov_i32(TCGV_PTR_TO_NAT(R), (A))
#else
@@ -1164,6 +1166,173 @@ void tcg_gen_atomic_xor_fetch_i64(TCGv_i64, TCGv,
TCGv_i64, TCGArg, TCGMemOp);
tcg_gen_add_i64(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), TCGV_PTR_TO_NAT(B))
# define tcg_gen_addi_ptr(R, A, B) \
tcg_gen_addi_i64(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), (B))
+# define tcg_gen_movi_ptr(R, B) \
+ tcg_gen_movi_i64(TCGV_PTR_TO_NAT(R), (B))
# define tcg_gen_ext_i32_ptr(R, A) \
tcg_gen_ext_i32_i64(TCGV_PTR_TO_NAT(R), (A))
#endif /* UINTPTR_MAX == UINT32_MAX */
+
+/***************************************/
+/* 64-bit and 128-bit vector arithmetic. */
+
+static inline void *tcg_v128_swap_slot(int n)
+{
+ return &tcg_ctx.v128_swap[n * 16];
+}
+
+/* Find a memory location for 128-bit TCG variable. */
+static inline void tcg_v128_to_ptr(TCGv_v128 tmp, TCGv_ptr base, int slot,
+ TCGv_ptr *real_base, intptr_t *real_offset,
+ int is_read)
+{
+ int idx = GET_TCGV_V128(tmp);
+ assert(idx >= 0 && idx < tcg_ctx.nb_temps);
+ if (idx < tcg_ctx.nb_globals) {
+ /* Globals use their locations within CPUArchState. */
+ int env = GET_TCGV_PTR(tcg_ctx.tcg_env);
+ TCGTemp *ts_env = &tcg_ctx.temps[env];
+ TCGTemp *ts_arg = &tcg_ctx.temps[idx];
+
+ /* Sanity checks: global's memory locations must be addressed
+ relative to ENV. */
+ assert(ts_env->val_type == TEMP_VAL_REG &&
+ ts_env == ts_arg->mem_base &&
+ ts_arg->mem_allocated);
+
+ *real_base = tcg_ctx.tcg_env;
+ *real_offset = ts_arg->mem_offset;
+ } else {
+ /* Temporaries use swap space in TCGContext. Since we already have
+ a 128-bit temporary we'll assume that the target supports 128-bit
+ loads and stores. */
+ *real_base = base;
+ *real_offset = slot * 16;
+ if (is_read) {
+ tcg_gen_st_v128(tmp, base, slot * 16);
+ }
+ }
+}
+
+/* Find a memory location for 64-bit vector TCG variable. */
+static inline void tcg_v64_to_ptr(TCGv_v64 tmp, TCGv_ptr base, int slot,
+ TCGv_ptr *real_base, intptr_t *real_offset,
+ int is_read)
+{
+ int idx = GET_TCGV_V64(tmp);
+ assert(idx >= 0 && idx < tcg_ctx.nb_temps);
+ if (idx < tcg_ctx.nb_globals) {
+ /* Globals use their locations within CPUArchState. */
+ int env = GET_TCGV_PTR(tcg_ctx.tcg_env);
+ TCGTemp *ts_env = &tcg_ctx.temps[env];
+ TCGTemp *ts_arg = &tcg_ctx.temps[idx];
+
+ /* Sanity checks: global's memory locations must be addressed
+ relative to ENV. */
+ assert(ts_env->val_type == TEMP_VAL_REG &&
+ ts_env == ts_arg->mem_base &&
+ ts_arg->mem_allocated);
+
+ *real_base = tcg_ctx.tcg_env;
+ *real_offset = ts_arg->mem_offset;
+ } else {
+ /* Temporaries use swap space in TCGContext. Since we already have
+ a 128-bit temporary we'll assume that the target supports 128-bit
+ loads and stores. */
+ *real_base = base;
+ *real_offset = slot * 16;
+ if (is_read) {
+ tcg_gen_st_v64(tmp, base, slot * 16);
+ }
+ }
+}
+
+#define GEN_VECT_WRAPPER(name, type, func) \
+ static inline void glue(tcg_gen_, name)(glue(TCGv_, type) res, \
+ glue(TCGv_, type) arg1, \
+ glue(TCGv_, type) arg2) \
