[GlobalISel] Combine (sext (trunc x)) to (sext_inreg x)

llvm/include/llvm/Target/GlobalISel/Combine.td

@@ -1522,7 +1522,7 @@ def extract_vector_element_build_vector_trunc8 : GICombineRule<
 
 def sext_trunc : GICombineRule<
    (defs root:$root, build_fn_matchinfo:$matchinfo),
-   (match (G_TRUNC $src, $x, (MIFlags NoSWrap)),
+   (match (G_TRUNC $src, $x),
           (G_SEXT $root, $src),
    [{ return Helper.matchSextOfTrunc(${root}, ${matchinfo}); }]),
    (apply [{ Helper.applyBuildFnMO(${root}, ${matchinfo}); }])>;

llvm/lib/CodeGen/GlobalISel/CombinerHelperCasts.cpp

@@ -36,6 +36,20 @@ bool CombinerHelper::matchSextOfTrunc(const MachineOperand &MO,
   LLT DstTy = MRI.getType(Dst);
   LLT SrcTy = MRI.getType(Src);
 
+  // Combines without nsw trunc.
+  if (!(Trunc->getFlags() & MachineInstr::NoSWrap)) {
+    if (DstTy != SrcTy)
+      return false;
+
+    unsigned TruncWidth = MRI.getType(Trunc->getReg(0)).getScalarSizeInBits();
+    MatchInfo = [=](MachineIRBuilder &B) {
+      B.buildSExtInReg(Dst, Src, TruncWidth);
+    };
+    return true;
+  }
+
+  // Combines for nsw trunc.
+
   if (DstTy == SrcTy) {
     MatchInfo = [=](MachineIRBuilder &B) { B.buildCopy(Dst, Src); };
     return true;

llvm/test/CodeGen/AMDGPU/GlobalISel/combine-trunc-sext.mir

@@ -0,0 +1,117 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -run-pass=amdgpu-prelegalizer-combiner -verify-machineinstrs %s -o - | FileCheck -check-prefix=GCN %s
+
+---
+name: trunc_sext_i32_i16
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0
+
+    ; GCN-LABEL: name: trunc_sext_i32_i16
+    ; GCN: liveins: $vgpr0
+    ; GCN-NEXT: {{  $}}
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GCN-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 16
+    ; GCN-NEXT: $vgpr0 = COPY [[SEXT_INREG]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s16) = G_TRUNC %0
+    %2:_(s32) = G_SEXT %1
+    $vgpr0 = COPY %2
+...
+
+---
+name: trunc_sext_i32_i8
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0
+
+    ; GCN-LABEL: name: trunc_sext_i32_i8
+    ; GCN: liveins: $vgpr0
+    ; GCN-NEXT: {{  $}}
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GCN-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 8
+    ; GCN-NEXT: $vgpr0 = COPY [[SEXT_INREG]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s8) = G_TRUNC %0
+    %2:_(s32) = G_SEXT %1
+    $vgpr0 = COPY %2
+...
+
+---
+name: trunc_sext_i64_i32
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; GCN-LABEL: name: trunc_sext_i64_i32
+    ; GCN: liveins: $vgpr0_vgpr1
+    ; GCN-NEXT: {{  $}}
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
+    ; GCN-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s64) = G_SEXT_INREG [[COPY]], 32
+    ; GCN-NEXT: $vgpr0_vgpr1 = COPY [[SEXT_INREG]](s64)
+    %0:_(s64) = COPY $vgpr0_vgpr1
+    %1:_(s32) = G_TRUNC %0
+    %2:_(s64) = G_SEXT %1
+    $vgpr0_vgpr1 = COPY %2
+...
+
+---
+name: trunc_sext_v4i32_v4i16
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1_vgpr2_vgpr3
+
+    ; GCN-LABEL: name: trunc_sext_v4i32_v4i16
+    ; GCN: liveins: $vgpr0_vgpr1_vgpr2_vgpr3
+    ; GCN-NEXT: {{  $}}
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
+    ; GCN-NEXT: [[SEXT_INREG:%[0-9]+]]:_(<4 x s32>) = G_SEXT_INREG [[COPY]], 16
+    ; GCN-NEXT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[SEXT_INREG]](<4 x s32>)
+    %0:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
+    %1:_(<4 x s16>) = G_TRUNC %0
+    %2:_(<4 x s32>) = G_SEXT %1
+    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2
+...
+
+---
+name: trunc_sext_v4i16_v4i8
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; GCN-LABEL: name: trunc_sext_v4i16_v4i8
+    ; GCN: liveins: $vgpr0_vgpr1
+    ; GCN-NEXT: {{  $}}
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
+    ; GCN-NEXT: [[SEXT_INREG:%[0-9]+]]:_(<4 x s16>) = G_SEXT_INREG [[COPY]], 8
+    ; GCN-NEXT: $vgpr0_vgpr1 = COPY [[SEXT_INREG]](<4 x s16>)
+    %0:_(<4 x s16>) = COPY $vgpr0_vgpr1
+    %1:_(<4 x s8>) = G_TRUNC %0
+    %2:_(<4 x s16>) = G_SEXT %1
+    $vgpr0_vgpr1 = COPY %2
+...
+
+---
+name: trunc_sext_mismatching_types
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; GCN-LABEL: name: trunc_sext_mismatching_types
+    ; GCN: liveins: $vgpr0_vgpr1
+    ; GCN-NEXT: {{  $}}
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
+    ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s64)
+    ; GCN-NEXT: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[TRUNC]](s16)
+    ; GCN-NEXT: $vgpr0 = COPY [[SEXT]](s32)
+    %0:_(s64) = COPY $vgpr0_vgpr1
+    %1:_(s16) = G_TRUNC %0
+    %2:_(s32) = G_SEXT %1
+    $vgpr0 = COPY %2
+...