Add generic expanders for reversing bits within a word.
Reviewed-by: Philippe Mathieu-Daudé <[email protected]>
Signed-off-by: Richard Henderson <[email protected]>
---
include/tcg/tcg-op-common.h | 5 +++
include/tcg/tcg-op.h | 7 ++++
tcg/tcg-op.c | 76 +++++++++++++++++++++++++++++++++++++
3 files changed, 88 insertions(+)
diff --git a/include/tcg/tcg-op-common.h b/include/tcg/tcg-op-common.h
index 1fe342db0d..f7b6aadb50 100644
--- a/include/tcg/tcg-op-common.h
+++ b/include/tcg/tcg-op-common.h
@@ -164,6 +164,8 @@ void tcg_gen_smax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32
arg2);
void tcg_gen_umin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
void tcg_gen_umax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
void tcg_gen_abs_i32(TCGv_i32, TCGv_i32);
+void tcg_gen_revbit8_i32(TCGv_i32 ret, TCGv_i32 arg);
+void tcg_gen_revbit32_i32(TCGv_i32 ret, TCGv_i32 arg);
/* Replicate a value of size @vece from @in to all the lanes in @out */
void tcg_gen_dup_i32(unsigned vece, TCGv_i32 out, TCGv_i32 in);
@@ -275,6 +277,9 @@ void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64
arg2);
void tcg_gen_umin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
void tcg_gen_umax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
void tcg_gen_abs_i64(TCGv_i64, TCGv_i64);
+void tcg_gen_revbit8_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_revbit32_i64(TCGv_i64 ret, TCGv_i64 arg, int flags);
+void tcg_gen_revbit64_i64(TCGv_i64 ret, TCGv_i64 arg);
/* Replicate a value of size @vece from @in to all the lanes in @out */
void tcg_gen_dup_i64(unsigned vece, TCGv_i64 out, TCGv_i64 in);
diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h
index 96a5af1a29..568b78fe81 100644
--- a/include/tcg/tcg-op.h
+++ b/include/tcg/tcg-op.h
@@ -115,6 +115,10 @@ typedef TCGv_i64 TCGv;
#define tcg_gen_bswap_tl tcg_gen_bswap64_i64
#define tcg_gen_hswap_tl tcg_gen_hswap_i64
#define tcg_gen_wswap_tl tcg_gen_wswap_i64
+#define tcg_gen_revbit8_tl tcg_gen_revbit8_i64
+#define tcg_gen_revbit32_tl tcg_gen_revbit32_i64
+#define tcg_gen_revbit64_tl tcg_gen_revbit64_i64
+#define tcg_gen_revbit_tl tcg_gen_revbit64_i64
#define tcg_gen_concat_tl_i64 tcg_gen_concat32_i64
#define tcg_gen_extr_i64_tl tcg_gen_extr32_i64
#define tcg_gen_andc_tl tcg_gen_andc_i64
@@ -234,6 +238,9 @@ typedef TCGv_i64 TCGv;
#define tcg_gen_bswap32_tl(D, S, F) tcg_gen_bswap32_i32(D, S)
#define tcg_gen_bswap_tl tcg_gen_bswap32_i32
#define tcg_gen_hswap_tl tcg_gen_hswap_i32
+#define tcg_gen_revbit8_tl tcg_gen_revbit8_i32
+#define tcg_gen_revbit32_tl(D, S, F) tcg_gen_revbit32_i32(D, S)
+#define tcg_gen_revbit_tl tcg_gen_revbit32_i32
#define tcg_gen_concat_tl_i64 tcg_gen_concat_i32_i64
#define tcg_gen_extr_i64_tl tcg_gen_extr_i64_i32
#define tcg_gen_andc_tl tcg_gen_andc_i32
diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index bbcb510c76..3d28280785 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -1160,6 +1160,45 @@ void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg)
tcg_gen_extract_i32(ret, arg, 0, 16);
}
+/*
+ * Internal helper for bit and byte reversal.
+ * Given a repeating matched block of 1's and 0's, swap the bits within
+ * those two blocks. E.g. mask=00ff00ff, shift the input bits left and
+ * right 8 bits.
