[llvm] c457c88 - [GlobalISel] Combine (sext (trunc x)) to (sext_inreg x) (#131622)

via llvm-commits llvm-commits at lists.llvm.org
Mon Mar 24 01:32:07 PDT 2025


Author: Pierre van Houtryve
Date: 2025-03-24T09:32:04+01:00
New Revision: c457c8895181aff3c02e9ffdb7e05f58957aa151

URL: https://github.com/llvm/llvm-project/commit/c457c8895181aff3c02e9ffdb7e05f58957aa151
DIFF: https://github.com/llvm/llvm-project/commit/c457c8895181aff3c02e9ffdb7e05f58957aa151.diff

LOG: [GlobalISel] Combine (sext (trunc x)) to (sext_inreg x) (#131622)

Split from #131312

Added: 
    llvm/test/CodeGen/AArch64/GlobalISel/combine-ext-trunc.mir
    llvm/test/CodeGen/AMDGPU/GlobalISel/combine-trunc-sext.mir

Modified: 
    llvm/include/llvm/Target/GlobalISel/Combine.td
    llvm/lib/CodeGen/GlobalISel/CombinerHelperCasts.cpp
    llvm/test/CodeGen/AArch64/GlobalISel/prelegalizercombiner-extending-loads.mir
    llvm/test/CodeGen/RISCV/GlobalISel/combine.mir

Removed: 
    llvm/test/CodeGen/AArch64/GlobalISel/combine-with-flags.mir


################################################################################
diff  --git a/llvm/include/llvm/Target/GlobalISel/Combine.td b/llvm/include/llvm/Target/GlobalISel/Combine.td
index 3590ab221ad44..660b03080f92e 100644
--- a/llvm/include/llvm/Target/GlobalISel/Combine.td
+++ b/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}); }])>;

diff  --git a/llvm/lib/CodeGen/GlobalISel/CombinerHelperCasts.cpp b/llvm/lib/CodeGen/GlobalISel/CombinerHelperCasts.cpp
index 7b4c427a9c504..576fd5fd81703 100644
--- a/llvm/lib/CodeGen/GlobalISel/CombinerHelperCasts.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/CombinerHelperCasts.cpp
@@ -36,6 +36,26 @@ bool CombinerHelper::matchSextOfTrunc(const MachineOperand &MO,
   LLT DstTy = MRI.getType(Dst);
   LLT SrcTy = MRI.getType(Src);
 
+  // Combines without nsw trunc.
+  if (!Trunc->getFlag(MachineInstr::NoSWrap)) {
+    if (DstTy != SrcTy ||
+        !isLegalOrBeforeLegalizer({TargetOpcode::G_SEXT_INREG, {DstTy, SrcTy}}))
+      return false;
+
+    // Do this for 8 bit values and up. We don't want to do it for e.g. G_TRUNC
+    // to i1.
+    unsigned TruncWidth = MRI.getType(Trunc->getReg(0)).getScalarSizeInBits();
+    if (TruncWidth < 8)
+      return false;
+
+    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;