+ { \
+ if (glue(TCG_TARGET_HAS_, name)) { \
+ glue(tcg_gen_op3_, type)(glue(INDEX_op_, name), res, arg1, \
+ arg2); \
+ } else { \
+ TCGv_ptr base = tcg_temp_new_ptr(); \
+ TCGv_ptr t1 = tcg_temp_new_ptr(); \
+ TCGv_ptr t2 = tcg_temp_new_ptr(); \
+ TCGv_ptr t3 = tcg_temp_new_ptr(); \
+ TCGv_ptr arg1p, arg2p, resp; \
+ intptr_t arg1of, arg2of, resof; \
+ \
+ tcg_gen_movi_ptr(base, (unsigned long)&tcg_ctx.v128_swap[0]); \
+ \
+ glue(glue(tcg_, type), _to_ptr)(arg1, base, 1, \
+ &arg1p, &arg1of, 1); \
+ glue(glue(tcg_, type), _to_ptr)(arg2, base, 2, \
+ &arg2p, &arg2of, 1); \
+ glue(glue(tcg_, type), _to_ptr)(res, base, 0, &resp, &resof, 0); \
+ \
+ tcg_gen_addi_ptr(t1, resp, resof); \
+ tcg_gen_addi_ptr(t2, arg1p, arg1of); \
+ tcg_gen_addi_ptr(t3, arg2p, arg2of); \
+ func(t1, t2, t3); \
+ \
+ if ((intptr_t)res >= tcg_ctx.nb_globals) { \
+ glue(tcg_gen_ld_, type)(res, base, 0); \
+ } \
+ \
+ tcg_temp_free_ptr(base); \
+ tcg_temp_free_ptr(t1); \
+ tcg_temp_free_ptr(t2); \
+ tcg_temp_free_ptr(t3); \
+ } \
+ }
+
+#define TCG_INTERNAL_OP(name, N, size, ld, st, op, type) \
+ static inline void glue(tcg_internal_, name)(TCGv_ptr resp, \
+ TCGv_ptr arg1p, \
+ TCGv_ptr arg2p) \
+ { \
+ int i; \
+ glue(TCGv_, type) tmp1, tmp2; \
+ \
+ tmp1 = glue(tcg_temp_new_, type)(); \
+ tmp2 = glue(tcg_temp_new_, type)(); \
+ \
+ for (i = 0; i < N; i++) { \
+ glue(tcg_gen_, ld)(tmp1, arg1p, i * size); \
+ glue(tcg_gen_, ld)(tmp2, arg2p, i * size); \
+ glue(tcg_gen_, op)(tmp1, tmp1, tmp2); \
+ glue(tcg_gen_, st)(tmp1, resp, i * size); \
+ } \
+ \
+ glue(tcg_temp_free_, type)(tmp1); \
+ glue(tcg_temp_free_, type)(tmp2); \
+ }
+
+#define TCG_INTERNAL_OP_8(name, N, op) \
+ TCG_INTERNAL_OP(name, N, 1, ld8u_i32, st8_i32, op, i32)
+#define TCG_INTERNAL_OP_16(name, N, op) \
+ TCG_INTERNAL_OP(name, N, 2, ld16u_i32, st16_i32, op, i32)
+#define TCG_INTERNAL_OP_32(name, N, op) \
+ TCG_INTERNAL_OP(name, N, 4, ld_i32, st_i32, op, i32)
+#define TCG_INTERNAL_OP_64(name, N, op) \
+ TCG_INTERNAL_OP(name, N, 8, ld_i64, st_i64, op, i64)
+
+TCG_INTERNAL_OP_8(add_i8x16, 16, add_i32)
+TCG_INTERNAL_OP_16(add_i16x8, 8, add_i32)
+TCG_INTERNAL_OP_32(add_i32x4, 4, add_i32)
+TCG_INTERNAL_OP_64(add_i64x2, 2, add_i64)
+
+TCG_INTERNAL_OP_8(add_i8x8, 8, add_i32)
+TCG_INTERNAL_OP_16(add_i16x4, 4, add_i32)
+TCG_INTERNAL_OP_32(add_i32x2, 2, add_i32)
+TCG_INTERNAL_OP_64(add_i64x1, 1, add_i64)
+
+GEN_VECT_WRAPPER(add_i8x16, v128, tcg_internal_add_i8x16)
+GEN_VECT_WRAPPER(add_i16x8, v128, tcg_internal_add_i16x8)
+GEN_VECT_WRAPPER(add_i32x4, v128, tcg_internal_add_i32x4)
+GEN_VECT_WRAPPER(add_i64x2, v128, tcg_internal_add_i64x2)
+
+GEN_VECT_WRAPPER(add_i8x8, v64, tcg_internal_add_i8x8)
+GEN_VECT_WRAPPER(add_i16x4, v64, tcg_internal_add_i16x4)
+GEN_VECT_WRAPPER(add_i32x2, v64, tcg_internal_add_i32x2)
+GEN_VECT_WRAPPER(add_i64x1, v64, tcg_internal_add_i64x1)
diff --git a/tcg/tcg-opc.h b/tcg/tcg-opc.h
index d622592..0022535 100644
--- a/tcg/tcg-opc.h
+++ b/tcg/tcg-opc.h
@@ -196,6 +196,18 @@ DEF(ld_v128, 1, 1, 1, IMPL128)