+ */
+static void gen_bitswap_i32(TCGv_i32 ret, TCGv_i32 arg, uint32_t mask)
+{
+ TCGv_i32 t0 = tcg_temp_ebb_new_i32();
+ TCGv_i32 t1 = tcg_temp_ebb_new_i32();
+ int sh = cto32(mask);
+
+ tcg_gen_andi_i32(t0, arg, mask);
+ tcg_gen_shri_i32(t1, arg, sh);
+ tcg_gen_shli_i32(t0, t0, sh);
+ tcg_gen_andi_i32(t1, t1, mask);
+ tcg_gen_or_i32(ret, t0, t1);
+
+ tcg_temp_free_i32(t0);
+ tcg_temp_free_i32(t1);
+}
+
+/* Similarly for 64-bit operands. */
+static void gen_bitswap_i64(TCGv_i64 ret, TCGv_i64 arg, uint64_t mask)
+{
+ TCGv_i64 t0 = tcg_temp_ebb_new_i64();
+ TCGv_i64 t1 = tcg_temp_ebb_new_i64();
+ int sh = cto64(mask);
+
+ tcg_gen_andi_i64(t0, arg, mask);
+ tcg_gen_shri_i64(t1, arg, sh);
+ tcg_gen_shli_i64(t0, t0, sh);
+ tcg_gen_andi_i64(t1, t1, mask);
+ tcg_gen_or_i64(ret, t0, t1);
+
+ tcg_temp_free_i64(t0);
+ tcg_temp_free_i64(t1);
+}
+
/*
* bswap16_i32: 16-bit byte swap on the low bits of a 32-bit value.
*
@@ -1244,6 +1283,19 @@ void tcg_gen_hswap_i32(TCGv_i32 ret, TCGv_i32 arg)
tcg_gen_rotli_i32(ret, arg, 16);
}
+void tcg_gen_revbit8_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+ gen_bitswap_i32(ret, arg, 0x55555555u);
+ gen_bitswap_i32(ret, ret, 0x33333333u);
+ gen_bitswap_i32(ret, ret, 0x0f0f0f0fu);
+}
+
+void tcg_gen_revbit32_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+ tcg_gen_revbit8_i32(ret, arg);
+ tcg_gen_bswap32_i32(ret, ret);
+}
+
void tcg_gen_smin_i32(TCGv_i32 ret, TCGv_i32 a, TCGv_i32 b)
{
tcg_gen_movcond_i32(TCG_COND_LT, ret, a, b, a, b);
@@ -1869,6 +1921,30 @@ void tcg_gen_wswap_i64(TCGv_i64 ret, TCGv_i64 arg)
tcg_gen_rotli_i64(ret, arg, 32);
}
+void tcg_gen_revbit32_i64(TCGv_i64 ret, TCGv_i64 arg, int flags)
+{
+ /* Only one extension flag may be present. */
+ tcg_debug_assert(!(flags & TCG_BSWAP_OS) || !(flags & TCG_BSWAP_OZ));
+
+ gen_bitswap_i64(ret, arg, 0x55555555ull);
+ gen_bitswap_i64(ret, ret, 0x33333333ull);
+ gen_bitswap_i64(ret, ret, 0x0f0f0f0full);
+ tcg_gen_bswap32_i64(ret, ret, flags | TCG_BSWAP_IZ);
+}
+
+void tcg_gen_revbit8_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+ gen_bitswap_i64(ret, arg, 0x5555555555555555ull);
+ gen_bitswap_i64(ret, ret, 0x3333333333333333ull);
+ gen_bitswap_i64(ret, ret, 0x0f0f0f0f0f0f0f0full);
+}
+
+void tcg_gen_revbit64_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+ tcg_gen_revbit8_i64(ret, arg);
+ tcg_gen_bswap64_i64(ret, ret);
+}
+
void tcg_gen_not_i64(TCGv_i64 ret, TCGv_i64 arg)
{
if (tcg_op_supported(INDEX_op_not, TCG_TYPE_I64, 0)) {
--
2.43.0