diff options
Diffstat (limited to 'gcc')
-rw-r--r-- | gcc/config/arm/aarch-common-protos.h | 2 | ||||
-rw-r--r-- | gcc/config/arm/aarch-common.c | 36 | ||||
-rw-r--r-- | gcc/config/arm/cortex-a53.md | 10 |
3 files changed, 48 insertions, 0 deletions
diff --git a/gcc/config/arm/aarch-common-protos.h b/gcc/config/arm/aarch-common-protos.h index 8e9fb7a895b..5298172e6b6 100644 --- a/gcc/config/arm/aarch-common-protos.h +++ b/gcc/config/arm/aarch-common-protos.h @@ -30,7 +30,9 @@ extern bool aarch_rev16_p (rtx); extern bool aarch_rev16_shleft_mask_imm_p (rtx, machine_mode); extern bool aarch_rev16_shright_mask_imm_p (rtx, machine_mode); extern int arm_early_load_addr_dep (rtx, rtx); +extern int arm_early_load_addr_dep_ptr (rtx, rtx); extern int arm_early_store_addr_dep (rtx, rtx); +extern int arm_early_store_addr_dep_ptr (rtx, rtx); extern int arm_mac_accumulator_is_mul_result (rtx, rtx); extern int arm_mac_accumulator_is_result (rtx, rtx); extern int arm_no_early_alu_shift_dep (rtx, rtx); diff --git a/gcc/config/arm/aarch-common.c b/gcc/config/arm/aarch-common.c index dd37be0291a..74b80b27255 100644 --- a/gcc/config/arm/aarch-common.c +++ b/gcc/config/arm/aarch-common.c @@ -241,6 +241,24 @@ arm_early_load_addr_dep (rtx producer, rtx consumer) return reg_overlap_mentioned_p (value, addr); } +/* Return nonzero if the CONSUMER instruction (a load) does need + a Pmode PRODUCER's value to calculate the address. */ + +int +arm_early_load_addr_dep_ptr (rtx producer, rtx consumer) +{ + rtx value = arm_find_sub_rtx_with_code (PATTERN (producer), SET, false); + rtx addr = arm_find_sub_rtx_with_code (PATTERN (consumer), SET, false); + + if (!value || !addr || !MEM_P (SET_SRC (value))) + return 0; + + value = SET_DEST (value); + addr = SET_SRC (addr); + + return GET_MODE (value) == Pmode && reg_overlap_mentioned_p (value, addr); +} + /* Return nonzero if the CONSUMER instruction (an ALU op) does not have an early register shift value or amount dependency on the result of PRODUCER. */ @@ -336,6 +354,24 @@ arm_early_store_addr_dep (rtx producer, rtx consumer) return !arm_no_early_store_addr_dep (producer, consumer); } +/* Return nonzero if the CONSUMER instruction (a store) does need + a Pmode PRODUCER's value to calculate the address. */ + +int +arm_early_store_addr_dep_ptr (rtx producer, rtx consumer) +{ + rtx value = arm_find_sub_rtx_with_code (PATTERN (producer), SET, false); + rtx addr = arm_find_sub_rtx_with_code (PATTERN (consumer), SET, false); + + if (!value || !addr || !MEM_P (SET_SRC (value))) + return 0; + + value = SET_DEST (value); + addr = SET_DEST (addr); + + return GET_MODE (value) == Pmode && reg_overlap_mentioned_p (value, addr); +} + /* Return non-zero iff the consumer (a multiply-accumulate or a multiple-subtract instruction) has an accumulator dependency on the result of the producer and no other dependency on that result. It diff --git a/gcc/config/arm/cortex-a53.md b/gcc/config/arm/cortex-a53.md index 9653aa2345a..b51efae527a 100644 --- a/gcc/config/arm/cortex-a53.md +++ b/gcc/config/arm/cortex-a53.md @@ -254,6 +254,16 @@ "cortex_a53_store*" "arm_no_early_store_addr_dep") +;; Model a bypass for load to load/store address. + +(define_bypass 3 "cortex_a53_load1" + "cortex_a53_load*" + "arm_early_load_addr_dep_ptr") + +(define_bypass 3 "cortex_a53_load1" + "cortex_a53_store*" + "arm_early_store_addr_dep_ptr") + ;; Model a GP->FP register move as similar to stores. (define_bypass 0 "cortex_a53_alu*,cortex_a53_shift*" |