[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v6 04/13] tcg: Implement tcg_gen_{h,w}swap_{i32,i64}
From: |
David Hildenbrand |
Subject: |
[PATCH v6 04/13] tcg: Implement tcg_gen_{h,w}swap_{i32,i64} |
Date: |
Thu, 28 Apr 2022 11:46:59 +0200 |
From: Richard Henderson <richard.henderson@linaro.org>
Swap half-words (16-bit) and words (32-bit) within a larger value.
Mirrors functions of the same names within include/qemu/bitops.h.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: David Miller <dmiller423@gmail.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
include/tcg/tcg-op.h | 6 ++++++
tcg/tcg-op.c | 30 ++++++++++++++++++++++++++++++
2 files changed, 36 insertions(+)
diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h
index caa0a63612..b09b8b4a05 100644
--- a/include/tcg/tcg-op.h
+++ b/include/tcg/tcg-op.h
@@ -332,6 +332,7 @@ void tcg_gen_ext8u_i32(TCGv_i32 ret, TCGv_i32 arg);
void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg);
void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg, int flags);
void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg);
+void tcg_gen_hswap_i32(TCGv_i32 ret, TCGv_i32 arg);
void tcg_gen_smin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
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);
@@ -531,6 +532,8 @@ void tcg_gen_ext32u_i64(TCGv_i64 ret, TCGv_i64 arg);
void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg, int flags);
void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg, int flags);
void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_hswap_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_wswap_i64(TCGv_i64 ret, TCGv_i64 arg);
void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
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);
@@ -1077,6 +1080,8 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg
offset, TCGType t);
#define tcg_gen_bswap32_tl tcg_gen_bswap32_i64
#define tcg_gen_bswap64_tl tcg_gen_bswap64_i64
#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_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
@@ -1192,6 +1197,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg
offset, TCGType t);
#define tcg_gen_bswap16_tl tcg_gen_bswap16_i32
#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_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 5d48537927..019fab00cc 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -1056,6 +1056,12 @@ void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg)
}
}
+void tcg_gen_hswap_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+ /* Swapping 2 16-bit elements is a rotate. */
+ tcg_gen_rotli_i32(ret, arg, 16);
+}
+
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);
@@ -1792,6 +1798,30 @@ void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg)
}
}
+void tcg_gen_hswap_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+ uint64_t m = 0x0000ffff0000ffffull;
+ TCGv_i64 t0 = tcg_temp_new_i64();
+ TCGv_i64 t1 = tcg_temp_new_i64();
+
+ /* See include/qemu/bitops.h, hswap64. */
+ tcg_gen_rotli_i64(t1, arg, 32);
+ tcg_gen_andi_i64(t0, t1, m);
+ tcg_gen_shli_i64(t0, t0, 16);
+ tcg_gen_shri_i64(t1, t1, 16);
+ tcg_gen_andi_i64(t1, t1, m);
+ tcg_gen_or_i64(ret, t0, t1);
+
+ tcg_temp_free_i64(t0);
+ tcg_temp_free_i64(t1);
+}
+
+void tcg_gen_wswap_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+ /* Swapping 2 32-bit elements is a rotate. */
+ tcg_gen_rotli_i64(ret, arg, 32);
+}
+
void tcg_gen_not_i64(TCGv_i64 ret, TCGv_i64 arg)
{
if (TCG_TARGET_REG_BITS == 32) {
--
2.35.1
- [PATCH v6 00/13] s390x/tcg: Implement Vector-Enhancements Facility 2, David Hildenbrand, 2022/04/28
- [PATCH v6 04/13] tcg: Implement tcg_gen_{h,w}swap_{i32,i64},
David Hildenbrand <=
- [PATCH v6 07/13] target/s390x: vxeh2: Update for changes to vector shifts, David Hildenbrand, 2022/04/28
- [PATCH v6 02/13] s390x/cpu_models: drop "msa5" from the TCG "max" model, David Hildenbrand, 2022/04/28
- [PATCH v6 01/13] target/s390x: Fix writeback to v1 in helper_vstl, David Hildenbrand, 2022/04/28
- [PATCH v6 05/13] target/s390x: vxeh2: vector convert short/32b, David Hildenbrand, 2022/04/28
- [PATCH v6 06/13] target/s390x: vxeh2: vector string search, David Hildenbrand, 2022/04/28
- [PATCH v6 03/13] s390x/cpu_models: make "max" match the unmodified "qemu" CPU model under TCG, David Hildenbrand, 2022/04/28
- [PATCH v6 12/13] target/s390x: add S390_FEAT_VECTOR_ENH2 to qemu CPU model, David Hildenbrand, 2022/04/28
- [PATCH v6 08/13] target/s390x: vxeh2: vector shift double by bit, David Hildenbrand, 2022/04/28
- [PATCH v6 09/13] target/s390x: vxeh2: vector {load, store} elements reversed, David Hildenbrand, 2022/04/28
- [PATCH v6 10/13] target/s390x: vxeh2: vector {load, store} byte reversed elements, David Hildenbrand, 2022/04/28