maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-unmerge-values.mir

495 lines
23 KiB
Plaintext
Raw Normal View History

AMDGPU/GlobalISel: Make some G_MERGE_VALUEs legal llvm-svn: 327267
2018-03-12 21:35:43 +08:00
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
GlobalISel: Implement widenScalar for G_UNMERGE_VALUES For the scalar case only. Also move the similar G_MERGE_VALUES handling to a separate function and cleanup to make them look more similar. llvm-svn: 352979
2019-02-03 08:07:33 +08:00
# RUN: llc -mtriple=amdgcn-- -O0 -run-pass=legalizer -global-isel-abort=0 -o - %s | FileCheck %s
AMDGPU/GlobalISel: Make some G_MERGE_VALUEs legal llvm-svn: 327267
2018-03-12 21:35:43 +08:00
---
AMDGPU/GlobalISel: Fix some crashs in g_unmerge_values/g_merge_values This was crashing in the predicate function assuming the value is a vector. Copy more of what AArch64 uses. This probably needs more refinement later, but I don't exactly understand what it means in some cases, particularly since any legalization for these seems to be missing. llvm-svn: 351693
2019-01-21 02:40:36 +08:00
name: test_unmerge_s32_s64
AMDGPU/GlobalISel: Make some G_MERGE_VALUEs legal llvm-svn: 327267
2018-03-12 21:35:43 +08:00
body: |
bb.0:
AMDGPU/GlobalISel: Fix some crashs in g_unmerge_values/g_merge_values This was crashing in the predicate function assuming the value is a vector. Copy more of what AArch64 uses. This probably needs more refinement later, but I don't exactly understand what it means in some cases, particularly since any legalization for these seems to be missing. llvm-svn: 351693
2019-01-21 02:40:36 +08:00
; CHECK-LABEL: name: test_unmerge_s32_s64
AMDGPU/GlobalISel: Make some G_MERGE_VALUEs legal llvm-svn: 327267
2018-03-12 21:35:43 +08:00
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[C]](s64)
; CHECK: $vgpr0 = COPY [[UV]](s32)
AMDGPU/GlobalISel: Fix some crashs in g_unmerge_values/g_merge_values This was crashing in the predicate function assuming the value is a vector. Copy more of what AArch64 uses. This probably needs more refinement later, but I don't exactly understand what it means in some cases, particularly since any legalization for these seems to be missing. llvm-svn: 351693
2019-01-21 02:40:36 +08:00
; CHECK: $vgpr1 = COPY [[UV1]](s32)
AMDGPU/GlobalISel: Make some G_MERGE_VALUEs legal llvm-svn: 327267
2018-03-12 21:35:43 +08:00
%0:_(s64) = G_CONSTANT i64 0
%1:_(s32), %2:_(s32) = G_UNMERGE_VALUES %0:_(s64)
$vgpr0 = COPY %1(s32)
AMDGPU/GlobalISel: Fix some crashs in g_unmerge_values/g_merge_values This was crashing in the predicate function assuming the value is a vector. Copy more of what AArch64 uses. This probably needs more refinement later, but I don't exactly understand what it means in some cases, particularly since any legalization for these seems to be missing. llvm-svn: 351693
2019-01-21 02:40:36 +08:00
$vgpr1 = COPY %2(s32)
...
---
name: test_unmerge_s32_v2s32
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_unmerge_s32_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: $vgpr0 = COPY [[UV]](s32)
; CHECK: $vgpr21 = COPY [[UV1]](s32)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(s32), %2:_(s32) = G_UNMERGE_VALUES %0
$vgpr0 = COPY %1
$vgpr21= COPY %2
...
