1. Patchew
  2. QEMU
  3. [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1
  4. View patch

[PATCH v3 51/97] target/arm: Implement SME2 SUNPK, UUNPK

Richard Henderson posted 97 patches 2 months, 1 week ago
Maintainers: Laurent Vivier <laurent@vivier.eu>, Peter Maydell <peter.maydell@linaro.org>
There is a newer version of this series
[PATCH v3 51/97] target/arm: Implement SME2 SUNPK, UUNPK
Posted by Richard Henderson 2 months, 1 week ago 
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 13 ++++++++++++
 target/arm/tcg/sme_helper.c    | 38 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 16 ++++++++++++++
 target/arm/tcg/sme.decode      | 18 ++++++++++++++++
 4 files changed, 85 insertions(+)

diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 792b993695..893b23aa3b 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -241,3 +241,16 @@ DEF_HELPER_FLAGS_3(sme2_sqcvtun_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sme2_sqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sme2_uqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sme2_sqcvtun_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sme2_sunpk2_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sunpk2_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sunpk2_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk2_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk2_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk2_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 906d369d37..a7d282695d 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1730,6 +1730,44 @@ void HELPER(sme2_fcvt_w)(void *vd, void *vs, float_status *fpst, uint32_t desc)
     }
 }
 
+#define UNPK(NAME, SREG, TW, TN, HW, HN)                        \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc)            \
+{                                                               \
+    ARMVectorReg scratch[SREG];                                 \
+    size_t oprsz = simd_oprsz(desc);                            \
+    size_t n = oprsz / sizeof(TW);                              \
+    if ((vs - vd) < 2 * SREG * sizeof(ARMVectorReg)) {          \
+        vs = memcpy(scratch, vs, sizeof(scratch));              \
+    }                                                           \
+    for (size_t r = 0; r < SREG; ++r) {                         \
+        TN *s = vs + r * sizeof(ARMVectorReg);                  \
+        for (size_t i = 0; i < 2; ++i) {                        \
+            TW *d = vd + (2 * r + i) * sizeof(ARMVectorReg);    \
+            for (size_t e = 0; e < n; ++e) {                    \
+                d[HW(e)] = s[i * n + HN(e)];                    \
+            }                                                   \
+        }                                                       \
+    }                                                           \
+}
+
+UNPK(sme2_sunpk2_bh, 1, int16_t, int8_t, H2, H1)
+UNPK(sme2_sunpk2_hs, 1, int32_t, int16_t, H4, H2)
+UNPK(sme2_sunpk2_sd, 1, int64_t, int32_t, H8, H4)
+
+UNPK(sme2_sunpk4_bh, 2, int16_t, int8_t, H2, H1)
+UNPK(sme2_sunpk4_hs, 2, int32_t, int16_t, H4, H2)
+UNPK(sme2_sunpk4_sd, 2, int64_t, int32_t, H8, H4)
+
+UNPK(sme2_uunpk2_bh, 1, uint16_t, uint8_t, H2, H1)
+UNPK(sme2_uunpk2_hs, 1, uint32_t, uint16_t, H4, H2)
+UNPK(sme2_uunpk2_sd, 1, uint64_t, uint32_t, H8, H4)
+
+UNPK(sme2_uunpk4_bh, 2, uint16_t, uint8_t, H2, H1)
+UNPK(sme2_uunpk4_hs, 2, uint32_t, uint16_t, H4, H2)
+UNPK(sme2_uunpk4_sd, 2, uint64_t, uint32_t, H8, H4)
+
+#undef UNPK
+
 /* Deinterleave and convert. */
 void HELPER(sme2_fcvtl)(void *vd, void *vs, float_status *fpst, uint32_t desc)
 {
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index dd1a6668fb..b45e68750d 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1419,3 +1419,19 @@ TRANS_FEAT(SQCVTUN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_sb)
 TRANS_FEAT(SQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtn_dh)
 TRANS_FEAT(UQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvtn_dh)
 TRANS_FEAT(SQCVTUN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_dh)
+
+TRANS_FEAT(SUNPK_2bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_bh)
+TRANS_FEAT(SUNPK_2hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_hs)
+TRANS_FEAT(SUNPK_2sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_sd)
+
+TRANS_FEAT(SUNPK_4bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_bh)
+TRANS_FEAT(SUNPK_4hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_hs)
+TRANS_FEAT(SUNPK_4sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_sd)
+
+TRANS_FEAT(UUNPK_2bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_bh)
+TRANS_FEAT(UUNPK_2hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_hs)
+TRANS_FEAT(UUNPK_2sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_sd)
+
+TRANS_FEAT(UUNPK_4bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_bh)
+TRANS_FEAT(UUNPK_4hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_hs)
+TRANS_FEAT(UUNPK_4sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_sd)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index e005f6e6ed..38c210cd4f 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -734,6 +734,8 @@ SUB_aaz_d       11000001 111 000010 .. 111 ...00 11 ...     @az_4x4_o3
                 &zz_n n=2 zd=%zd_ax2 zn=%zn_ax2
 @zz_4x4         ........ ... ..... ...... .... . .....      \
                 &zz_n n=4 zd=%zd_ax4 zn=%zn_ax4
+@zz_4x2_n1      ........ ... ..... ...... .... . .....      \
+                &zz_n n=1 zd=%zd_ax4 zn=%zn_ax2
 