diff  --git a/llvm/test/CodeGen/AArch64/GlobalISel/combine-with-flags.mir b/llvm/test/CodeGen/AArch64/GlobalISel/combine-ext-trunc.mir
similarity index 74%
rename from llvm/test/CodeGen/AArch64/GlobalISel/combine-with-flags.mir
rename to llvm/test/CodeGen/AArch64/GlobalISel/combine-ext-trunc.mir
index 8cb44605246ff..d034ec18aa271 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/combine-with-flags.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/combine-ext-trunc.mir
@@ -100,9 +100,8 @@ body:             |
     ; CHECK: liveins: $w0, $w1
     ; CHECK-NEXT: {{  $}}
     ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x0
-    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = nuw G_TRUNC [[COPY]](s64)
-    ; CHECK-NEXT: [[SEXT:%[0-9]+]]:_(s64) = G_SEXT [[TRUNC]](s32)
-    ; CHECK-NEXT: $x1 = COPY [[SEXT]](s64)
+    ; CHECK-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s64) = G_SEXT_INREG [[COPY]], 32
+    ; CHECK-NEXT: $x1 = COPY [[SEXT_INREG]](s64)
     %0:_(s64) = COPY $x0
     %2:_(s32) = nuw G_TRUNC %0
     %3:_(s64) = G_SEXT  %2
@@ -117,9 +116,8 @@ body:             |
     ; CHECK: liveins: $w0, $w1
     ; CHECK-NEXT: {{  $}}
     ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x0
-    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
-    ; CHECK-NEXT: [[SEXT:%[0-9]+]]:_(s64) = G_SEXT [[TRUNC]](s32)
-    ; CHECK-NEXT: $x1 = COPY [[SEXT]](s64)
+    ; CHECK-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s64) = G_SEXT_INREG [[COPY]], 32
+    ; CHECK-NEXT: $x1 = COPY [[SEXT_INREG]](s64)
     %0:_(s64) = COPY $x0
     %2:_(s32) = G_TRUNC %0
     %3:_(s64) = G_SEXT  %2
@@ -372,3 +370,150 @@ body:             |
     %3:_(s32) = G_SEXT  %2
     $w1 = COPY %3
 ...
+---
+name: trunc_sext_i32_i16
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0
+
+    ; CHECK-LABEL: name: trunc_sext_i32_i16
+    ; CHECK: liveins: $w0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $w0
+    ; CHECK-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 16
+    ; CHECK-NEXT: $w0 = COPY [[SEXT_INREG]](s32)
+    %0:_(s32) = COPY $w0
+    %1:_(s16) = G_TRUNC %0
+    %2:_(s32) = G_SEXT %1
+    $w0 = COPY %2
+...
+---
+name: trunc_sext_i32_i1
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0
+
+    ; CHECK-LABEL: name: trunc_sext_i32_i1
+    ; CHECK: liveins: $w0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $w0
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s1) = G_TRUNC [[COPY]](s32)
+    ; CHECK-NEXT: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[TRUNC]](s1)
+    ; CHECK-NEXT: $w0 = COPY [[SEXT]](s32)
+    %0:_(s32) = COPY $w0
+    %1:_(s1) = G_TRUNC %0
+    %2:_(s32) = G_SEXT %1
+    $w0 = COPY %2
+...
+---
+name: trunc_sext_i32_i2
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0
+
+    ; CHECK-LABEL: name: trunc_sext_i32_i2
+    ; CHECK: liveins: $w0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $w0
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s2) = G_TRUNC [[COPY]](s32)
+    ; CHECK-NEXT: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[TRUNC]](s2)
+    ; CHECK-NEXT: $w0 = COPY [[SEXT]](s32)
+    %0:_(s32) = COPY $w0
+    %1:_(s2) = G_TRUNC %0
+    %2:_(s32) = G_SEXT %1
+    $w0 = COPY %2
+...
+---
+name: trunc_sext_i32_i8
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0
+
+    ; CHECK-LABEL: name: trunc_sext_i32_i8
+    ; CHECK: liveins: $w0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $w0
+    ; CHECK-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 8
+    ; CHECK-NEXT: $w0 = COPY [[SEXT_INREG]](s32)
+    %0:_(s32) = COPY $w0
+    %1:_(s8) = G_TRUNC %0
+    %2:_(s32) = G_SEXT %1
+    $w0 = COPY %2
+...
+---
+name: trunc_sext_i64_i32
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0, $w1
+
+    ; CHECK-LABEL: name: trunc_sext_i64_i32
+    ; CHECK: liveins: $w0, $w1
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x0
+    ; CHECK-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s64) = G_SEXT_INREG [[COPY]], 32
+    ; CHECK-NEXT: $x0 = COPY [[SEXT_INREG]](s64)
+    %0:_(s64) = COPY $x0
+    %1:_(s32) = G_TRUNC %0
+    %2:_(s64) = G_SEXT %1
+    $x0 = COPY %2
+...
+---
+name: trunc_sext_v2i32_v2i16
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0, $w1
+
+    ; CHECK-LABEL: name: trunc_sext_v2i32_v2i16
+    ; CHECK: liveins: $w0, $w1
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $x0
+    ; CHECK-NEXT: [[SEXT_INREG:%[0-9]+]]:_(<2 x s32>) = G_SEXT_INREG [[COPY]], 16
+    ; CHECK-NEXT: $x0 = COPY [[SEXT_INREG]](<2 x s32>)
+    %0:_(<2 x s32>) = COPY $x0
+    %1:_(<2 x s16>) = G_TRUNC %0
+    %2:_(<2 x s32>) = G_SEXT %1
+    $x0 = COPY %2
+...
+---
+name: trunc_sext_v4i16_v4i8
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0, $w1
+
+    ; CHECK-LABEL: name: trunc_sext_v4i16_v4i8
+    ; CHECK: liveins: $w0, $w1
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $x0
+    ; CHECK-NEXT: [[SEXT_INREG:%[0-9]+]]:_(<4 x s16>) = G_SEXT_INREG [[COPY]], 8
+    ; CHECK-NEXT: $x0 = COPY [[SEXT_INREG]](<4 x s16>)
+    %0:_(<4 x s16>) = COPY $x0
+    %1:_(<4 x s8>) = G_TRUNC %0
+    %2:_(<4 x s16>) = G_SEXT %1
+    $x0 = COPY %2
+...
+---
+name: trunc_sext_mismatching_types
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $w0, $w1
+
+    ; CHECK-LABEL: name: trunc_sext_mismatching_types
+    ; CHECK: liveins: $w0, $w1
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x0
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s64)
+    ; CHECK-NEXT: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[TRUNC]](s16)
+    ; CHECK-NEXT: $w0 = COPY [[SEXT]](s32)
+    %0:_(s64) = COPY $x0
+    %1:_(s16) = G_TRUNC %0
+    %2:_(s32) = G_SEXT %1
+    $w0 = COPY %2
+...

