From: Peter Maydell <peter.maydell@linaro.org>
To: qemu-devel@nongnu.org
Subject: [Qemu-devel] [PULL 14/33] target/arm: Split contiguous loads for endianness
Date: Mon, 8 Oct 2018 14:59:45 +0100 [thread overview]
Message-ID: <20181008140004.12612-15-peter.maydell@linaro.org> (raw)
In-Reply-To: <20181008140004.12612-1-peter.maydell@linaro.org>
From: Richard Henderson <richard.henderson@linaro.org>
We can choose the endianness at translation time, rather than
re-computing it at execution time.
Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20181005175350.30752-11-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
target/arm/helper-sve.h | 117 +++++++++++++++-------
target/arm/sve_helper.c | 70 ++++++-------
target/arm/translate-sve.c | 196 +++++++++++++++++++++++++------------
3 files changed, 252 insertions(+), 131 deletions(-)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 023952a9a47..526caec8dac 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -1128,20 +1128,35 @@ DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld4bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld2hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld3hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld4hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld2hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld3hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld4hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld2ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld3ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld4ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld2hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld3hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld4hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld2dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld3dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld4dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld2ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld3ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld4ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_ld1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld2ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld3ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld4ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_ld1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld2dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld3dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld4dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_ld1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
@@ -1150,13 +1165,21 @@ DEF_HELPER_FLAGS_4(sve_ld1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1hsu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1hdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1hss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1hds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ld1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1hsu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1hdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1hss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_ld1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_ld1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ldff1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ldff1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
@@ -1166,17 +1189,28 @@ DEF_HELPER_FLAGS_4(sve_ldff1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ldff1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ldff1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldff1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldff1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldff1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldff1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldff1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1hsu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1hdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1hss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1hds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldff1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldff1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldff1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1hsu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1hdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1hss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldff1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_ldff1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_ldff1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldff1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ldnf1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ldnf1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