---
name: test_unmerge_s16_v2s16
body: |
bb.0:
liveins: $vgpr0
; CHECK-LABEL: name: test_unmerge_s16_v2s16
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
GlobalISel: Lower scalarizing unmerge of a vector to shifts AMDGPU sometimes has legal s16 and <2 x s16> operations, but all registers are really 32-bit. An unmerge destination really should ben widened to a 32-bit register. If widening a scalarizing vector with a target size that matches the vector size, bitcast to integer and extract the relevant bits with shifts. I'm not sure if this is the right place for this. This could arguably be part of widenScalar for the result. I also have a growing feeling that we're missing a bitcast legalize action. llvm-svn: 367604
2019-08-02 03:10:05 +08:00
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; CHECK: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY [[BITCAST]](s32)
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
; CHECK: $vgpr0 = COPY [[COPY1]](s32)
; CHECK: $vgpr1 = COPY [[COPY2]](s32)
AMDGPU/GlobalISel: Fix some crashs in g_unmerge_values/g_merge_values This was crashing in the predicate function assuming the value is a vector. Copy more of what AArch64 uses. This probably needs more refinement later, but I don't exactly understand what it means in some cases, particularly since any legalization for these seems to be missing. llvm-svn: 351693
2019-01-21 02:40:36 +08:00
%0:_(<2 x s16>) = COPY $vgpr0
%1:_(s16), %2:_(s16) = G_UNMERGE_VALUES %0
%3:_(s32) = G_ANYEXT %1
%4:_(s32) = G_ANYEXT %2
$vgpr0 = COPY %3
$vgpr1 = COPY %4
...
---
name: test_unmerge_s16_v3s16
body: |
bb.0:
; CHECK-LABEL: name: test_unmerge_s16_v3s16
GlobalISel: Implement moreElementsVector for implicit_def llvm-svn: 353754
2019-02-12 06:00:39 +08:00
; CHECK: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; CHECK: [[EXTRACT:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[DEF]](<4 x s16>), 0
; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[EXTRACT]](<3 x s16>)
AMDGPU/GlobalISel: Fix some crashs in g_unmerge_values/g_merge_values This was crashing in the predicate function assuming the value is a vector. Copy more of what AArch64 uses. This probably needs more refinement later, but I don't exactly understand what it means in some cases, particularly since any legalization for these seems to be missing. llvm-svn: 351693
2019-01-21 02:40:36 +08:00
; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UV]](s16)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[UV1]](s16)
; CHECK: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[UV2]](s16)
; CHECK: $vgpr0 = COPY [[ANYEXT]](s32)
; CHECK: $vgpr1 = COPY [[ANYEXT1]](s32)
; CHECK: $vgpr2 = COPY [[ANYEXT2]](s32)
%0:_(<3 x s16>) = G_IMPLICIT_DEF
%1:_(s16), %2:_(s16), %3:_(s16) = G_UNMERGE_VALUES %0
%4:_(s32) = G_ANYEXT %1
%5:_(s32) = G_ANYEXT %2
%6:_(s32) = G_ANYEXT %3
$vgpr0 = COPY %4
$vgpr1 = COPY %5
$vgpr2 = COPY %6
AMDGPU/GlobalISel: Make some G_MERGE_VALUEs legal llvm-svn: 327267
2018-03-12 21:35:43 +08:00
...
GlobalISel: Implement widenScalar for G_UNMERGE_VALUES For the scalar case only. Also move the similar G_MERGE_VALUES handling to a separate function and cleanup to make them look more similar. llvm-svn: 352979
2019-02-03 08:07:33 +08:00
---
GlobalISel: Lower scalarizing unmerge of a vector to shifts AMDGPU sometimes has legal s16 and <2 x s16> operations, but all registers are really 32-bit. An unmerge destination really should ben widened to a 32-bit register. If widening a scalarizing vector with a target size that matches the vector size, bitcast to integer and extract the relevant bits with shifts. I'm not sure if this is the right place for this. This could arguably be part of widenScalar for the result. I also have a growing feeling that we're missing a bitcast legalize action. llvm-svn: 367604
2019-08-02 03:10:05 +08:00
name: test_unmerge_s16_v4s16
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_unmerge_s16_v4s16
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
GlobalISel: Partially implement fewerElementsVector G_UNMERGE_VALUES Odd sized vectors aren't handled yet. llvm-svn: 368713
2019-08-14 00:26:28 +08:00
; CHECK: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; CHECK: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
; CHECK: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
; CHECK: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY [[BITCAST]](s32)
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[BITCAST1]](s32)
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY [[LSHR1]](s32)
; CHECK: $vgpr0 = COPY [[COPY1]](s32)
; CHECK: $vgpr1 = COPY [[COPY2]](s32)
; CHECK: $vgpr2 = COPY [[COPY3]](s32)
; CHECK: $vgpr3 = COPY [[COPY4]](s32)
GlobalISel: Lower scalarizing unmerge of a vector to shifts AMDGPU sometimes has legal s16 and <2 x s16> operations, but all registers are really 32-bit. An unmerge destination really should ben widened to a 32-bit register. If widening a scalarizing vector with a target size that matches the vector size, bitcast to integer and extract the relevant bits with shifts. I'm not sure if this is the right place for this. This could arguably be part of widenScalar for the result. I also have a growing feeling that we're missing a bitcast legalize action. llvm-svn: 367604
2019-08-02 03:10:05 +08:00
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
%1:_(s16), %2:_(s16), %3:_(s16), %4:_(s16) = G_UNMERGE_VALUES %0
%5:_(s32) = G_ANYEXT %1
%6:_(s32) = G_ANYEXT %2
%7:_(s32) = G_ANYEXT %3
%8:_(s32) = G_ANYEXT %4
$vgpr0 = COPY %5
$vgpr1 = COPY %6
$vgpr2 = COPY %7
$vgpr3 = COPY %8
...
