From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: qemu-arm@nongnu.org
Subject: [PATCH v3 33/51] target/arm: Implement SME integer outer product
Date: Mon, 20 Jun 2022 10:52:17 -0700 [thread overview]
Message-ID: <20220620175235.60881-34-richard.henderson@linaro.org> (raw)
In-Reply-To: <20220620175235.60881-1-richard.henderson@linaro.org>
This is SMOPA, SUMOPA, USMOPA_s, UMOPA, for both Int8 and Int16.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper-sme.h | 16 ++++++++
target/arm/sme.decode | 10 +++++
target/arm/sme_helper.c | 82 ++++++++++++++++++++++++++++++++++++++
target/arm/translate-sme.c | 14 +++++++
4 files changed, 122 insertions(+)
diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h
index ecc957be14..31562551ee 100644
--- a/target/arm/helper-sme.h
+++ b/target/arm/helper-sme.h
@@ -128,3 +128,19 @@ DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(sme_bfmopa, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme_umopa_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme_sumopa_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme_usmopa_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme_smopa_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme_umopa_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme_sumopa_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme_usmopa_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sme.decode b/target/arm/sme.decode
index e8d27fd8a0..628804e37a 100644
--- a/target/arm/sme.decode
+++ b/target/arm/sme.decode
@@ -76,3 +76,13 @@ FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64
BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32
FMOPA_h 10000001 101 ..... ... ... ..... . 00 .. @op_32
+
+SMOPA_s 1010000 0 10 0 ..... ... ... ..... . 00 .. @op_32
+SUMOPA_s 1010000 0 10 1 ..... ... ... ..... . 00 .. @op_32
+USMOPA_s 1010000 1 10 0 ..... ... ... ..... . 00 .. @op_32
+UMOPA_s 1010000 1 10 1 ..... ... ... ..... . 00 .. @op_32
+
+SMOPA_d 1010000 0 11 0 ..... ... ... ..... . 0 ... @op_64
+SUMOPA_d 1010000 0 11 1 ..... ... ... ..... . 0 ... @op_64
+USMOPA_d 1010000 1 11 0 ..... ... ... ..... . 0 ... @op_64
+UMOPA_d 1010000 1 11 1 ..... ... ... ..... . 0 ... @op_64
diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c
index 6863a204d4..f1c7e6ae56 100644
--- a/target/arm/sme_helper.c
+++ b/target/arm/sme_helper.c
@@ -1090,3 +1090,85 @@ void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn,
} while (row & 15);
}
}
+
+typedef uint64_t IMOPFn(uint64_t, uint64_t, uint64_t, uint8_t, bool);
+
+static inline void do_imopa(uint64_t *za, uint64_t *zn, uint64_t *zm,
+ uint8_t *pn, uint8_t *pm,
+ uint32_t desc, IMOPFn *fn)
+{
+ intptr_t row, col, oprsz = simd_oprsz(desc) / 8;
+ bool neg = simd_data(desc);
+
+ for (row = 0; row < oprsz; ++row) {
+ uint8_t pa = pn[H1(row)];
+ uint64_t *za_row = &za[row * sizeof(ARMVectorReg)];
+ uint64_t n = zn[row];
+
+ for (col = 0; col < oprsz; ++col) {
+ uint8_t pb = pm[H1(col)];
+ uint64_t *a = &za_row[col];
+
+ *a = fn(n, zm[col], *a, pa & pb, neg);
+ }
+ }
+}
+
+#define DEF_IMOP_32(NAME, NTYPE, MTYPE) \
+static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \
