Commit 908c7a23d5 for qemu.org
commit 908c7a23d5984e94934cdc7a29ccfdf404ca8f42
Author: Richard Henderson <richard.henderson@linaro.org>
Date: Tue Jun 9 12:21:00 2026 -0700
target/arm: Enable FEAT_FP8DOT4, FEAT_SSVE_FP8DOT4 for -cpu max
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260609192110.752384-37-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst
index e46f5fdcd1..f13721c327 100644
--- a/docs/system/arm/emulation.rst
+++ b/docs/system/arm/emulation.rst
@@ -76,6 +76,7 @@ the following architecture extensions:
- FEAT_FP (Floating Point extensions)
- FEAT_FP16 (Half-precision floating-point data processing)
- FEAT_FP8 (FP8 convert instructions)
+- FEAT_FP8DOT4 (FP8 4-way dot product to single-precision instructions)
- FEAT_FP8FMA (FP8 multiply-accumulate to half-precision and single-precision instructions)
- FEAT_FPAC (Faulting on AUT* instructions)
- FEAT_FPACCOMBINE (Faulting on combined pointer authentication instructions)
@@ -167,6 +168,7 @@ the following architecture extensions:
- FEAT_SME_F64F64 (Double-precision floating-point outer product instructions)
- FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions)
- FEAT_SME_LUTv2 (Lookup table instructions with 4-bit indices and 8-bit elements)
+- FEAT_SSVE_FP8DOT4 (SVE2 FP8 4-way dot product to single-precision instructions in Streaming SVE mode)
- FEAT_SSVE_FP8FMA (SVE2 FP8 multiply-accumulate to half-precision and single-precision instructions in Streaming SVE mode)
- FEAT_SVE (Scalable Vector Extension)
- FEAT_SVE_AES (Scalable Vector AES instructions)
diff --git a/linux-user/aarch64/elfload.c b/linux-user/aarch64/elfload.c
index a82d65a681..be33fede6b 100644
--- a/linux-user/aarch64/elfload.c
+++ b/linux-user/aarch64/elfload.c
@@ -227,7 +227,9 @@ abi_ulong get_elf_hwcap2(CPUState *cs)
ARM_HWCAP2_A64_F8E4M3 |
ARM_HWCAP2_A64_F8E5M2);
GET_FEATURE_ID(aa64_f8fma, ARM_HWCAP2_A64_F8FMA);
+ GET_FEATURE_ID(aa64_f8dp4, ARM_HWCAP2_A64_F8DP4);
GET_FEATURE_ID(aa64_ssve_f8fma, ARM_HWCAP2_A64_SME_SF8FMA);
+ GET_FEATURE_ID(aa64_ssve_f8dp4, ARM_HWCAP2_A64_SME_SF8DP4);
return hwcaps;
}
diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c
index 38c0f0eafd..831b190b21 100644
--- a/target/arm/tcg/cpu64.c
+++ b/target/arm/tcg/cpu64.c
@@ -1383,6 +1383,7 @@ void aarch64_max_tcg_initfn(Object *obj)
SET_IDREG(isar, ID_AA64DFR0, t);
t = GET_IDREG(isar, ID_AA64SMFR0);
+ t = FIELD_DP64(t, ID_AA64SMFR0, SF8DP4, 1); /* FEAT_SSVE_FP8DOT4 */
t = FIELD_DP64(t, ID_AA64SMFR0, SF8FMA, 1); /* FEAT_SSVE_FP8FMA */
t = FIELD_DP64(t, ID_AA64SMFR0, F32F32, 1); /* FEAT_SME */
t = FIELD_DP64(t, ID_AA64SMFR0, BI32I32, 1); /* FEAT_SME2 */
@@ -1402,6 +1403,7 @@ void aarch64_max_tcg_initfn(Object *obj)
t = GET_IDREG(isar, ID_AA64FPFR0);
t = FIELD_DP64(t, ID_AA64FPFR0, F8E5M2, 1); /* FEAT_FP8 */
t = FIELD_DP64(t, ID_AA64FPFR0, F8E4M3, 1); /* FEAT_FP8 */
+ t = FIELD_DP64(t, ID_AA64FPFR0, F8DP4, 1); /* FEAT_FP8DOT4 */
t = FIELD_DP64(t, ID_AA64FPFR0, F8FMA, 1); /* FEAT_FP8FMA */
t = FIELD_DP64(t, ID_AA64FPFR0, F8CVT, 1); /* FEAT_FP8 */
SET_IDREG(isar, ID_AA64FPFR0, t);