DEF(st_v64, 0, 2, 1, IMPLV64)
DEF(ld_v64, 1, 1, 1, IMPLV64)
+/* 128-bit vector arith */
+DEF(add_i8x16, 1, 2, 0, IMPL128 | IMPL(TCG_TARGET_HAS_add_i8x16))
+DEF(add_i16x8, 1, 2, 0, IMPL128 | IMPL(TCG_TARGET_HAS_add_i16x8))
+DEF(add_i32x4, 1, 2, 0, IMPL128 | IMPL(TCG_TARGET_HAS_add_i32x4))
+DEF(add_i64x2, 1, 2, 0, IMPL128 | IMPL(TCG_TARGET_HAS_add_i64x2))
+
+/* 64-bit vector arith */
+DEF(add_i8x8, 1, 2, 0, IMPLV64 | IMPL(TCG_TARGET_HAS_add_i8x8))
+DEF(add_i16x4, 1, 2, 0, IMPLV64 | IMPL(TCG_TARGET_HAS_add_i16x4))
+DEF(add_i32x2, 1, 2, 0, IMPLV64 | IMPL(TCG_TARGET_HAS_add_i32x2))
+DEF(add_i64x1, 1, 2, 0, IMPLV64 | IMPL(TCG_TARGET_HAS_add_i64x1))
+
/* QEMU specific */
DEF(insn_start, 0, 0, TLADDR_ARGS * TARGET_INSN_START_WORDS,
TCG_OPF_NOT_PRESENT)
diff --git a/tcg/tcg.h b/tcg/tcg.h
index 6473228..6f4d0e7 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -145,6 +145,34 @@ typedef uint64_t TCGRegSet;
#define TCG_TARGET_HAS_rem_i64 0
#endif
+/* 64-bit vector */
+#ifndef TCG_TARGET_HAS_add_i8x8
+#define TCG_TARGET_HAS_add_i8x8 0
+#endif
+#ifndef TCG_TARGET_HAS_add_i16x4
+#define TCG_TARGET_HAS_add_i16x4 0
+#endif
+#ifndef TCG_TARGET_HAS_add_i32x2
+#define TCG_TARGET_HAS_add_i32x2 0
+#endif
+#ifndef TCG_TARGET_HAS_add_i64x1
+#define TCG_TARGET_HAS_add_i64x1 0
+#endif
+
+/* 128-bit vector */
+#ifndef TCG_TARGET_HAS_add_i8x16
+#define TCG_TARGET_HAS_add_i8x16 0
+#endif
+#ifndef TCG_TARGET_HAS_add_i16x8
+#define TCG_TARGET_HAS_add_i16x8 0
+#endif
+#ifndef TCG_TARGET_HAS_add_i32x4
+#define TCG_TARGET_HAS_add_i32x4 0
+#endif
+#ifndef TCG_TARGET_HAS_add_i64x2
+#define TCG_TARGET_HAS_add_i64x2 0
+#endif
+
/* For 32-bit targets, some sort of unsigned widening multiply is required. */
#if TCG_TARGET_REG_BITS == 32 \
&& !(defined(TCG_TARGET_HAS_mulu2_i32) \
@@ -750,6 +778,7 @@ struct TCGContext {
void *code_gen_buffer;
size_t code_gen_buffer_size;
void *code_gen_ptr;
+ uint8_t v128_swap[16 * 3];
/* Threshold to flush the translated code buffer. */
void *code_gen_highwater;
--
2.1.4
- [Qemu-devel] [PATCH 13/18] tcg: do not relay on exact values of MO_BSWAP or MO_SIGN in backend, (continued)
- [Qemu-devel] [PATCH 12/18] tcg/i386: support remaining vector addition operations, Kirill Batuzov, 2017/01/17
- [Qemu-devel] [PATCH 14/18] tcg: introduce new TCGMemOp - MO_128, Kirill Batuzov, 2017/01/17
- [Qemu-devel] [PATCH 07/18] tcg: add vector addition operations,
Kirill Batuzov <=
- [Qemu-devel] [PATCH 15/18] tcg: introduce qemu_ld_v128 and qemu_st_v128 opcodes, Kirill Batuzov, 2017/01/17
- [Qemu-devel] [PATCH 16/18] softmmu: create helpers for vector loads, Kirill Batuzov, 2017/01/17
- [Qemu-devel] [PATCH 17/18] tcg/i386: add support for qemu_ld_v128/qemu_st_v128 ops, Kirill Batuzov, 2017/01/17
- [Qemu-devel] [PATCH 18/18] target/arm: load two consecutive 64-bits vector regs as a 128-bit vector reg, Kirill Batuzov, 2017/01/17
- Re: [Qemu-devel] [PATCH 00/18] Emulate guest vector operations with host vector operations, Alex Bennée, 2017/01/27