+{ \
+ uint32_t sum0 = 0, sum1 = 0; \
+ /* Apply P to N as a mask, making the inactive elements 0. */ \
+ n &= expand_pred_b(p); \
+ sum0 += (NTYPE)(n >> 0) * (MTYPE)(m >> 0); \
+ sum0 += (NTYPE)(n >> 8) * (MTYPE)(m >> 8); \
+ sum0 += (NTYPE)(n >> 16) * (MTYPE)(m >> 16); \
+ sum0 += (NTYPE)(n >> 24) * (MTYPE)(m >> 24); \
+ sum1 += (NTYPE)(n >> 32) * (MTYPE)(m >> 32); \
+ sum1 += (NTYPE)(n >> 40) * (MTYPE)(m >> 40); \
+ sum1 += (NTYPE)(n >> 48) * (MTYPE)(m >> 48); \
+ sum1 += (NTYPE)(n >> 56) * (MTYPE)(m >> 56); \
+ if (neg) { \
+ sum0 = (uint32_t)a - sum0, sum1 = (uint32_t)(a >> 32) - sum1; \
+ } else { \
+ sum0 = (uint32_t)a + sum0, sum1 = (uint32_t)(a >> 32) + sum1; \
+ } \
+ return ((uint64_t)sum1 << 32) | sum0; \
+}
+
+#define DEF_IMOP_64(NAME, NTYPE, MTYPE) \
+static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \
+{ \
+ uint64_t sum = 0; \
+ /* Apply P to N as a mask, making the inactive elements 0. */ \
+ n &= expand_pred_h(p); \
+ sum += (NTYPE)(n >> 0) * (MTYPE)(m >> 0); \
+ sum += (NTYPE)(n >> 16) * (MTYPE)(m >> 16); \
+ sum += (NTYPE)(n >> 32) * (MTYPE)(m >> 32); \
+ sum += (NTYPE)(n >> 48) * (MTYPE)(m >> 48); \
+ return neg ? a - sum : a + sum; \
+}
+
+DEF_IMOP_32(smopa_s, int8_t, int8_t)
+DEF_IMOP_32(umopa_s, uint8_t, uint8_t)
+DEF_IMOP_32(sumopa_s, int8_t, uint8_t)
+DEF_IMOP_32(usmopa_s, uint8_t, int8_t)
+
+DEF_IMOP_64(smopa_d, int16_t, int16_t)
+DEF_IMOP_64(umopa_d, uint16_t, uint16_t)
+DEF_IMOP_64(sumopa_d, int16_t, uint16_t)
+DEF_IMOP_64(usmopa_d, uint16_t, int16_t)
+
+#define DEF_IMOPH(NAME) \
+ void HELPER(sme_##NAME)(void *vza, void *vzn, void *vzm, void *vpn, \
+ void *vpm, uint32_t desc) \
+ { do_imopa(vza, vzn, vzm, vpn, vpm, desc, NAME); }
+
+DEF_IMOPH(smopa_s)
+DEF_IMOPH(umopa_s)
+DEF_IMOPH(sumopa_s)
+DEF_IMOPH(usmopa_s)
+DEF_IMOPH(smopa_d)
+DEF_IMOPH(umopa_d)
+DEF_IMOPH(sumopa_d)
+DEF_IMOPH(usmopa_d)
diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c
index 847f2274b1..4aa0aff25c 100644
--- a/target/arm/translate-sme.c
+++ b/target/arm/translate-sme.c
@@ -337,3 +337,17 @@ TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst,
/* TODO: FEAT_EBF16 */
TRANS_FEAT(BFMOPA, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_bfmopa)
+
+TRANS_FEAT(SMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_smopa_s)
+TRANS_FEAT(UMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_umopa_s)
+TRANS_FEAT(SUMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_sumopa_s)
+TRANS_FEAT(USMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_usmopa_s)
+
+TRANS_FEAT(SMOPA_d, aa64_sme_i16i64, do_outprod,
+ a, MO_64, gen_helper_sme_smopa_d)
+TRANS_FEAT(UMOPA_d, aa64_sme_i16i64, do_outprod,
+ a, MO_64, gen_helper_sme_umopa_d)
+TRANS_FEAT(SUMOPA_d, aa64_sme_i16i64, do_outprod,
+ a, MO_64, gen_helper_sme_sumopa_d)
+TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod,
+ a, MO_64, gen_helper_sme_usmopa_d)
--
2.34.1
next prev parent reply other threads:[~2022-06-20 18:46 UTC|newest]
Thread overview: 81+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-20 17:51 [PATCH v3 00/51] target/arm: Scalable Matrix Extension Richard Henderson