@@ -1186,17 +1220,28 @@ DEF_HELPER_FLAGS_4(sve_ldnf1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ldnf1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ldnf1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldnf1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldnf1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldnf1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldnf1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldnf1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1hsu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1hdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1hss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1hds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldnf1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldnf1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldnf1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1hsu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1hdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1hss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_ldnf1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_ldnf1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_ldnf1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ldnf1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 0b1e06823b6..d31988b46ab 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -4249,18 +4249,18 @@ void HELPER(sve_##NAME##_r)(CPUARMState *env, void *vg, \
sve_##NAME##_host, sve_##NAME##_tlb); \
}
-/* TODO: Propagate the endian check back to the translator. */
#define DO_LD1_2(NAME, ESZ, MSZ) \
-void HELPER(sve_##NAME##_r)(CPUARMState *env, void *vg, \
- target_ulong addr, uint32_t desc) \
-{ \
- if (arm_cpu_data_is_big_endian(env)) { \
- sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \
- sve_##NAME##_be_host, sve_##NAME##_be_tlb); \
- } else { \
- sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \
- sve_##NAME##_le_host, sve_##NAME##_le_tlb); \
- } \
+void HELPER(sve_##NAME##_le_r)(CPUARMState *env, void *vg, \
+ target_ulong addr, uint32_t desc) \
+{ \
+ sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \
+ sve_##NAME##_le_host, sve_##NAME##_le_tlb); \
+} \
+void HELPER(sve_##NAME##_be_r)(CPUARMState *env, void *vg, \
+ target_ulong addr, uint32_t desc) \
+{ \
+ sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \
+ sve_##NAME##_be_host, sve_##NAME##_be_tlb); \
}
DO_LD1_1(ld1bb, 0)
@@ -4387,12 +4387,17 @@ void __attribute__((flatten)) HELPER(sve_ld##N##bb_r) \
}
#define DO_LDN_2(N, SUFF, SIZE) \
-void __attribute__((flatten)) HELPER(sve_ld##N##SUFF##_r) \
+void __attribute__((flatten)) HELPER(sve_ld##N##SUFF##_le_r) \
(CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \
{ \
sve_ld##N##_r(env, vg, addr, desc, SIZE, GETPC(), \
- arm_cpu_data_is_big_endian(env) \
- ? sve_ld1##SUFF##_be_tlb : sve_ld1##SUFF##_le_tlb); \
+ sve_ld1##SUFF##_le_tlb); \
+} \
+void __attribute__((flatten)) HELPER(sve_ld##N##SUFF##_be_r) \
+ (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc) \
+{ \
+ sve_ld##N##_r(env, vg, addr, desc, SIZE, GETPC(), \
+ sve_ld1##SUFF##_be_tlb); \
}
DO_LDN_1(2)
@@ -4618,29 +4623,28 @@ void HELPER(sve_ldnf1##PART##_r)(CPUARMState *env, void *vg, \
sve_ldnf1_r(env, vg, addr, desc, ESZ, 0, sve_ld1##PART##_host); \
}
-/* TODO: Propagate the endian check back to the translator. */
#define DO_LDFF1_LDNF1_2(PART, ESZ, MSZ) \
-void HELPER(sve_ldff1##PART##_r)(CPUARMState *env, void *vg, \
- target_ulong addr, uint32_t desc) \
+void HELPER(sve_ldff1##PART##_le_r)(CPUARMState *env, void *vg, \
+ target_ulong addr, uint32_t desc) \
{ \
- if (arm_cpu_data_is_big_endian(env)) { \
- sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \
- sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb); \
- } else { \
- sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \
- sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb); \
- } \
+ sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \
+ sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb); \
} \
-void HELPER(sve_ldnf1##PART##_r)(CPUARMState *env, void *vg, \
- target_ulong addr, uint32_t desc) \
