Hexagon (target/hexagon) Only use branch_taken when packet has multi cof

When a packet has more than one change-of-flow instruction, only the first
one to branch is considered.  We use the branch_taken variable to keep
track of this.

However, when there is a single cof instruction, we don't need the same
amount of bookkeeping.

We add the pkt_has_multi_cof member to the Packet structure, and pass this
information to the needed functions.

When there is a generated helper function with cof, the generator will
pass this pkt_has_multi_cof as a runtime value.

Acked-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Taylor Simpson <tsimpson@quicinc.com>
Message-Id: <20221108162906.3166-5-tsimpson@quicinc.com>

9 files changed, 51 insertions, 16 deletions

diff --git a/target/hexagon/decode.c b/target/hexagon/decode.c
index 6b73b5c..041c8de 100644
--- a/target/hexagon/decode.c
+++ b/target/hexagon/decode.c
@@ -388,6 +388,7 @@ static void decode_set_insn_attr_fields(Packet *pkt)
     uint16_t opcode;
 
     pkt->pkt_has_cof = false;
+    pkt->pkt_has_multi_cof = false;
     pkt->pkt_has_endloop = false;
     pkt->pkt_has_dczeroa = false;
 
@@ -412,13 +413,23 @@ static void decode_set_insn_attr_fields(Packet *pkt)
             }
         }
 
-        pkt->pkt_has_cof |= decode_opcode_can_jump(opcode);
+        if (decode_opcode_can_jump(opcode)) {
+            if (pkt->pkt_has_cof) {
+                pkt->pkt_has_multi_cof = true;
+            }
+            pkt->pkt_has_cof = true;
+        }
 
         pkt->insn[i].is_endloop = decode_opcode_ends_loop(opcode);
 
         pkt->pkt_has_endloop |= pkt->insn[i].is_endloop;
 
-        pkt->pkt_has_cof |= pkt->pkt_has_endloop;
+        if (pkt->pkt_has_endloop) {
+            if (pkt->pkt_has_cof) {
+                pkt->pkt_has_multi_cof = true;
+            }
+            pkt->pkt_has_cof = true;
+        }
     }
 }
 
diff --git a/target/hexagon/gen_helper_funcs.py b/target/hexagon/gen_helper_funcs.py
index a446c45..c4fc609 100755
--- a/target/hexagon/gen_helper_funcs.py
+++ b/target/hexagon/gen_helper_funcs.py
@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 
 ##
-##  Copyright(c) 2019-2021 Qualcomm Innovation Center, Inc. All Rights Reserved.
+##  Copyright(c) 2019-2022 Qualcomm Innovation Center, Inc. All Rights Reserved.
 ##
 ##  This program is free software; you can redistribute it and/or modify
 ##  it under the terms of the GNU General Public License as published by
@@ -238,6 +238,9 @@ def gen_helper_function(f, tag, tagregs, tagimms):
             gen_helper_arg_imm(f,immlett)
             i += 1
 
+        if (hex_common.need_pkt_has_multi_cof(tag)):
+            f.write(", uint32_t pkt_has_multi_cof")
+
         if hex_common.need_slot(tag):
             if i > 0: f.write(", ")
             f.write("uint32_t slot")
diff --git a/target/hexagon/gen_helper_protos.py b/target/hexagon/gen_helper_protos.py
index 3b4e993..8c6b36d 100755
--- a/target/hexagon/gen_helper_protos.py
+++ b/target/hexagon/gen_helper_protos.py
@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 
 ##
-##  Copyright(c) 2019-2021 Qualcomm Innovation Center, Inc. All Rights Reserved.
+##  Copyright(c) 2019-2022 Qualcomm Innovation Center, Inc. All Rights Reserved.
 ##
 ##  This program is free software; you can redistribute it and/or modify
 ##  it under the terms of the GNU General Public License as published by
@@ -82,6 +82,7 @@ def gen_helper_prototype(f, tag, tagregs, tagimms):
         ## Figure out how many arguments the helper will take
         if (numscalarresults == 0):
             def_helper_size = len(regs)+len(imms)+numscalarreadwrite+1
+            if hex_common.need_pkt_has_multi_cof(tag): def_helper_size += 1
             if hex_common.need_part1(tag): def_helper_size += 1
             if hex_common.need_slot(tag): def_helper_size += 1
             f.write('DEF_HELPER_%s(%s' % (def_helper_size, tag))
@@ -89,6 +90,7 @@ def gen_helper_prototype(f, tag, tagregs, tagimms):
             f.write(', void' )
         else:
             def_helper_size = len(regs)+len(imms)+numscalarreadwrite
+            if hex_common.need_pkt_has_multi_cof(tag): def_helper_size += 1
             if hex_common.need_part1(tag): def_helper_size += 1
             if hex_common.need_slot(tag): def_helper_size += 1
             f.write('DEF_HELPER_%s(%s' % (def_helper_size, tag))
@@ -126,7 +128,9 @@ def gen_helper_prototype(f, tag, tagregs, tagimms):
         for immlett,bits,immshift in imms:
             f.write(", s32")
 