diff  --git a/llvm/test/CodeGen/AArch64/GlobalISel/prelegalizercombiner-extending-loads.mir b/llvm/test/CodeGen/AArch64/GlobalISel/prelegalizercombiner-extending-loads.mir
index 47c85f7678593..28c7485bbf60c 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/prelegalizercombiner-extending-loads.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/prelegalizercombiner-extending-loads.mir
@@ -469,10 +469,8 @@ body: |
     ; CHECK-NEXT: {{  $}}
     ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
     ; CHECK-NEXT: [[ZEXTLOAD:%[0-9]+]]:_(s64) = G_ZEXTLOAD [[COPY]](p0) :: (load (s8))
-    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[ZEXTLOAD]](s64)
-    ; CHECK-NEXT: [[SEXT:%[0-9]+]]:_(s64) = G_SEXT [[TRUNC]](s32)
     ; CHECK-NEXT: $x0 = COPY [[ZEXTLOAD]](s64)
-    ; CHECK-NEXT: $x1 = COPY [[SEXT]](s64)
+    ; CHECK-NEXT: $x1 = COPY [[ZEXTLOAD]](s64)
     %0:_(p0) = COPY $x0
     %1:_(s32) = G_ZEXTLOAD %0 :: (load (s8))
     %2:_(s64) = G_ZEXT %1

diff  --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-trunc-sext.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-trunc-sext.mir
new file mode 100644
index 0000000000000..b2277c4e1141b
--- /dev/null
+++ b/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
+...

diff  --git a/llvm/test/CodeGen/RISCV/GlobalISel/combine.mir b/llvm/test/CodeGen/RISCV/GlobalISel/combine.mir
index ef3fc4c9d5fae..cd574945965b5 100644
--- a/llvm/test/CodeGen/RISCV/GlobalISel/combine.mir
+++ b/llvm/test/CodeGen/RISCV/GlobalISel/combine.mir
@@ -8,9 +8,8 @@ body:             |
 
     ; RV64-LABEL: name: nneg_zext
     ; RV64: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
-    ; RV64-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
-    ; RV64-NEXT: [[SEXT:%[0-9]+]]:_(s64) = G_SEXT [[TRUNC]](s32)
-    ; RV64-NEXT: $x10 = COPY [[SEXT]](s64)
+    ; RV64-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s64) = G_SEXT_INREG [[COPY]], 32
+    ; RV64-NEXT: $x10 = COPY [[SEXT_INREG]](s64)
     ; RV64-NEXT: PseudoRET implicit $x10
     %0:_(s64) = COPY $x10
     %2:_(s32) = G_TRUNC %0


        


More information about the llvm-commits mailing list