+void HELPER(sve_ldnf1##PART##_le_r)(CPUARMState *env, void *vg, \
+ target_ulong addr, uint32_t desc) \
{ \
- if (arm_cpu_data_is_big_endian(env)) { \
- sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, \
- sve_ld1##PART##_be_host); \
- } else { \
- sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, \
- sve_ld1##PART##_le_host); \
- } \
+ sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, sve_ld1##PART##_le_host); \
+} \
+void HELPER(sve_ldff1##PART##_be_r)(CPUARMState *env, void *vg, \
+ target_ulong addr, uint32_t desc) \
+{ \
+ sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, \
+ sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb); \
+} \
+void HELPER(sve_ldnf1##PART##_be_r)(CPUARMState *env, void *vg, \
+ target_ulong addr, uint32_t desc) \
+{ \
+ sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, sve_ld1##PART##_be_host); \
}
DO_LDFF1_LDNF1_1(bb, 0)
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 4ee3bbca29d..8d191df7d8c 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -4624,32 +4624,58 @@ static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
static void do_ld_zpa(DisasContext *s, int zt, int pg,
TCGv_i64 addr, int dtype, int nreg)
{
- static gen_helper_gvec_mem * const fns[16][4] = {
- { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r,
- gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r },
- { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL },
+ static gen_helper_gvec_mem * const fns[2][16][4] = {
+ /* Little-endian */
+ { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r,
+ gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r },
+ { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1sds_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1hh_r, gen_helper_sve_ld2hh_r,
- gen_helper_sve_ld3hh_r, gen_helper_sve_ld4hh_r },
- { gen_helper_sve_ld1hsu_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1hdu_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1sds_le_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1hh_le_r, gen_helper_sve_ld2hh_le_r,
+ gen_helper_sve_ld3hh_le_r, gen_helper_sve_ld4hh_le_r },
+ { gen_helper_sve_ld1hsu_le_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1hdu_le_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1hds_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1hss_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1ss_r, gen_helper_sve_ld2ss_r,
- gen_helper_sve_ld3ss_r, gen_helper_sve_ld4ss_r },
- { gen_helper_sve_ld1sdu_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1hds_le_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1hss_le_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1ss_le_r, gen_helper_sve_ld2ss_le_r,
+ gen_helper_sve_ld3ss_le_r, gen_helper_sve_ld4ss_le_r },
+ { gen_helper_sve_ld1sdu_le_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1bds_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1bss_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL },
- { gen_helper_sve_ld1dd_r, gen_helper_sve_ld2dd_r,
- gen_helper_sve_ld3dd_r, gen_helper_sve_ld4dd_r },
+ { gen_helper_sve_ld1bds_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1bss_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1dd_le_r, gen_helper_sve_ld2dd_le_r,
+ gen_helper_sve_ld3dd_le_r, gen_helper_sve_ld4dd_le_r } },
+
+ /* Big-endian */
+ { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r,
+ gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r },
+ { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL },
+
+ { gen_helper_sve_ld1sds_be_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1hh_be_r, gen_helper_sve_ld2hh_be_r,
+ gen_helper_sve_ld3hh_be_r, gen_helper_sve_ld4hh_be_r },
+ { gen_helper_sve_ld1hsu_be_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1hdu_be_r, NULL, NULL, NULL },
+
+ { gen_helper_sve_ld1hds_be_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1hss_be_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1ss_be_r, gen_helper_sve_ld2ss_be_r,
+ gen_helper_sve_ld3ss_be_r, gen_helper_sve_ld4ss_be_r },
+ { gen_helper_sve_ld1sdu_be_r, NULL, NULL, NULL },
+
+ { gen_helper_sve_ld1bds_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1bss_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1dd_be_r, gen_helper_sve_ld2dd_be_r,
+ gen_helper_sve_ld3dd_be_r, gen_helper_sve_ld4dd_be_r } }
};
- gen_helper_gvec_mem *fn = fns[dtype][nreg];
+ gen_helper_gvec_mem *fn = fns[s->be_data == MO_BE][dtype][nreg];
/* While there are holes in the table, they are not
* accessible via the instruction encoding.