2022-06-20 17:51 ` [PATCH v3 01/51] target/arm: Implement TPIDR2_EL0 Richard Henderson
2022-06-20 17:51 ` [PATCH v3 02/51] target/arm: Add SMEEXC_EL to TB flags Richard Henderson
2022-06-20 17:51 ` [PATCH v3 03/51] target/arm: Add syn_smetrap Richard Henderson
2022-06-20 17:51 ` [PATCH v3 04/51] target/arm: Add ARM_CP_SME Richard Henderson
2022-06-20 17:51 ` [PATCH v3 05/51] target/arm: Add SVCR Richard Henderson
2022-06-20 17:51 ` [PATCH v3 06/51] target/arm: Add SMCR_ELx Richard Henderson
2022-06-20 17:51 ` [PATCH v3 07/51] target/arm: Add SMIDR_EL1, SMPRI_EL1, SMPRIMAP_EL2 Richard Henderson
2022-06-20 17:51 ` [PATCH v3 08/51] target/arm: Add PSTATE.{SM,ZA} to TB flags Richard Henderson
2022-06-20 17:51 ` [PATCH v3 09/51] target/arm: Add the SME ZA storage to CPUARMState Richard Henderson
2022-06-21 20:24 ` Peter Maydell
2022-06-20 17:51 ` [PATCH v3 10/51] target/arm: Implement SMSTART, SMSTOP Richard Henderson
2022-06-20 17:51 ` [PATCH v3 11/51] target/arm: Move error for sve%d property to arm_cpu_sve_finalize Richard Henderson
2022-06-20 17:51 ` [PATCH v3 12/51] target/arm: Create ARMVQMap Richard Henderson
2022-06-20 17:51 ` [PATCH v3 13/51] target/arm: Generalize cpu_arm_{get,set}_vq Richard Henderson
2022-06-20 17:51 ` [PATCH v3 14/51] target/arm: Generalize cpu_arm_{get, set}_default_vec_len Richard Henderson
2022-06-20 17:51 ` [PATCH v3 15/51] target/arm: Move arm_cpu_*_finalize to internals.h Richard Henderson
2022-06-20 17:52 ` [PATCH v3 16/51] target/arm: Unexport aarch64_add_*_properties Richard Henderson
2022-06-20 17:52 ` [PATCH v3 17/51] target/arm: Add cpu properties for SME Richard Henderson
2022-06-21 17:13 ` Peter Maydell
2024-04-12 11:36 ` Peter Maydell
2024-04-12 16:17 ` Richard Henderson
2022-06-20 17:52 ` [PATCH v3 18/51] target/arm: Introduce sve_vqm1_for_el_sm Richard Henderson
2022-06-20 17:52 ` [PATCH v3 19/51] target/arm: Add SVL to TB flags Richard Henderson
2022-06-20 17:52 ` [PATCH v3 20/51] target/arm: Move pred_{full, gvec}_reg_{offset, size} to translate-a64.h Richard Henderson
2022-06-20 17:52 ` [PATCH v3 21/51] target/arm: Add infrastructure for disas_sme Richard Henderson
2022-06-20 17:52 ` [PATCH v3 22/51] target/arm: Trap AdvSIMD usage when Streaming SVE is active Richard Henderson
2022-06-24 15:30 ` Peter Maydell
2022-06-24 20:34 ` Richard Henderson
2022-06-24 21:38 ` Peter Maydell
2022-06-26 3:37 ` Richard Henderson
2022-06-20 17:52 ` [PATCH v3 23/51] target/arm: Implement SME RDSVL, ADDSVL, ADDSPL Richard Henderson
2022-06-21 17:23 ` Peter Maydell
2022-06-22 0:58 ` Richard Henderson
2022-06-23 10:12 ` Peter Maydell
2022-06-20 17:52 ` [PATCH v3 24/51] target/arm: Implement SME ZERO Richard Henderson
2022-06-21 20:07 ` Peter Maydell
2022-06-20 17:52 ` [PATCH v3 25/51] target/arm: Implement SME MOVA Richard Henderson
2022-06-23 11:24 ` Peter Maydell
2022-06-23 14:44 ` Richard Henderson
2022-06-20 17:52 ` [PATCH v3 26/51] target/arm: Implement SME LD1, ST1 Richard Henderson
2022-06-23 11:41 ` Peter Maydell
2022-06-23 20:36 ` Richard Henderson
2022-06-24 10:05 ` Peter Maydell
2022-06-20 17:52 ` [PATCH v3 27/51] target/arm: Export unpredicated ld/st from translate-sve.c Richard Henderson
