AMDGPU/GlobalISel: Fix bit ops for non-power-of-2 sizes

llvm-svn: 354825

llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp

@@ -174,6 +174,7 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST,
     .clampScalar(0, S32, S64)
     .moreElementsIf(isSmallOddVector(0), oneMoreElement(0))
     .fewerElementsIf(vectorWiderThan(0, 32), fewerEltsToSize64Vector(0))
+    .widenScalarToNextPow2(0)
     .scalarize(0);
 
   getActionDefinitionsBuilder({G_UADDO, G_SADDO, G_USUBO, G_SSUBO,
@@ -270,6 +271,7 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST,
     .legalFor({{S64, S32}, {S32, S16}, {S64, S16},
                {S32, S1}, {S64, S1}, {S16, S1},
                // FIXME: Hack
+               {S64, LLT::scalar(33)},
                {S32, S8}, {S128, S32}, {S128, S64}, {S32, LLT::scalar(24)}})
     .scalarize(0);
 

llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-and.mir

@@ -147,6 +147,29 @@ body: |
     $vgpr0 = COPY %5
 ...
 
+---
+name: test_and_s48
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
+
+    ; CHECK-LABEL: name: test_and_s48
+    ; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
+    ; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
+    ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY [[COPY]](s64)
+    ; CHECK: [[COPY3:%[0-9]+]]:_(s64) = COPY [[COPY1]](s64)
+    ; CHECK: [[AND:%[0-9]+]]:_(s64) = G_AND [[COPY2]], [[COPY3]]
+    ; CHECK: [[COPY4:%[0-9]+]]:_(s64) = COPY [[AND]](s64)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[COPY4]](s64)
+    %0:_(s64) = COPY $vgpr0_vgpr1
+    %1:_(s64) = COPY $vgpr2_vgpr3
+    %2:_(s48) = G_TRUNC %0
+    %3:_(s48) = G_TRUNC %1
+    %4:_(s48) = G_AND %2, %3
+    %5:_(s64) = G_ANYEXT %4
+    $vgpr0_vgpr1 = COPY %5
+...
+
 ---
 name: test_and_v2s32
 body: |

llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ctlz-zero-undef.mir

@@ -205,8 +205,10 @@ body: |
     ; CHECK: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[USUBO]](s32), [[USUBE]](s32)
     ; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 4294967295
     ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY [[MV]](s64)
-    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[COPY2]], [[C2]]
+    ; CHECK: [[COPY3:%[0-9]+]]:_(s64) = COPY [[C2]](s64)
-    ; CHECK: $vgpr0_vgpr1 = COPY [[AND1]](s64)
+    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[COPY2]], [[COPY3]]
+    ; CHECK: [[COPY4:%[0-9]+]]:_(s64) = COPY [[AND1]](s64)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[COPY4]](s64)
     %0:_(s64) = COPY $vgpr0_vgpr1
     %1:_(s33) = G_TRUNC %0
     %2:_(s33) = G_CTLZ_ZERO_UNDEF %1

llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ctlz.mir

@@ -205,8 +205,10 @@ body: |
     ; CHECK: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[USUBO]](s32), [[USUBE]](s32)
     ; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 4294967295
     ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY [[MV]](s64)
-    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[COPY2]], [[C2]]
+    ; CHECK: [[COPY3:%[0-9]+]]:_(s64) = COPY [[C2]](s64)
-    ; CHECK: $vgpr0_vgpr1 = COPY [[AND1]](s64)
+    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[COPY2]], [[COPY3]]
+    ; CHECK: [[COPY4:%[0-9]+]]:_(s64) = COPY [[AND1]](s64)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[COPY4]](s64)
     %0:_(s64) = COPY $vgpr0_vgpr1
     %1:_(s33) = G_TRUNC %0
     %2:_(s33) = G_CTLZ %1

llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ctpop.mir

@@ -191,8 +191,10 @@ body: |
     ; CHECK: [[ZEXT:%[0-9]+]]:_(s64) = G_ZEXT [[CTPOP]](s32)
     ; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 4294967295
     ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY [[ZEXT]](s64)
-    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[COPY2]], [[C1]]
+    ; CHECK: [[COPY3:%[0-9]+]]:_(s64) = COPY [[C1]](s64)
-    ; CHECK: $vgpr0_vgpr1 = COPY [[AND1]](s64)
+    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[COPY2]], [[COPY3]]
+    ; CHECK: [[COPY4:%[0-9]+]]:_(s64) = COPY [[AND1]](s64)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[COPY4]](s64)
     %0:_(s64) = COPY $vgpr0_vgpr1
     %1:_(s33) = G_TRUNC %0
     %2:_(s33) = G_CTPOP %1

llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-cttz-zero-undef.mir

@@ -191,8 +191,10 @@ body: |
     ; CHECK: [[ZEXT:%[0-9]+]]:_(s64) = G_ZEXT [[CTTZ_ZERO_UNDEF]](s32)
     ; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 4294967295
     ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY [[ZEXT]](s64)
-    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[COPY2]], [[C1]]
+    ; CHECK: [[COPY3:%[0-9]+]]:_(s64) = COPY [[C1]](s64)
-    ; CHECK: $vgpr0_vgpr1 = COPY [[AND1]](s64)
+    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[COPY2]], [[COPY3]]
+    ; CHECK: [[COPY4:%[0-9]+]]:_(s64) = COPY [[AND1]](s64)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[COPY4]](s64)
     %0:_(s64) = COPY $vgpr0_vgpr1
     %1:_(s33) = G_TRUNC %0
     %2:_(s33) = G_CTTZ_ZERO_UNDEF %1

llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-cttz.mir

@@ -201,8 +201,10 @@ body: |
     ; CHECK: [[ZEXT:%[0-9]+]]:_(s64) = G_ZEXT [[CTTZ]](s32)
     ; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 4294967295
     ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY [[ZEXT]](s64)
-    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[COPY2]], [[C2]]
+    ; CHECK: [[COPY3:%[0-9]+]]:_(s64) = COPY [[C2]](s64)
-    ; CHECK: $vgpr0_vgpr1 = COPY [[AND1]](s64)
+    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[COPY2]], [[COPY3]]
+    ; CHECK: [[COPY4:%[0-9]+]]:_(s64) = COPY [[AND1]](s64)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[COPY4]](s64)
     %0:_(s64) = COPY $vgpr0_vgpr1
     %1:_(s33) = G_TRUNC %0
     %2:_(s33) = G_CTTZ %1

llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-or.mir

@@ -147,6 +147,29 @@ body: |
     $vgpr0 = COPY %5
 ...
 
+---
+name: test_or_s48
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
+
+    ; CHECK-LABEL: name: test_or_s48
+    ; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
+    ; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
+    ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY [[COPY]](s64)
+    ; CHECK: [[COPY3:%[0-9]+]]:_(s64) = COPY [[COPY1]](s64)
+    ; CHECK: [[OR:%[0-9]+]]:_(s64) = G_OR [[COPY2]], [[COPY3]]
+    ; CHECK: [[COPY4:%[0-9]+]]:_(s64) = COPY [[OR]](s64)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[COPY4]](s64)
+    %0:_(s64) = COPY $vgpr0_vgpr1
+    %1:_(s64) = COPY $vgpr2_vgpr3
+    %2:_(s48) = G_TRUNC %0
+    %3:_(s48) = G_TRUNC %1
+    %4:_(s48) = G_OR %2, %3
+    %5:_(s64) = G_ANYEXT %4
+    $vgpr0_vgpr1 = COPY %5
+...
+
 ---
 name: test_or_v2s32
 body: |

llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-unmerge-values.mir

@@ -199,24 +199,35 @@ body: |
     liveins: $vgpr0
     ; CHECK-LABEL: name: test_unmerge_s1_s3
     ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
-    ; CHECK: [[TRUNC:%[0-9]+]]:_(s3) = G_TRUNC [[COPY]](s32)
+    ; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 15
-    ; CHECK: [[ZEXT:%[0-9]+]]:_(s48) = G_ZEXT [[TRUNC]](s3)
+    ; CHECK: [[TRUNC:%[0-9]+]]:_(s48) = G_TRUNC [[C]](s64)
-    ; CHECK: [[C:%[0-9]+]]:_(s48) = G_CONSTANT i48 15
+    ; CHECK: [[TRUNC1:%[0-9]+]]:_(s32) = G_TRUNC [[TRUNC]](s48)
-    ; CHECK: [[SHL:%[0-9]+]]:_(s48) = G_SHL [[ZEXT]], [[C]](s48)
+    ; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 7
-    ; CHECK: [[OR:%[0-9]+]]:_(s48) = G_OR [[ZEXT]], [[SHL]]
+    ; CHECK: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[COPY]](s32)
-    ; CHECK: [[C1:%[0-9]+]]:_(s48) = G_CONSTANT i48 30
+    ; CHECK: [[AND:%[0-9]+]]:_(s64) = G_AND [[ANYEXT]], [[C1]]
-    ; CHECK: [[SHL1:%[0-9]+]]:_(s48) = G_SHL [[OR]], [[C1]](s48)
+    ; CHECK: [[SHL:%[0-9]+]]:_(s64) = G_SHL [[AND]], [[TRUNC1]](s32)
-    ; CHECK: [[OR1:%[0-9]+]]:_(s48) = G_OR [[OR]], [[SHL1]]
+    ; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 7
-    ; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[OR1]](s48)
+    ; CHECK: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[COPY]](s32)
-    ; CHECK: [[TRUNC1:%[0-9]+]]:_(s1) = G_TRUNC [[UV]](s16)
+    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[ANYEXT1]], [[C2]]
-    ; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC1]](s1)
+    ; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY [[SHL]](s64)
-    ; CHECK: [[TRUNC2:%[0-9]+]]:_(s1) = G_TRUNC [[UV1]](s16)
+    ; CHECK: [[OR:%[0-9]+]]:_(s64) = G_OR [[AND1]], [[COPY1]]
-    ; CHECK: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s1)
+    ; CHECK: [[TRUNC2:%[0-9]+]]:_(s48) = G_TRUNC [[OR]](s64)
-    ; CHECK: [[TRUNC3:%[0-9]+]]:_(s1) = G_TRUNC [[UV2]](s16)
+    ; CHECK: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 30
-    ; CHECK: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC3]](s1)
+    ; CHECK: [[TRUNC3:%[0-9]+]]:_(s48) = G_TRUNC [[C3]](s64)
-    ; CHECK: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; CHECK: [[TRUNC4:%[0-9]+]]:_(s32) = G_TRUNC [[TRUNC3]](s48)
-    ; CHECK: $vgpr1 = COPY [[ANYEXT1]](s32)
+    ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY [[OR]](s64)
-    ; CHECK: $vgpr2 = COPY [[ANYEXT2]](s32)
+    ; CHECK: [[SHL1:%[0-9]+]]:_(s64) = G_SHL [[COPY2]], [[TRUNC4]](s32)
+    ; CHECK: [[COPY3:%[0-9]+]]:_(s64) = COPY [[OR]](s64)
+    ; CHECK: [[COPY4:%[0-9]+]]:_(s64) = COPY [[SHL1]](s64)
+    ; CHECK: [[OR1:%[0-9]+]]:_(s64) = G_OR [[COPY3]], [[COPY4]]
+    ; CHECK: [[TRUNC5:%[0-9]+]]:_(s48) = G_TRUNC [[OR1]](s64)
+    ; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[TRUNC5]](s48)
+    ; CHECK: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[UV]](s16)
+    ; CHECK: [[ANYEXT3:%[0-9]+]]:_(s32) = G_ANYEXT [[UV1]](s16)
+    ; CHECK: [[ANYEXT4:%[0-9]+]]:_(s32) = G_ANYEXT [[UV2]](s16)
+    ; CHECK: $vgpr0 = COPY [[ANYEXT2]](s32)
+    ; CHECK: $vgpr1 = COPY [[ANYEXT3]](s32)
+    ; CHECK: $vgpr2 = COPY [[ANYEXT4]](s32)
     %0:_(s32) = COPY $vgpr0
     %1:_(s3) = G_TRUNC %0
     %2:_(s1), %3:_(s1), %4:_(s1) = G_UNMERGE_VALUES %1

llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-xor.mir

@@ -147,6 +147,29 @@ body: |
     $vgpr0 = COPY %5
 ...
 
+---
+name: test_xor_s48
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
+
+    ; CHECK-LABEL: name: test_xor_s48
+    ; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
+    ; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
+    ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY [[COPY]](s64)
+    ; CHECK: [[COPY3:%[0-9]+]]:_(s64) = COPY [[COPY1]](s64)
+    ; CHECK: [[XOR:%[0-9]+]]:_(s64) = G_XOR [[COPY2]], [[COPY3]]
+    ; CHECK: [[COPY4:%[0-9]+]]:_(s64) = COPY [[XOR]](s64)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[COPY4]](s64)
+    %0:_(s64) = COPY $vgpr0_vgpr1
+    %1:_(s64) = COPY $vgpr2_vgpr3
+    %2:_(s48) = G_TRUNC %0
+    %3:_(s48) = G_TRUNC %1
+    %4:_(s48) = G_XOR %2, %3
+    %5:_(s64) = G_ANYEXT %4
+    $vgpr0_vgpr1 = COPY %5
+...
+
 ---
 name: test_xor_v2s32
 body: |