---
name: test_unmerge_s16_v6s16
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_unmerge_s16_v6s16
; CHECK: [[COPY:%[0-9]+]]:_(<6 x s16>) = COPY $vgpr0_vgpr1_vgpr2
GlobalISel: Partially implement fewerElementsVector G_UNMERGE_VALUES Odd sized vectors aren't handled yet. llvm-svn: 368713
2019-08-14 00:26:28 +08:00
; CHECK: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>), [[UV2:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<6 x s16>)
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; CHECK: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
; CHECK: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
; CHECK: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
; CHECK: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
; CHECK: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY [[BITCAST]](s32)
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[BITCAST1]](s32)
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY [[LSHR1]](s32)
; CHECK: [[COPY5:%[0-9]+]]:_(s32) = COPY [[BITCAST2]](s32)
; CHECK: [[COPY6:%[0-9]+]]:_(s32) = COPY [[LSHR2]](s32)
; CHECK: $vgpr0 = COPY [[COPY1]](s32)
; CHECK: $vgpr1 = COPY [[COPY2]](s32)
; CHECK: $vgpr2 = COPY [[COPY3]](s32)
; CHECK: $vgpr3 = COPY [[COPY4]](s32)
; CHECK: $vgpr4 = COPY [[COPY5]](s32)
; CHECK: $vgpr5 = COPY [[COPY6]](s32)
GlobalISel: Lower scalarizing unmerge of a vector to shifts AMDGPU sometimes has legal s16 and <2 x s16> operations, but all registers are really 32-bit. An unmerge destination really should ben widened to a 32-bit register. If widening a scalarizing vector with a target size that matches the vector size, bitcast to integer and extract the relevant bits with shifts. I'm not sure if this is the right place for this. This could arguably be part of widenScalar for the result. I also have a growing feeling that we're missing a bitcast legalize action. llvm-svn: 367604
2019-08-02 03:10:05 +08:00
%0:_(<6 x s16>) = COPY $vgpr0_vgpr1_vgpr2
%1:_(s16), %2:_(s16), %3:_(s16), %4:_(s16), %5:_(s16), %6:_(s16) = G_UNMERGE_VALUES %0
%7:_(s32) = G_ANYEXT %1
%8:_(s32) = G_ANYEXT %2
%9:_(s32) = G_ANYEXT %3
%10:_(s32) = G_ANYEXT %4
%11:_(s32) = G_ANYEXT %5
%12:_(s32) = G_ANYEXT %6
$vgpr0 = COPY %7
$vgpr1 = COPY %8
$vgpr2 = COPY %9
$vgpr3 = COPY %10
$vgpr4 = COPY %11
$vgpr5 = COPY %12
...
---
GlobalISel: Implement widenScalar for G_UNMERGE_VALUES For the scalar case only. Also move the similar G_MERGE_VALUES handling to a separate function and cleanup to make them look more similar. llvm-svn: 352979
2019-02-03 08:07:33 +08:00
name: test_unmerge_s8_s16
body: |
bb.0:
liveins: $vgpr0
; CHECK-LABEL: name: test_unmerge_s8_s16
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY1]], [[C]]
; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C1]](s32)
; CHECK: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[OR]](s32)
; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UV]](s16)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[UV1]](s16)
; CHECK: $vgpr0 = COPY [[ANYEXT]](s32)
; CHECK: $vgpr1 = COPY [[ANYEXT1]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s16) = G_TRUNC %0
%2:_(s8), %3:_(s8) = G_UNMERGE_VALUES %1
%4:_(s32) = G_ANYEXT %2
%5:_(s32) = G_ANYEXT %3
$vgpr0 = COPY %4
$vgpr1 = COPY %5
...