2022-06-23 11:42 ` Peter Maydell
2022-06-20 17:52 ` [PATCH v3 28/51] target/arm: Implement SME LDR, STR Richard Henderson
2022-06-23 11:46 ` Peter Maydell
2022-06-20 17:52 ` [PATCH v3 29/51] target/arm: Implement SME ADDHA, ADDVA Richard Henderson
2022-06-23 12:04 ` Peter Maydell
2022-06-20 17:52 ` [PATCH v3 30/51] target/arm: Implement FMOPA, FMOPS (non-widening) Richard Henderson
2022-06-24 12:31 ` Peter Maydell
2022-06-24 14:16 ` Richard Henderson
2022-06-20 17:52 ` [PATCH v3 31/51] target/arm: Implement BFMOPA, BFMOPS Richard Henderson
2022-06-20 17:52 ` [PATCH v3 32/51] target/arm: Implement FMOPA, FMOPS (widening) Richard Henderson
2022-06-20 17:52 ` Richard Henderson [this message]
2022-06-24 12:39 ` [PATCH v3 33/51] target/arm: Implement SME integer outer product Peter Maydell
2022-06-20 17:52 ` [PATCH v3 34/51] target/arm: Implement PSEL Richard Henderson
2022-06-24 12:51 ` Peter Maydell
2022-06-20 17:52 ` [PATCH v3 35/51] target/arm: Implement REVD Richard Henderson
2022-06-24 12:54 ` Peter Maydell
2022-06-20 17:52 ` [PATCH v3 36/51] target/arm: Implement SCLAMP, UCLAMP Richard Henderson
2022-06-24 13:00 ` Peter Maydell
2022-06-20 17:52 ` [PATCH v3 37/51] target/arm: Reset streaming sve state on exception boundaries Richard Henderson
2022-06-24 13:02 ` Peter Maydell
2022-06-20 17:52 ` [PATCH v3 38/51] target/arm: Enable SME for -cpu max Richard Henderson
2022-06-24 13:03 ` Peter Maydell
2022-06-20 17:52 ` [PATCH v3 39/51] linux-user/aarch64: Clear tpidr2_el0 if CLONE_SETTLS Richard Henderson
2022-06-20 17:52 ` [PATCH v3 40/51] linux-user/aarch64: Reset PSTATE.SM on syscalls Richard Henderson
2022-06-20 17:52 ` [PATCH v3 41/51] linux-user/aarch64: Add SM bit to SVE signal context Richard Henderson
2022-06-20 17:52 ` [PATCH v3 42/51] linux-user/aarch64: Tidy target_restore_sigframe error return Richard Henderson
2022-06-20 17:52 ` [PATCH v3 43/51] linux-user/aarch64: Do not allow duplicate or short sve records Richard Henderson
2022-06-20 17:52 ` [PATCH v3 44/51] linux-user/aarch64: Verify extra record lock succeeded Richard Henderson
2022-06-20 17:52 ` [PATCH v3 45/51] linux-user/aarch64: Move sve record checks into restore Richard Henderson
2022-06-20 17:52 ` [PATCH v3 46/51] linux-user/aarch64: Implement SME signal handling Richard Henderson
2022-06-20 17:52 ` [PATCH v3 47/51] linux-user: Rename sve prctls Richard Henderson
2022-06-20 17:52 ` [PATCH v3 48/51] linux-user/aarch64: Implement PR_SME_GET_VL, PR_SME_SET_VL Richard Henderson
2022-06-20 17:52 ` [PATCH v3 49/51] target/arm: Only set ZEN in reset if SVE present Richard Henderson
2022-06-20 17:52 ` [PATCH v3 50/51] target/arm: Enable SME for user-only Richard Henderson
2022-06-20 17:52 ` [PATCH v3 51/51] linux-user/aarch64: Add SME related hwcap entries Richard Henderson
2022-06-24 15:02 ` [PATCH v3 00/51] target/arm: Scalable Matrix Extension Peter Maydell
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220620175235.60881-34-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--cc=qemu-arm@nongnu.org \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.