@@ -4689,59 +4715,103 @@ static bool trans_LD_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn)
static bool trans_LDFF1_zprr(DisasContext *s, arg_rprr_load *a, uint32_t insn)
{
- static gen_helper_gvec_mem * const fns[16] = {
- gen_helper_sve_ldff1bb_r,
- gen_helper_sve_ldff1bhu_r,
- gen_helper_sve_ldff1bsu_r,
- gen_helper_sve_ldff1bdu_r,
+ static gen_helper_gvec_mem * const fns[2][16] = {
+ /* Little-endian */
+ { gen_helper_sve_ldff1bb_r,
+ gen_helper_sve_ldff1bhu_r,
+ gen_helper_sve_ldff1bsu_r,
+ gen_helper_sve_ldff1bdu_r,
- gen_helper_sve_ldff1sds_r,
- gen_helper_sve_ldff1hh_r,
- gen_helper_sve_ldff1hsu_r,
- gen_helper_sve_ldff1hdu_r,
+ gen_helper_sve_ldff1sds_le_r,
+ gen_helper_sve_ldff1hh_le_r,
+ gen_helper_sve_ldff1hsu_le_r,
+ gen_helper_sve_ldff1hdu_le_r,
- gen_helper_sve_ldff1hds_r,
- gen_helper_sve_ldff1hss_r,
- gen_helper_sve_ldff1ss_r,
- gen_helper_sve_ldff1sdu_r,
+ gen_helper_sve_ldff1hds_le_r,
+ gen_helper_sve_ldff1hss_le_r,
+ gen_helper_sve_ldff1ss_le_r,
+ gen_helper_sve_ldff1sdu_le_r,
- gen_helper_sve_ldff1bds_r,
- gen_helper_sve_ldff1bss_r,
- gen_helper_sve_ldff1bhs_r,
- gen_helper_sve_ldff1dd_r,
+ gen_helper_sve_ldff1bds_r,
+ gen_helper_sve_ldff1bss_r,
+ gen_helper_sve_ldff1bhs_r,
+ gen_helper_sve_ldff1dd_le_r },
+
+ /* Big-endian */
+ { gen_helper_sve_ldff1bb_r,
+ gen_helper_sve_ldff1bhu_r,
+ gen_helper_sve_ldff1bsu_r,
+ gen_helper_sve_ldff1bdu_r,
+
+ gen_helper_sve_ldff1sds_be_r,
+ gen_helper_sve_ldff1hh_be_r,
+ gen_helper_sve_ldff1hsu_be_r,
+ gen_helper_sve_ldff1hdu_be_r,
+
+ gen_helper_sve_ldff1hds_be_r,
+ gen_helper_sve_ldff1hss_be_r,
+ gen_helper_sve_ldff1ss_be_r,
+ gen_helper_sve_ldff1sdu_be_r,
+
+ gen_helper_sve_ldff1bds_r,
+ gen_helper_sve_ldff1bss_r,
+ gen_helper_sve_ldff1bhs_r,
+ gen_helper_sve_ldff1dd_be_r },
};
if (sve_access_check(s)) {
TCGv_i64 addr = new_tmp_a64(s);
tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype));
tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn));
- do_mem_zpa(s, a->rd, a->pg, addr, fns[a->dtype]);
+ do_mem_zpa(s, a->rd, a->pg, addr, fns[s->be_data == MO_BE][a->dtype]);
}
return true;
}
static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn)
{
- static gen_helper_gvec_mem * const fns[16] = {
- gen_helper_sve_ldnf1bb_r,
- gen_helper_sve_ldnf1bhu_r,
- gen_helper_sve_ldnf1bsu_r,
- gen_helper_sve_ldnf1bdu_r,
+ static gen_helper_gvec_mem * const fns[2][16] = {
+ /* Little-endian */
+ { gen_helper_sve_ldnf1bb_r,
+ gen_helper_sve_ldnf1bhu_r,
+ gen_helper_sve_ldnf1bsu_r,
+ gen_helper_sve_ldnf1bdu_r,
- gen_helper_sve_ldnf1sds_r,
- gen_helper_sve_ldnf1hh_r,
- gen_helper_sve_ldnf1hsu_r,
- gen_helper_sve_ldnf1hdu_r,
+ gen_helper_sve_ldnf1sds_le_r,
+ gen_helper_sve_ldnf1hh_le_r,
+ gen_helper_sve_ldnf1hsu_le_r,
+ gen_helper_sve_ldnf1hdu_le_r,
- gen_helper_sve_ldnf1hds_r,
- gen_helper_sve_ldnf1hss_r,
- gen_helper_sve_ldnf1ss_r,
- gen_helper_sve_ldnf1sdu_r,
+ gen_helper_sve_ldnf1hds_le_r,
+ gen_helper_sve_ldnf1hss_le_r,
+ gen_helper_sve_ldnf1ss_le_r,
+ gen_helper_sve_ldnf1sdu_le_r,
- gen_helper_sve_ldnf1bds_r,
- gen_helper_sve_ldnf1bss_r,
- gen_helper_sve_ldnf1bhs_r,
- gen_helper_sve_ldnf1dd_r,
+ gen_helper_sve_ldnf1bds_r,
+ gen_helper_sve_ldnf1bss_r,
+ gen_helper_sve_ldnf1bhs_r,
+ gen_helper_sve_ldnf1dd_le_r },
+
+ /* Big-endian */
+ { gen_helper_sve_ldnf1bb_r,
+ gen_helper_sve_ldnf1bhu_r,
+ gen_helper_sve_ldnf1bsu_r,
+ gen_helper_sve_ldnf1bdu_r,
+
+ gen_helper_sve_ldnf1sds_be_r,
+ gen_helper_sve_ldnf1hh_be_r,
+ gen_helper_sve_ldnf1hsu_be_r,
+ gen_helper_sve_ldnf1hdu_be_r,
+
+ gen_helper_sve_ldnf1hds_be_r,
+ gen_helper_sve_ldnf1hss_be_r,
+ gen_helper_sve_ldnf1ss_be_r,
+ gen_helper_sve_ldnf1sdu_be_r,
+
+ gen_helper_sve_ldnf1bds_r,
+ gen_helper_sve_ldnf1bss_r,
+ gen_helper_sve_ldnf1bhs_r,
+ gen_helper_sve_ldnf1dd_be_r },
};
if (sve_access_check(s)) {
@@ -4751,16 +4821,18 @@ static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn)
TCGv_i64 addr = new_tmp_a64(s);
tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), off);
- do_mem_zpa(s, a->rd, a->pg, addr, fns[a->dtype]);
+ do_mem_zpa(s, a->rd, a->pg, addr, fns[s->be_data == MO_BE][a->dtype]);
}
return true;
}
static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz)
{
- static gen_helper_gvec_mem * const fns[4] = {
- gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_r,
- gen_helper_sve_ld1ss_r, gen_helper_sve_ld1dd_r,
+ static gen_helper_gvec_mem * const fns[2][4] = {
+ { gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_le_r,
+ gen_helper_sve_ld1ss_le_r, gen_helper_sve_ld1dd_le_r },
+ { gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_be_r,
+ gen_helper_sve_ld1ss_be_r, gen_helper_sve_ld1dd_be_r },
};
unsigned vsz = vec_full_reg_size(s);
TCGv_ptr t_pg;
@@ -4792,7 +4864,7 @@ static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz)
t_pg = tcg_temp_new_ptr();
tcg_gen_addi_ptr(t_pg, cpu_env, poff);
- fns[msz](cpu_env, t_pg, addr, desc);
+ fns[s->be_data == MO_BE][msz](cpu_env, t_pg, addr, desc);
tcg_temp_free_ptr(t_pg);
tcg_temp_free_i32(desc);
--
2.19.0
next prev parent reply other threads:[~2018-10-08 14:00 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-08 13:59 [Qemu-devel] [PULL 00/33] target-arm queue Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 01/33] target/arm: fix code comments error Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 02/33] virt: Suppress external aborts on virt-2.10 and earlier Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 03/33] target/arm: Correct condition for v8M callee stack push Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 04/33] target/arm: Don't read r4 from v8M exception stackframe twice Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 05/33] target/arm: Define ID_AA64ZFR0_EL1 Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 06/33] target/arm: Adjust sve_exception_el Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 07/33] target/arm: Pass in current_el to fp and sve_exception_el Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 08/33] target/arm: Handle SVE vector length changes in system mode Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 09/33] target/arm: Adjust aarch64_cpu_dump_state for system mode SVE Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 10/33] target/arm: Clear unused predicate bits for LD1RQ Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 11/33] target/arm: Rewrite helper_sve_ld1*_r using pages Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 12/33] target/arm: Rewrite helper_sve_ld[234]*_r Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 13/33] target/arm: Rewrite helper_sve_st[1234]*_r Peter Maydell
2018-10-08 13:59 ` Peter Maydell [this message]
2018-10-08 13:59 ` [Qemu-devel] [PULL 15/33] target/arm: Split contiguous stores for endianness Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 16/33] target/arm: Rewrite vector gather loads Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 17/33] target/arm: Rewrite vector gather stores Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 18/33] target/arm: Rewrite vector gather first-fault loads Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 19/33] target/arm: Pass TCGMemOpIdx to sve memory helpers Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 20/33] target/arm: Define new TBFLAG for v8M stack checking Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 21/33] target/arm: Define new EXCP type for v8M stack overflows Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 22/33] target/arm: Move v7m_using_psp() to internals.h Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 23/33] target/arm: Add v8M stack checks on ADD/SUB/MOV of SP Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 24/33] target/arm: Add some comments in Thumb decode Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 25/33] target/arm: Add v8M stack checks on exception entry Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 26/33] target/arm: Add v8M stack limit checks on NS function calls Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 27/33] target/arm: Add v8M stack checks for LDRD/STRD (imm) Peter Maydell
2018-10-08 13:59 ` [Qemu-devel] [PULL 28/33] target/arm: Add v8M stack checks for Thumb2 LDM/STM Peter Maydell
2018-10-08 14:00 ` [Qemu-devel] [PULL 29/33] target/arm: Add v8M stack checks for T32 load/store single Peter Maydell
2018-10-08 14:00 ` [Qemu-devel] [PULL 30/33] target/arm: Add v8M stack checks for Thumb push/pop Peter Maydell
2018-10-08 14:00 ` [Qemu-devel] [PULL 31/33] target/arm: Add v8M stack checks for VLDM/VSTM Peter Maydell
2018-10-08 14:00 ` [Qemu-devel] [PULL 32/33] target/arm: Add v8M stack checks for MSR to SP_NS Peter Maydell
2018-10-08 14:00 ` [Qemu-devel] [PULL 33/33] hw/display/bcm2835_fb: Silence Coverity warning about multiply overflow Peter Maydell
2018-10-08 14:46 ` [Qemu-devel] [PULL 00/33] target-arm queue 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=20181008140004.12612-15-peter.maydell@linaro.org \
--to=peter.maydell@linaro.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.