---
name: test_unmerge_s8_s32
body: |
bb.0:
liveins: $vgpr0
; CHECK-LABEL: name: test_unmerge_s8_s32
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[ZEXT:%[0-9]+]]:_(s64) = G_ZEXT [[COPY]](s32)
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 8
; CHECK: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[C]](s64)
; CHECK: [[SHL:%[0-9]+]]:_(s64) = G_SHL [[ZEXT]], [[TRUNC]](s32)
; CHECK: [[OR:%[0-9]+]]:_(s64) = G_OR [[ZEXT]], [[SHL]]
; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
; CHECK: [[TRUNC1:%[0-9]+]]:_(s32) = G_TRUNC [[C1]](s64)
; CHECK: [[SHL1:%[0-9]+]]:_(s64) = G_SHL [[OR]], [[TRUNC1]](s32)
; CHECK: [[OR1:%[0-9]+]]:_(s64) = G_OR [[OR]], [[SHL1]]
; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 24
; CHECK: [[TRUNC2:%[0-9]+]]:_(s32) = G_TRUNC [[C2]](s64)
; CHECK: [[SHL2:%[0-9]+]]:_(s64) = G_SHL [[OR1]], [[TRUNC2]](s32)
; CHECK: [[OR2:%[0-9]+]]:_(s64) = G_OR [[OR1]], [[SHL2]]
; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[OR2]](s64)
; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UV]](s16)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[UV1]](s16)
; CHECK: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[UV2]](s16)
; CHECK: [[ANYEXT3:%[0-9]+]]:_(s32) = G_ANYEXT [[UV3]](s16)
; CHECK: $vgpr0 = COPY [[ANYEXT]](s32)
; CHECK: $vgpr1 = COPY [[ANYEXT1]](s32)
; CHECK: $vgpr2 = COPY [[ANYEXT2]](s32)
; CHECK: $vgpr3 = COPY [[ANYEXT3]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s8), %2:_(s8), %3:_(s8), %4:_(s8) = G_UNMERGE_VALUES %0
%5:_(s32) = G_ANYEXT %1
%6:_(s32) = G_ANYEXT %2
%7:_(s32) = G_ANYEXT %3
%8:_(s32) = G_ANYEXT %4
$vgpr0 = COPY %5
$vgpr1 = COPY %6
$vgpr2 = COPY %7
$vgpr3 = COPY %8
...
---
name: test_unmerge_s16_s32
body: |
bb.0:
liveins: $vgpr0
; CHECK-LABEL: name: test_unmerge_s16_s32
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY]](s32)
; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UV]](s16)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[UV1]](s16)
; CHECK: $vgpr0 = COPY [[ANYEXT]](s32)
; CHECK: $vgpr1 = COPY [[ANYEXT1]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s16), %2:_(s16) = G_UNMERGE_VALUES %0
%3:_(s32) = G_ANYEXT %1
%4:_(s32) = G_ANYEXT %2
$vgpr0 = COPY %3
$vgpr1 = COPY %4
...
---
name: test_unmerge_s16_s64
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_unmerge_s16_s64
; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY]](s64)
; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UV]](s16)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[UV1]](s16)
; CHECK: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[UV2]](s16)
; CHECK: [[ANYEXT3:%[0-9]+]]:_(s32) = G_ANYEXT [[UV3]](s16)
; CHECK: $vgpr0 = COPY [[ANYEXT]](s32)
; CHECK: $vgpr1 = COPY [[ANYEXT1]](s32)
; CHECK: $vgpr2 = COPY [[ANYEXT2]](s32)
; CHECK: $vgpr3 = COPY [[ANYEXT3]](s32)
%0:_(s64) = COPY $vgpr0_vgpr1
%1:_(s16), %2:_(s16), %3:_(s16), %4:_(s16) = G_UNMERGE_VALUES %0
%5:_(s32) = G_ANYEXT %1
%6:_(s32) = G_ANYEXT %2
%7:_(s32) = G_ANYEXT %3
%8:_(s32) = G_ANYEXT %4
$vgpr0 = COPY %5
$vgpr1 = COPY %6
$vgpr2 = COPY %7
$vgpr3 = COPY %8
...
