[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PULL 53/55] target/arm: Export bfdotadd from vec_helper.c
From: |
Peter Maydell |
Subject: |
[PULL 53/55] target/arm: Export bfdotadd from vec_helper.c |
Date: |
Thu, 9 Jun 2022 10:05:35 +0100 |
From: Richard Henderson <richard.henderson@linaro.org>
We will need this over in sme_helper.c.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20220607203306.657998-19-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
target/arm/vec_internal.h | 13 +++++++++++++
target/arm/vec_helper.c | 2 +-
2 files changed, 14 insertions(+), 1 deletion(-)
diff --git a/target/arm/vec_internal.h b/target/arm/vec_internal.h
index 1d527fadac1..1f4ed80ff76 100644
--- a/target/arm/vec_internal.h
+++ b/target/arm/vec_internal.h
@@ -230,4 +230,17 @@ uint64_t pmull_h(uint64_t op1, uint64_t op2);
*/
uint64_t pmull_w(uint64_t op1, uint64_t op2);
+/**
+ * bfdotadd:
+ * @sum: addend
+ * @e1, @e2: multiplicand vectors
+ *
+ * BFloat16 2-way dot product of @e1 & @e2, accumulating with @sum.
+ * The @e1 and @e2 operands correspond to the 32-bit source vector
+ * slots and contain two Bfloat16 values each.
+ *
+ * Corresponds to the ARM pseudocode function BFDotAdd.
+ */
+float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2);
+
#endif /* TARGET_ARM_VEC_INTERNAL_H */
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 26c373e522f..9a9c034e36f 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -2557,7 +2557,7 @@ DO_MMLA_B(gvec_usmmla_b, do_usmmla_b)
* BFloat16 Dot Product
*/
-static float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2)
+float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2)
{
/* FPCR is ignored for BFDOT and BFMMLA. */
float_status bf_status = {
--
2.25.1
- [PULL 30/55] target/arm: Move regime_is_user to ptw.c, (continued)
- [PULL 30/55] target/arm: Move regime_is_user to ptw.c, Peter Maydell, 2022/06/09
- [PULL 35/55] target/arm: Pass CPUARMState to arm_ld[lq]_ptw, Peter Maydell, 2022/06/09
- [PULL 33/55] target/arm: Move arm_cpu_get_phys_page_attrs_debug to ptw.c, Peter Maydell, 2022/06/09
- [PULL 26/55] target/arm: Move get_S1prot, get_S2prot to ptw.c, Peter Maydell, 2022/06/09
- [PULL 43/55] target/arm: Hoist arm_is_el2_enabled check in sve_exception_el, Peter Maydell, 2022/06/09
- [PULL 42/55] target/arm: Use el_is_in_host for sve_exception_el, Peter Maydell, 2022/06/09
- [PULL 44/55] target/arm: Do not use aarch64_sve_zcr_get_valid_len in reset, Peter Maydell, 2022/06/09
- [PULL 46/55] target/arm: Use uint32_t instead of bitmap for sve vq's, Peter Maydell, 2022/06/09
- [PULL 49/55] target/arm: Export sve contiguous ldst support functions, Peter Maydell, 2022/06/09
- [PULL 51/55] target/arm: Use expand_pred_b in mve_helper.c, Peter Maydell, 2022/06/09
- [PULL 53/55] target/arm: Export bfdotadd from vec_helper.c,
Peter Maydell <=
- [PULL 55/55] target/arm: Add ID_AA64SMFR0_EL1, Peter Maydell, 2022/06/09
- [PULL 54/55] target/arm: Add isar_feature_aa64_sme, Peter Maydell, 2022/06/09
- [PULL 39/55] target/arm: Remove fp checks from sve_exception_el, Peter Maydell, 2022/06/09
- [PULL 45/55] target/arm: Merge aarch64_sve_zcr_get_valid_len into caller, Peter Maydell, 2022/06/09
- [PULL 47/55] target/arm: Rename sve_zcr_len_for_el to sve_vqm1_for_el, Peter Maydell, 2022/06/09
- [PULL 48/55] target/arm: Split out load/store primitives to sve_ldst_internal.h, Peter Maydell, 2022/06/09
- [PULL 52/55] target/arm: Move expand_pred_h to vec_internal.h, Peter Maydell, 2022/06/09
- [PULL 40/55] target/arm: Add el_is_in_host, Peter Maydell, 2022/06/09
- [PULL 37/55] linux-user/aarch64: Introduce sve_vq, Peter Maydell, 2022/06/09
- [PULL 50/55] target/arm: Move expand_pred_b to vec_internal.h, Peter Maydell, 2022/06/09