 BFCVT           11000001 011 00000 111000 ....0 .....       @zz_1x2
 BFCVTN          11000001 011 00000 111000 ....1 .....       @zz_1x2
@@ -782,3 +784,19 @@ SQCVTUN_sb      11000001 011 10011 111000 ...10 .....       @zz_1x4
 SQCVTN_dh       11000001 101 10011 111000 ...10 .....       @zz_1x4
 UQCVTN_dh       11000001 101 10011 111000 ...11 .....       @zz_1x4
 SQCVTUN_dh      11000001 111 10011 111000 ...10 .....       @zz_1x4
+
+SUNPK_2bh       11000001 011 00101 111000 ..... ....0       @zz_2x1
+SUNPK_2hs       11000001 101 00101 111000 ..... ....0       @zz_2x1
+SUNPK_2sd       11000001 111 00101 111000 ..... ....0       @zz_2x1
+
+UUNPK_2bh       11000001 011 00101 111000 ..... ....1       @zz_2x1
+UUNPK_2hs       11000001 101 00101 111000 ..... ....1       @zz_2x1
+UUNPK_2sd       11000001 111 00101 111000 ..... ....1       @zz_2x1
+
+SUNPK_4bh       11000001 011 10101 111000 ....0 ...00       @zz_4x2_n1
+SUNPK_4hs       11000001 101 10101 111000 ....0 ...00       @zz_4x2_n1
+SUNPK_4sd       11000001 111 10101 111000 ....0 ...00       @zz_4x2_n1
+
+UUNPK_4bh       11000001 011 10101 111000 ....0 ...01       @zz_4x2_n1
+UUNPK_4hs       11000001 101 10101 111000 ....0 ...01       @zz_4x2_n1
+UUNPK_4sd       11000001 111 10101 111000 ....0 ...01       @zz_4x2_n1
-- 
2.43.0
Re: [PATCH v3 51/97] target/arm: Implement SME2 SUNPK, UUNPK
Posted by Peter Maydell 2 months, 1 week ago 
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---


> +#define UNPK(NAME, SREG, TW, TN, HW, HN)                        \
> +void HELPER(NAME)(void *vd, void *vs, uint32_t desc)            \
> +{                                                               \
> +    ARMVectorReg scratch[SREG];                                 \
> +    size_t oprsz = simd_oprsz(desc);                            \
> +    size_t n = oprsz / sizeof(TW);                              \
> +    if ((vs - vd) < 2 * SREG * sizeof(ARMVectorReg)) {          \
> +        vs = memcpy(scratch, vs, sizeof(scratch));              \
> +    }                                                           \
> +    for (size_t r = 0; r < SREG; ++r) {                         \
> +        TN *s = vs + r * sizeof(ARMVectorReg);                  \
> +        for (size_t i = 0; i < 2; ++i) {                        \
> +            TW *d = vd + (2 * r + i) * sizeof(ARMVectorReg);    \
> +            for (size_t e = 0; e < n; ++e) {                    \
> +                d[HW(e)] = s[i * n + HN(e)];                    \
> +            }                                                   \
> +        }                                                       \
> +    }                                                           \
> +}

Similar remarks about the "when do we need to copy" check
and the H macros as patch 49, but otherwise

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>

thanks
-- PMM

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.