*/
#include "qemu/osdep.h"
-#include "qemu-common.h"
-#include "tcg.h"
-#include "tcg-op.h"
-#include "tcg-op-gvec.h"
-#include "tcg-gvec-desc.h"
+#include "tcg/tcg.h"
+#include "tcg/tcg-op.h"
+#include "tcg/tcg-op-gvec.h"
+#include "qemu/main-loop.h"
+#include "tcg/tcg-gvec-desc.h"
#define MAX_UNROLL 4
tcg_temp_free_i32(desc);
}
+/* Generate a call to a gvec-style helper with five vector operands
+ and an extra pointer operand. */
+void tcg_gen_gvec_5_ptr(uint32_t dofs, uint32_t aofs, uint32_t bofs,
+ uint32_t cofs, uint32_t eofs, TCGv_ptr ptr,
+ uint32_t oprsz, uint32_t maxsz, int32_t data,
+ gen_helper_gvec_5_ptr *fn)
+{
+ TCGv_ptr a0, a1, a2, a3, a4;
+ TCGv_i32 desc = tcg_const_i32(simd_desc(oprsz, maxsz, data));
+
+ a0 = tcg_temp_new_ptr();
+ a1 = tcg_temp_new_ptr();
+ a2 = tcg_temp_new_ptr();
+ a3 = tcg_temp_new_ptr();
+ a4 = tcg_temp_new_ptr();
+
+ tcg_gen_addi_ptr(a0, cpu_env, dofs);
+ tcg_gen_addi_ptr(a1, cpu_env, aofs);
+ tcg_gen_addi_ptr(a2, cpu_env, bofs);
+ tcg_gen_addi_ptr(a3, cpu_env, cofs);
+ tcg_gen_addi_ptr(a4, cpu_env, eofs);
+
+ fn(a0, a1, a2, a3, a4, ptr, desc);
+
+ tcg_temp_free_ptr(a0);
+ tcg_temp_free_ptr(a1);
+ tcg_temp_free_ptr(a2);
+ tcg_temp_free_ptr(a3);
+ tcg_temp_free_ptr(a4);
+ tcg_temp_free_i32(desc);
+}
+
/* Return true if we want to implement something of OPRSZ bytes
in units of LNSZ. This limits the expansion of inline code. */
static inline bool check_size_impl(uint32_t oprsz, uint32_t lnsz)
void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
uint32_t oprsz, uint32_t maxsz)
{
+ check_size_align(oprsz, maxsz, dofs);
if (vece <= MO_64) {
- TCGType type = choose_vector_type(0, vece, oprsz, 0);
+ TCGType type = choose_vector_type(NULL, vece, oprsz, 0);
if (type != 0) {
TCGv_vec t_vec = tcg_temp_new_vec(type);
tcg_gen_dup_mem_vec(vece, t_vec, cpu_env, aofs);
do_dup_store(type, dofs, oprsz, maxsz, t_vec);
tcg_temp_free_vec(t_vec);
- return;
- }
- }
- if (vece <= MO_32) {
- TCGv_i32 in = tcg_temp_new_i32();
- switch (vece) {
- case MO_8:
- tcg_gen_ld8u_i32(in, cpu_env, aofs);
- break;
- case MO_16:
- tcg_gen_ld16u_i32(in, cpu_env, aofs);
- break;
- case MO_32:
- tcg_gen_ld_i32(in, cpu_env, aofs);
- break;
+ } else if (vece <= MO_32) {
+ TCGv_i32 in = tcg_temp_new_i32();
+ switch (vece) {
+ case MO_8:
+ tcg_gen_ld8u_i32(in, cpu_env, aofs);
+ break;
+ case MO_16:
+ tcg_gen_ld16u_i32(in, cpu_env, aofs);
+ break;
+ default:
+ tcg_gen_ld_i32(in, cpu_env, aofs);
+ break;
+ }
+ do_dup(vece, dofs, oprsz, maxsz, in, NULL, 0);
+ tcg_temp_free_i32(in);
+ } else {
+ TCGv_i64 in = tcg_temp_new_i64();
+ tcg_gen_ld_i64(in, cpu_env, aofs);
+ do_dup(vece, dofs, oprsz, maxsz, NULL, in, 0);
+ tcg_temp_free_i64(in);
}
- tcg_gen_gvec_dup_i32(vece, dofs, oprsz, maxsz, in);
- tcg_temp_free_i32(in);
- } else if (vece == MO_64) {
- TCGv_i64 in = tcg_temp_new_i64();
- tcg_gen_ld_i64(in, cpu_env, aofs);
- tcg_gen_gvec_dup_i64(MO_64, dofs, oprsz, maxsz, in);
- tcg_temp_free_i64(in);
} else {
/* 128-bit duplicate. */
/* ??? Dup to 256-bit vector. */
tcg_temp_free_i64(in0);
tcg_temp_free_i64(in1);
}
+ if (oprsz < maxsz) {
+ expand_clr(dofs + oprsz, maxsz - oprsz);
+ }
}
}
expand_clr(dofs + oprsz, maxsz - oprsz);
}
}
+
+static void tcg_gen_bitsel_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b, TCGv_i64 c)
+{
+ TCGv_i64 t = tcg_temp_new_i64();
+
+ tcg_gen_and_i64(t, b, a);
+ tcg_gen_andc_i64(d, c, a);
+ tcg_gen_or_i64(d, d, t);
+ tcg_temp_free_i64(t);
+}
+
+void tcg_gen_gvec_bitsel(unsigned vece, uint32_t dofs, uint32_t aofs,
+ uint32_t bofs, uint32_t cofs,
+ uint32_t oprsz, uint32_t maxsz)
+{
+ static const GVecGen4 g = {
+ .fni8 = tcg_gen_bitsel_i64,
+ .fniv = tcg_gen_bitsel_vec,
+ .fno = gen_helper_gvec_bitsel,
+ };
+
+ tcg_gen_gvec_4(dofs, aofs, bofs, cofs, oprsz, maxsz, &g);
+}