Mesa (staging/20.2): aco: update phi_map in add_subdword_operand()

[GitLab Mirror]

Module: Mesa
Branch: staging/20.2
Commit: 1ddbe3aa11fec7f292cee4f547efade25414932b
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=1ddbe3aa11fec7f292cee4f547efade25414932b

Author: Rhys Perry <pendingchaos02 at gmail.com>
Date:   Tue Oct 27 10:59:35 2020 +0000

aco: update phi_map in add_subdword_operand()

Signed-off-by: Rhys Perry <pendingchaos02 at gmail.com>
Reviewed-by: Daniel Schürmann <daniel at schuermann.dev>
Fixes: 56345b8c610 ("aco: allow reading/writing upper halves/bytes when possible")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7216>
(cherry picked from commit d4503a902057cb5ddb0b2099e3d6df5ef2ba656a)

---

 .pick_status.json                            |  2 +-
 src/amd/compiler/aco_register_allocation.cpp | 40 +++++++++++++++++-----------
 2 files changed, 25 insertions(+), 17 deletions(-)

diff --git a/.pick_status.json b/.pick_status.json
index 26201579243..fb4a52a8930 100644
--- a/.pick_status.json
+++ b/.pick_status.json
@@ -1471,7 +1471,7 @@
         "description": "aco: update phi_map in add_subdword_operand()",
         "nominated": true,
         "nomination_type": 1,
-        "resolution": 0,
+        "resolution": 1,
         "master_sha": null,
         "because_sha": "56345b8c610e06b2c6ccb0d0975e62f9a008e34e"
     },
diff --git a/src/amd/compiler/aco_register_allocation.cpp b/src/amd/compiler/aco_register_allocation.cpp
index 5ff028423b8..2e7935e2dee 100644
--- a/src/amd/compiler/aco_register_allocation.cpp
+++ b/src/amd/compiler/aco_register_allocation.cpp
@@ -38,8 +38,10 @@
 namespace aco {
 namespace {
 
+struct ra_ctx;
+
 unsigned get_subdword_operand_stride(chip_class chip, const aco_ptr<Instruction>& instr, unsigned idx, RegClass rc);
-void add_subdword_operand(chip_class chip, aco_ptr<Instruction>& instr, unsigned idx, unsigned byte, RegClass rc);
+void add_subdword_operand(ra_ctx& ctx, aco_ptr<Instruction>& instr, unsigned idx, unsigned byte, RegClass rc);
 std::pair<unsigned, unsigned> get_subdword_definition_info(Program *program, const aco_ptr<Instruction>& instr, RegClass rc);
 void add_subdword_definition(Program *program, aco_ptr<Instruction>& instr, unsigned idx, PhysReg reg, bool is_partial);
 
@@ -352,8 +354,22 @@ unsigned get_subdword_operand_stride(chip_class chip, const aco_ptr<Instruction>
    return 4;
 }
 
-void add_subdword_operand(chip_class chip, aco_ptr<Instruction>& instr, unsigned idx, unsigned byte, RegClass rc)
+void update_phi_map(ra_ctx& ctx, Instruction *old, Instruction *instr)
 {
+   for (Operand& op : instr->operands) {
+      if (!op.isTemp())
+         continue;
+      std::unordered_map<unsigned, phi_info>::iterator phi = ctx.phi_map.find(op.tempId());
+      if (phi != ctx.phi_map.end()) {
+         phi->second.uses.erase(old);
+         phi->second.uses.emplace(instr);
+      }
+   }
+}
+
+void add_subdword_operand(ra_ctx& ctx, aco_ptr<Instruction>& instr, unsigned idx, unsigned byte, RegClass rc)
+{
+   chip_class chip = ctx.program->chip_class;
    if (instr->format == Format::PSEUDO || byte == 0)
       return;
 
@@ -376,7 +392,9 @@ void add_subdword_operand(chip_class chip, aco_ptr<Instruction>& instr, unsigned
       }
       return;
    } else if (can_use_SDWA(chip, instr)) {
-      convert_to_SDWA(chip, instr);
+      aco_ptr<Instruction> tmp = convert_to_SDWA(chip, instr);
+      if (tmp)
+         update_phi_map(ctx, tmp.get(), instr.get());
       return;
    } else if (rc.bytes() == 2 && can_use_opsel(chip, instr->opcode, idx, byte / 2)) {
       VOP3A_instruction *vop3 = static_cast<VOP3A_instruction *>(instr.get());
@@ -2233,7 +2251,7 @@ void register_allocation(Program *program, std::vector<TempSet>& live_out_per_bl
             if (op.isTemp() && op.isFirstKill() && op.isLateKill())
                register_file.clear(op);
             if (op.isTemp() && op.physReg().byte() != 0)
-               add_subdword_operand(program->chip_class, instr, i, op.physReg().byte(), op.regClass());
+               add_subdword_operand(ctx, instr, i, op.physReg().byte(), op.regClass());
          }
 
          /* emit parallelcopy */
@@ -2366,19 +2384,9 @@ void register_allocation(Program *program, std::vector<TempSet>& live_out_per_bl
             aco_ptr<Instruction> tmp = std::move(instr);
             Format format = asVOP3(tmp->format);
             instr.reset(create_instruction<VOP3A_instruction>(tmp->opcode, format, tmp->operands.size(), tmp->definitions.size()));
-            for (unsigned i = 0; i < instr->operands.size(); i++) {
-               Operand& operand = tmp->operands[i];
-               instr->operands[i] = operand;
-               /* keep phi_map up to date */
-               if (operand.isTemp()) {
-                  std::unordered_map<unsigned, phi_info>::iterator phi = ctx.phi_map.find(operand.tempId());
-                  if (phi != ctx.phi_map.end()) {
-                     phi->second.uses.erase(tmp.get());
-                     phi->second.uses.emplace(instr.get());
-                  }
-               }
-            }
+            std::copy(tmp->operands.begin(), tmp->operands.end(), instr->operands.begin());
             std::copy(tmp->definitions.begin(), tmp->definitions.end(), instr->definitions.begin());
+            update_phi_map(ctx, tmp.get(), instr.get());
          }
 
          instructions.emplace_back(std::move(*it));