-        ## Add the arguments for the instruction slot and part1 (if needed)
+        ## Add the arguments for the instruction pkt_has_multi_cof, slot and
+        ## part1 (if needed)
+        if hex_common.need_pkt_has_multi_cof(tag): f.write(', i32')
         if hex_common.need_slot(tag): f.write(', i32' )
         if hex_common.need_part1(tag): f.write(' , i32' )
         f.write(')\n')
diff --git a/target/hexagon/gen_tcg_funcs.py b/target/hexagon/gen_tcg_funcs.py
index ca5fde9..bd199dc 100755
--- a/target/hexagon/gen_tcg_funcs.py
+++ b/target/hexagon/gen_tcg_funcs.py
@@ -622,6 +622,9 @@ def gen_tcg_func(f, tag, regs, imms):
         ## Generate the call to the helper
         for immlett,bits,immshift in imms:
             gen_helper_decl_imm(f,immlett)
+        if hex_common.need_pkt_has_multi_cof(tag):
+            f.write("    TCGv pkt_has_multi_cof = ")
+            f.write("tcg_constant_tl(ctx->pkt->pkt_has_multi_cof);\n")
         if hex_common.need_part1(tag):
             f.write("    TCGv part1 = tcg_constant_tl(insn->part1);\n")
         if hex_common.need_slot(tag):
@@ -654,6 +657,8 @@ def gen_tcg_func(f, tag, regs, imms):
         for immlett,bits,immshift in imms:
             gen_helper_call_imm(f,immlett)
 
+        if hex_common.need_pkt_has_multi_cof(tag):
+            f.write(", pkt_has_multi_cof")
         if hex_common.need_slot(tag): f.write(", slot")
         if hex_common.need_part1(tag): f.write(", part1" )
         f.write(");\n")
diff --git a/target/hexagon/hex_common.py b/target/hexagon/hex_common.py
index d9ba7df..f5b5850 100755
--- a/target/hexagon/hex_common.py
+++ b/target/hexagon/hex_common.py
@@ -207,6 +207,9 @@ def need_part1(tag):
 def need_ea(tag):
     return re.compile(r"\bEA\b").search(semdict[tag])
 
+def need_pkt_has_multi_cof(tag):
+    return 'A_COF' in attribdict[tag]
+
 def skip_qemu_helper(tag):
     return tag in overrides.keys()
 
diff --git a/target/hexagon/insn.h b/target/hexagon/insn.h
index cb92586..775c4c1 100644
--- a/target/hexagon/insn.h
+++ b/target/hexagon/insn.h
@@ -57,6 +57,7 @@ struct Packet {
 
     /* Pre-decodes about COF */
     bool pkt_has_cof;          /* Has any change-of-flow */
+    bool pkt_has_multi_cof;    /* Has more than one change-of-flow */
     bool pkt_has_endloop;
 
     bool pkt_has_dczeroa;
diff --git a/target/hexagon/macros.h b/target/hexagon/macros.h
index 93ee473..8fd8123 100644
--- a/target/hexagon/macros.h
+++ b/target/hexagon/macros.h
@@ -407,7 +407,7 @@ static inline TCGv gen_read_ireg(TCGv result, TCGv val, int shift)
 
 #define fCHECK_PCALIGN(A)
 
-#define fWRITE_NPC(A) write_new_pc(env, A)
+#define fWRITE_NPC(A) write_new_pc(env, pkt_has_multi_cof != 0, A)
 
 #define fBRANCH(LOC, TYPE)          fWRITE_NPC(LOC)
 #define fJUMPR(REGNO, TARGET, TYPE) fBRANCH(TARGET, COF_TYPE_JUMPR)
diff --git a/target/hexagon/op_helper.c b/target/hexagon/op_helper.c
index 085afc3..84391e2 100644
--- a/target/hexagon/op_helper.c
+++ b/target/hexagon/op_helper.c
@@ -104,20 +104,26 @@ static void log_store64(CPUHexagonState *env, target_ulong addr,
     env->mem_log_stores[slot].data64 = val;
 }
 
-static void write_new_pc(CPUHexagonState *env, target_ulong addr)
+static void write_new_pc(CPUHexagonState *env, bool pkt_has_multi_cof,
+                         target_ulong addr)
 {
     HEX_DEBUG_LOG("write_new_pc(0x" TARGET_FMT_lx ")\n", addr);
 
-    /*
-     * If more than one branch is taken in a packet, only the first one
-     * is actually done.
-     */
-    if (env->branch_taken) {
-        HEX_DEBUG_LOG("INFO: multiple branches taken in same packet, "
-                      "ignoring the second one\n");
+    if (pkt_has_multi_cof) {
+        /*
+         * If more than one branch is taken in a packet, only the first one
+         * is actually done.
+         */
+        if (env->branch_taken) {
+            HEX_DEBUG_LOG("INFO: multiple branches taken in same packet, "
+                          "ignoring the second one\n");
+        } else {
+            fCHECK_PCALIGN(addr);
+            env->next_PC = addr;
+            env->branch_taken = 1;
+        }
     } else {
         fCHECK_PCALIGN(addr);
-        env->branch_taken = 1;
         env->next_PC = addr;
     }
 }
diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c
index 0940d0f..1d872d7 100644
--- a/target/hexagon/translate.c
+++ b/target/hexagon/translate.c
@@ -248,7 +248,9 @@ static void gen_start_packet(DisasContext *ctx)
         tcg_gen_movi_tl(hex_slot_cancelled, 0);
     }
     if (pkt->pkt_has_cof) {
-        tcg_gen_movi_tl(hex_branch_taken, 0);
+        if (pkt->pkt_has_multi_cof) {
+            tcg_gen_movi_tl(hex_branch_taken, 0);
+        }
         tcg_gen_movi_tl(hex_next_PC, next_PC);
     }
     if (need_pred_written(pkt)) {