AMDGPU: Set sizes of spill pseudos

llvm-svn: 280595

3 files changed, 13 insertions, 3 deletions

diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index ae688f04017..56daea6e57e 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -3151,11 +3151,9 @@ unsigned SIInstrInfo::getInstSizeInBytes(const MachineInstr &MI) const {
 
   // If we have a definitive size, we can use it. Otherwise we need to inspect
   // the operands to know the size.
-  if (DescSize == 8 || DescSize == 4)
+  if (DescSize != 0)
     return DescSize;
 
-  assert(DescSize == 0);
-
   // 4-byte instructions may have a 32-bit literal encoded after them. Check
   // operands that coud ever be literals.
   if (isVALU(MI) || isSALU(MI)) {
diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
index 60a571d51bf..6e4f3f13b9e 100644
--- a/llvm/lib/Target/AMDGPU/SIInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -1371,6 +1371,8 @@ multiclass SI_SPILL_VGPR <RegisterClass vgpr_class> {
            SReg_32:$scratch_offset, i32imm:$offset)> {
       let mayStore = 1;
       let mayLoad = 0;
+      // (2 * 4) + (8 * num_subregs) bytes maximum
+      let Size = !add(!shl(!srl(vgpr_class.Size, 5), 3), 8);
     }
 
     def _RESTORE : VPseudoInstSI <
@@ -1379,6 +1381,9 @@ multiclass SI_SPILL_VGPR <RegisterClass vgpr_class> {
            i32imm:$offset)> {
       let mayStore = 0;
       let mayLoad = 1;
+
+      // (2 * 4) + (8 * num_subregs) bytes maximum
+      let Size = !add(!shl(!srl(vgpr_class.Size, 5), 3), 8);
     }
   } // End UseNamedOperandTable = 1, VGPRSpill = 1
 }
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.td b/llvm/lib/Target/AMDGPU/SIRegisterInfo.td
index ac2609dd127..adce99bbc28 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.td
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.td
@@ -193,6 +193,7 @@ def TTMP_128Regs : RegisterTuples<[sub0, sub1, sub2, sub3],
 def VGPR_32 : RegisterClass<"AMDGPU", [i32, f32], 32,
                             (add (sequence "VGPR%u", 0, 255))> {
   let AllocationPriority = 1;
+  let Size = 32;
 }
 
 // VGPR 64-bit registers
@@ -306,6 +307,8 @@ def SReg_512 : RegisterClass<"AMDGPU", [v64i8, v16i32], 32, (add SGPR_512)> {
 
 // Register class for all vector registers (VGPRs + Interploation Registers)
 def VReg_64 : RegisterClass<"AMDGPU", [i64, f64, v2i32, v2f32], 32, (add VGPR_64)> {
+  let Size = 64;
+
   // Requires 2 v_mov_b32 to copy
   let CopyCost = 2;
   let AllocationPriority = 2;
@@ -320,17 +323,21 @@ def VReg_96 : RegisterClass<"AMDGPU", [untyped], 32, (add VGPR_96)> {
 }
 
 def VReg_128 : RegisterClass<"AMDGPU", [v4i32, v4f32, v2i64, v2f64], 32, (add VGPR_128)> {
+  let Size = 128;
+
   // Requires 4 v_mov_b32 to copy
   let CopyCost = 4;
   let AllocationPriority = 4;
 }
 
 def VReg_256 : RegisterClass<"AMDGPU", [v8i32, v8f32], 32, (add VGPR_256)> {
+  let Size = 256;
   let CopyCost = 8;
   let AllocationPriority = 5;
 }
 
 def VReg_512 : RegisterClass<"AMDGPU", [v16i32, v16f32], 32, (add VGPR_512)> {
+  let Size = 512;
   let CopyCost = 16;
   let AllocationPriority = 6;
 }