[ARM/AArch64][2/2] Crypto intrinsics tuning for Cortex-A53 - pipeline description

	* config/arm/aarch-common.c (aarch_crypto_can_dual_issue): New.
	* config/arm/aarch-common-protos.h (aarch_crypto_can_dual_issue):
	Declare extern.
	* config/arm/cortex-a53.md: Add reservations and bypass for crypto
	instructions as well as AdvancedSIMD loads.

From-SVN: r208910

gcc/ChangeLog

 2014-03-28  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
 
+	* config/arm/aarch-common.c (aarch_crypto_can_dual_issue): New.
+	* config/arm/aarch-common-protos.h (aarch_crypto_can_dual_issue):
+	Declare extern.
+	* config/arm/cortex-a53.md: Add reservations and bypass for crypto
+	instructions as well as AdvancedSIMD loads.
+
+2014-03-28  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
+
 	* config/aarch64/aarch64-simd.md (aarch64_crypto_aes<aes_op>v16qi):
 	Use crypto_aese type.
 	(aarch64_crypto_aes<aesmc_op>v16qi): Use crypto_aesmc type.

gcc/config/arm/aarch-common-protos.h

@@ -23,6 +23,7 @@
 #ifndef GCC_AARCH_COMMON_PROTOS_H
 #define GCC_AARCH_COMMON_PROTOS_H
 
+extern int aarch_crypto_can_dual_issue (rtx, rtx);
 extern int arm_early_load_addr_dep (rtx, rtx);
 extern int arm_early_store_addr_dep (rtx, rtx);
 extern int arm_mac_accumulator_is_mul_result (rtx, rtx);

gcc/config/arm/aarch-common.c

@@ -31,6 +31,42 @@
 #include "c-family/c-common.h"
 #include "rtl.h"
 
+/* In ARMv8-A there's a general expectation that AESE/AESMC
+   and AESD/AESIMC sequences of the form:
+
+   AESE Vn, _
+   AESMC Vn, Vn
+
+   will issue both instructions in a single cycle on super-scalar
+   implementations.  This function identifies such pairs.  */
+
+int
+aarch_crypto_can_dual_issue (rtx producer, rtx consumer)
+{
+  rtx producer_src, consumer_src;
+
+  producer = single_set (producer);
+  consumer = single_set (consumer);
+
+  producer_src = producer ? SET_SRC (producer) : NULL;
+  consumer_src = consumer ? SET_SRC (consumer) : NULL;
+
+  if (producer_src && consumer_src
+      && GET_CODE (producer_src) == UNSPEC && GET_CODE (consumer_src) == UNSPEC
+      && ((XINT (producer_src, 1) == UNSPEC_AESE
+           && XINT (consumer_src, 1) == UNSPEC_AESMC)
+          || (XINT (producer_src, 1) == UNSPEC_AESD
+              && XINT (consumer_src, 1) == UNSPEC_AESIMC)))
+  {
+    unsigned int regno = REGNO (SET_DEST (producer));
+
+    return REGNO (SET_DEST (consumer)) == regno
+           && REGNO (XVECEXP (consumer_src, 0, 0)) == regno;
+  }
+
+  return 0;
+}
+
 typedef struct
 {
   rtx_code search_code;

gcc/config/arm/cortex-a53.md

@@ -61,6 +61,11 @@
 
 (define_cpu_unit "cortex_a53_fp_div_sqrt" "cortex_a53")
 
+;; The Advanced SIMD pipelines.
+
+(define_cpu_unit "cortex_a53_simd0" "cortex_a53")
+(define_cpu_unit "cortex_a53_simd1" "cortex_a53")
+
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;; ALU instructions.
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
@@ -248,6 +253,39 @@
   "cortex_a53_slot0, cortex_a53_fp_div_sqrt * 28")
 
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; ARMv8-A Cryptographic extensions.
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+(define_insn_reservation "cortex_a53_crypto_aese" 2
+  (and (eq_attr "tune" "cortexa53")
+       (eq_attr "type" "crypto_aese"))
+  "cortex_a53_simd0")
+
+(define_insn_reservation "cortex_a53_crypto_aesmc" 2
+  (and (eq_attr "tune" "cortexa53")
+       (eq_attr "type" "crypto_aesmc"))
+  "cortex_a53_simd0 | cortex_a53_simd1")
+
+(define_insn_reservation "cortex_a53_crypto_sha1_fast" 2
+  (and (eq_attr "tune" "cortexa53")
+       (eq_attr "type" "crypto_sha1_fast, crypto_sha256_fast"))
+  "cortex_a53_simd0")
+
+(define_insn_reservation "cortex_a53_crypto_sha1_xor" 3
+  (and (eq_attr "tune" "cortexa53")
+       (eq_attr "type" "crypto_sha1_xor"))
+  "cortex_a53_simd0")
+
+(define_insn_reservation "cortex_a53_crypto_sha_slow" 5
+  (and (eq_attr "tune" "cortexa53")
+       (eq_attr "type" "crypto_sha1_slow, crypto_sha256_slow"))
+  "cortex_a53_simd0")
+
+(define_bypass 0 "cortex_a53_crypto_aese"
+                 "cortex_a53_crypto_aesmc"
+                 "aarch_crypto_can_dual_issue")
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;; VFP to/from core transfers.
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 
@@ -284,6 +322,16 @@
        (eq_attr "type" "f_loadd"))
   "cortex_a53_slot0")
 
+(define_insn_reservation "cortex_a53_f_load_2reg" 5
+  (and (eq_attr "tune" "cortexa53")
+       (eq_attr "type" "neon_load2_2reg_q"))
+  "(cortex_a53_slot_any+cortex_a53_ls)*2")
+
+(define_insn_reservation "cortex_a53_f_loadq" 5
+  (and (eq_attr "tune" "cortexa53")
+       (eq_attr "type" "neon_load1_1reg_q"))
+  "cortex_a53_slot_any+cortex_a53_ls")
+
 (define_insn_reservation "cortex_a53_f_stores" 0
   (and (eq_attr "tune" "cortexa53")
        (eq_attr "type" "f_stores"))
@@ -307,3 +355,11 @@
 		  cortex_a53_fdivs, cortex_a53_fdivd,\
 		  cortex_a53_f2r")
 
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; Crude Advanced SIMD approximation.
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+(define_insn_reservation "cortex_53_advsimd" 4
+  (and (eq_attr "tune" "cortexa53")
+       (eq_attr "is_neon_type" "yes"))
+  "cortex_a53_simd0")