X-Git-Url: http://git.osdn.net/view?a=blobdiff_plain;f=lib%2FTarget%2FAMDGPU%2FSIInstrInfo.cpp;h=2370d5fa7b27b3e35540bdca4d65be22b48e0dcc;hb=1da08e2;hp=b7c4eed621124654b9a6de824f9a9e6eb0fe44f0;hpb=a490b3ede88aedc738297d4a82c0038328c5ccdf;p=android-x86%2Fexternal-llvm.git

diff --git a/lib/Target/AMDGPU/SIInstrInfo.cpp b/lib/Target/AMDGPU/SIInstrInfo.cpp
index b7c4eed6211..2370d5fa7b2 100644
--- a/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -2972,6 +2972,42 @@ bool SIInstrInfo::verifyInstruction(const MachineInstr &MI,
     }
   }
 
+  // Verify MIMG
+  if (isMIMG(MI.getOpcode()) && !MI.mayStore()) {
+    // Ensure that the return type used is large enough for all the options
+    // being used TFE/LWE require an extra result register.
+    const MachineOperand *DMask = getNamedOperand(MI, AMDGPU::OpName::dmask);
+    if (DMask) {
+      uint64_t DMaskImm = DMask->getImm();
+      uint32_t RegCount =
+          isGather4(MI.getOpcode()) ? 4 : countPopulation(DMaskImm);
+      const MachineOperand *TFE = getNamedOperand(MI, AMDGPU::OpName::tfe);
+      const MachineOperand *LWE = getNamedOperand(MI, AMDGPU::OpName::lwe);
+      const MachineOperand *D16 = getNamedOperand(MI, AMDGPU::OpName::d16);
+
+      // Adjust for packed 16 bit values
+      if (D16 && D16->getImm() && !ST.hasUnpackedD16VMem())
+        RegCount >>= 1;
+
+      // Adjust if using LWE or TFE
+      if ((LWE && LWE->getImm()) || (TFE && TFE->getImm()))
+        RegCount += 1;
+
+      const uint32_t DstIdx =
+          AMDGPU::getNamedOperandIdx(MI.getOpcode(), AMDGPU::OpName::vdata);
+      const MachineOperand &Dst = MI.getOperand(DstIdx);
+      if (Dst.isReg()) {
+        const TargetRegisterClass *DstRC = getOpRegClass(MI, DstIdx);
+        uint32_t DstSize = RI.getRegSizeInBits(*DstRC) / 32;
+        if (RegCount > DstSize) {
+          ErrInfo = "MIMG instruction returns too many registers for dst "
+                    "register class";
+          return false;
+        }
+      }
+    }
+  }
+
   // Verify VOP*. Ignore multiple sgpr operands on writelane.
   if (Desc.getOpcode() != AMDGPU::V_WRITELANE_B32
       && (isVOP1(MI) || isVOP2(MI) || isVOP3(MI) || isVOPC(MI) || isSDWA(MI))) {