[Beignet] [PATCH 4/5] GBE: don't always allocate ir::ocl::one/zero

[Zhigang Gong]

Use liveness information, we can only allocate them
on demand. And they could be treated as non-curbe-payload
register.

Signed-off-by: Zhigang Gong <zhigang.gong at intel.com>
---
 backend/src/backend/gen_context.cpp        | 10 ++++------
 backend/src/backend/gen_reg_allocation.cpp | 12 +++++++++---
 backend/src/backend/gen_reg_allocation.hpp |  2 ++
 backend/src/backend/program.h              |  2 --
 backend/src/ir/profile.cpp                 |  4 ++--
 5 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/backend/src/backend/gen_context.cpp b/backend/src/backend/gen_context.cpp
index 5980db2..3dbd957 100644
--- a/backend/src/backend/gen_context.cpp
+++ b/backend/src/backend/gen_context.cpp
@@ -160,8 +160,6 @@ namespace gbe
     // when group size not aligned to simdWidth, flag register need clear to
     // make prediction(any8/16h) work correctly
     const GenRegister blockip = getBlockIP(*this);
-    const GenRegister zero = ra->genReg(GenRegister::uw1grf(ir::ocl::zero));
-    const GenRegister one = ra->genReg(GenRegister::uw1grf(ir::ocl::one));
     p->push();
       p->curr.noMask = 1;
       p->curr.predicate = GEN_PREDICATE_NONE;
@@ -169,10 +167,10 @@ namespace gbe
       p->curr.noMask = 0;
       setBlockIP(*this, blockip, 0);
       p->curr.execWidth = 1;
-      // FIXME, need to get the final use set of zero/one, if there is no user,
-      // no need to generate the following two instructions.
-      p->MOV(zero, GenRegister::immuw(0));
-      p->MOV(one, GenRegister::immw(-1));
+      if (ra->isAllocated(ir::ocl::zero))
+        p->MOV(ra->genReg(GenRegister::uw1grf(ir::ocl::zero)), GenRegister::immuw(0));
+      if (ra->isAllocated(ir::ocl::one))
+        p->MOV(ra->genReg(GenRegister::uw1grf(ir::ocl::one)), GenRegister::immw(-1));
     p->pop();
   }
 
diff --git a/backend/src/backend/gen_reg_allocation.cpp b/backend/src/backend/gen_reg_allocation.cpp
index 4430ca5..06f6cc7 100644
--- a/backend/src/backend/gen_reg_allocation.cpp
+++ b/backend/src/backend/gen_reg_allocation.cpp
@@ -102,6 +102,9 @@ namespace gbe
     bool allocate(Selection &selection);
     /*! Return the Gen register from the selection register */
     GenRegister genReg(const GenRegister &reg);
+    INLINE bool isAllocated(const ir::Register &reg) {
+      return RA.contains(reg);
+    }
     /*! Output the register allocation */
     void outputAllocation(void);
     INLINE void getRegAttrib(ir::Register reg, uint32_t &regSize, ir::RegisterFamily *regFamily = NULL) const {
@@ -1033,13 +1036,12 @@ namespace gbe
       if (curbeType != GBE_GEN_REG) {
         intervals[regID].minID = 0;
 
-        // zero and one have implicitly usage in the initial block.
-        if (curbeType == GBE_CURBE_ONE || curbeType == GBE_CURBE_ZERO)
-          intervals[regID].maxID = 10;
         // FIXME stack buffer is not used, we may need to remove it in the furture.
         if (curbeType == GBE_CURBE_EXTRA_ARGUMENT && subType == GBE_STACK_BUFFER)
           intervals[regID].maxID = 1;
       }
+      if (regID == ir::ocl::zero.value() || regID ==  ir::ocl::one.value())
+        intervals[regID].minID = 0;
     }
 
     // Compute the intervals
@@ -1262,6 +1264,10 @@ namespace gbe
     return this->opaque->genReg(reg);
   }
 
+  bool GenRegAllocator::isAllocated(const ir::Register &reg) {
+    return this->opaque->isAllocated(reg);
+  }
+
   void GenRegAllocator::outputAllocation(void) {
     this->opaque->outputAllocation();
   }
diff --git a/backend/src/backend/gen_reg_allocation.hpp b/backend/src/backend/gen_reg_allocation.hpp
index 89dba64..8d5e797 100644
--- a/backend/src/backend/gen_reg_allocation.hpp
+++ b/backend/src/backend/gen_reg_allocation.hpp
@@ -54,6 +54,8 @@ namespace gbe
     bool allocate(Selection &selection);
     /*! Virtual to physical translation */
     GenRegister genReg(const GenRegister &reg);
+    /*! Check whether a register is allocated. */
+    bool isAllocated(const ir::Register &reg);
     /*! Output the register allocation */
     void outputAllocation(void);
     /*! Get register actual size in byte. */
diff --git a/backend/src/backend/program.h b/backend/src/backend/program.h
index 0758820..d364605 100644
--- a/backend/src/backend/program.h
+++ b/backend/src/backend/program.h
@@ -98,8 +98,6 @@ enum gbe_curbe_type {
   GBE_CURBE_BLOCK_IP,
   GBE_CURBE_DW_BLOCK_IP,
   GBE_CURBE_THREAD_NUM,
-  GBE_CURBE_ZERO,
-  GBE_CURBE_ONE,
   GBE_GEN_REG,
 };
 
diff --git a/backend/src/ir/profile.cpp b/backend/src/ir/profile.cpp
index 484e82d..4486863 100644
--- a/backend/src/ir/profile.cpp
+++ b/backend/src/ir/profile.cpp
@@ -80,8 +80,8 @@ namespace ir {
       DECL_NEW_REG(FAMILY_DWORD, barrierid, 1);
       DECL_NEW_REG(FAMILY_DWORD, threadn, 1, GBE_CURBE_THREAD_NUM);
       DECL_NEW_REG(FAMILY_DWORD, workdim, 1, GBE_CURBE_WORK_DIM);
-      DECL_NEW_REG(FAMILY_DWORD, zero, 1, GBE_CURBE_ZERO);
-      DECL_NEW_REG(FAMILY_DWORD, one, 1, GBE_CURBE_ONE);
+      DECL_NEW_REG(FAMILY_DWORD, zero, 1);
+      DECL_NEW_REG(FAMILY_DWORD, one, 1);
       DECL_NEW_REG(FAMILY_WORD, retVal, 1);
       DECL_NEW_REG(FAMILY_DWORD, printfbptr, 1, GBE_CURBE_PRINTF_BUF_POINTER);
       DECL_NEW_REG(FAMILY_DWORD, printfiptr, 1, GBE_CURBE_PRINTF_INDEX_POINTER);
-- 
1.9.1