AMDGPU/GlobalISel: Don't assert on G_INSERT > 128-bits

Just fallback for now. Really tablegen needs to generate all of the
subregister index handling we need.

llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp

@@ -736,6 +736,10 @@ bool AMDGPUInstructionSelector::selectG_INSERT(MachineInstr &I) const {
   if (Offset % 32 != 0 || InsSize % 32 != 0)
     return false;
 
+  // Currently not handled by getSubRegFromChannel.
+  if (InsSize > 128)
+    return false;
+
   unsigned SubReg = TRI.getSubRegFromChannel(Offset / 32, InsSize / 32);
   if (SubReg == AMDGPU::NoSubRegister)
     return false;

llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-insert.xfail.mir

@@ -1,9 +1,13 @@
 # RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=instruction-select -global-isel-abort=2 -pass-remarks-missed='gisel*' -verify-machineinstrs -o /dev/null %s 2>&1 | FileCheck -check-prefix=ERR %s
 
-# FIXME: This should not be legal and this test should be deleted
-# ERR: remark: <unknown>:0:0: cannot select: %3:sgpr(<4 x s16>) = G_INSERT %0:sgpr, %2:sgpr(s16), 0 (in function: insert_sgpr_2s16_to_v4s16_offset0)
+# ERR: remark: <unknown>:0:0: cannot select: %3:sgpr(<4 x s16>) = G_INSERT %0:sgpr, %2:sgpr(s16), 0 (in function: insert_sgpr_s16_to_v4s16_offset0)
+# ERR-NEXT: remark: <unknown>:0:0: cannot select: %2:sgpr(<16 x s32>) = G_INSERT %0:sgpr, %1:sgpr(<8 x s32>), 0 (in function: insert_sgpr_v8s32_to_v16s32_offset0)
+# ERR-NOT: remark
+
+# FIXME: This 16-bit insert source should not be legal and this test
+# should be deleted
 ---
-name:            insert_sgpr_2s16_to_v4s16_offset0
+name:            insert_sgpr_s16_to_v4s16_offset0
 legalized:       true
 regBankSelected: true
 
@@ -17,3 +21,19 @@ body: |
     S_ENDPGM 0, implicit %3
 
 ...
+
+# getSubRegFromChannel current does not handle cases > 128-bits
+---
+name:            insert_sgpr_v8s32_to_v16s32_offset0
+legalized:       true
+regBankSelected: true
+
+body: |
+  bb.0:
+    liveins: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15, $sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23
+    %0:sgpr(<16 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
+    %1:sgpr(<8 x s32>) = COPY $sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23
+    %2:sgpr(<16 x s32>) = G_INSERT %0, %1, 0
+    S_ENDPGM 0, implicit %2
+
+...