---
name: test_unmerge_s1_s3
body: |
bb.0:
liveins: $vgpr0
; CHECK-LABEL: name: test_unmerge_s1_s3
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
AMDGPU/GlobalISel: Fix bit ops for non-power-of-2 sizes llvm-svn: 354825
2019-02-26 05:32:48 +08:00
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 15
; CHECK: [[TRUNC:%[0-9]+]]:_(s48) = G_TRUNC [[C]](s64)
; CHECK: [[TRUNC1:%[0-9]+]]:_(s32) = G_TRUNC [[TRUNC]](s48)
; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 7
; CHECK: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[COPY]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s64) = G_AND [[ANYEXT]], [[C1]]
; CHECK: [[SHL:%[0-9]+]]:_(s64) = G_SHL [[AND]], [[TRUNC1]](s32)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[COPY]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[ANYEXT1]], [[C1]]
AMDGPU/GlobalISel: Fix bit ops for non-power-of-2 sizes llvm-svn: 354825
2019-02-26 05:32:48 +08:00
; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY [[SHL]](s64)
; CHECK: [[OR:%[0-9]+]]:_(s64) = G_OR [[AND1]], [[COPY1]]
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 30
; CHECK: [[TRUNC2:%[0-9]+]]:_(s48) = G_TRUNC [[C2]](s64)
[GlobalISel] Fix legalizer artifact combiner from crashing with invalid dead instructions. The artifact combiners push instructions which have been marked for deletion onto an list for the legalizer to deal with on return. However, for trunc(ext) combines the combiner routine recursively calls itself. When it does this the dead instructions list may not be empty, and the other combiners don't expect to be dealing with essentially invalid MIR (multiple vreg defs etc). This change fixes it by ensuring that the dead instructions are processed on entry into tryCombineInstruction. As a result, this fix exposed a few places in tests where G_TRUNC instructions were not being deleted even though they were dead. Differential Revision: https://reviews.llvm.org/D59892 llvm-svn: 357101
2019-03-28 01:47:42 +08:00
; CHECK: [[TRUNC3:%[0-9]+]]:_(s32) = G_TRUNC [[TRUNC2]](s48)
AMDGPU/GlobalISel: Fix bit ops for non-power-of-2 sizes llvm-svn: 354825
2019-02-26 05:32:48 +08:00
; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY [[OR]](s64)
[GlobalISel] Fix legalizer artifact combiner from crashing with invalid dead instructions. The artifact combiners push instructions which have been marked for deletion onto an list for the legalizer to deal with on return. However, for trunc(ext) combines the combiner routine recursively calls itself. When it does this the dead instructions list may not be empty, and the other combiners don't expect to be dealing with essentially invalid MIR (multiple vreg defs etc). This change fixes it by ensuring that the dead instructions are processed on entry into tryCombineInstruction. As a result, this fix exposed a few places in tests where G_TRUNC instructions were not being deleted even though they were dead. Differential Revision: https://reviews.llvm.org/D59892 llvm-svn: 357101
2019-03-28 01:47:42 +08:00
; CHECK: [[SHL1:%[0-9]+]]:_(s64) = G_SHL [[COPY2]], [[TRUNC3]](s32)
AMDGPU/GlobalISel: Fix bit ops for non-power-of-2 sizes llvm-svn: 354825
2019-02-26 05:32:48 +08:00
; 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]]
[GlobalISel] Fix legalizer artifact combiner from crashing with invalid dead instructions. The artifact combiners push instructions which have been marked for deletion onto an list for the legalizer to deal with on return. However, for trunc(ext) combines the combiner routine recursively calls itself. When it does this the dead instructions list may not be empty, and the other combiners don't expect to be dealing with essentially invalid MIR (multiple vreg defs etc). This change fixes it by ensuring that the dead instructions are processed on entry into tryCombineInstruction. As a result, this fix exposed a few places in tests where G_TRUNC instructions were not being deleted even though they were dead. Differential Revision: https://reviews.llvm.org/D59892 llvm-svn: 357101
2019-03-28 01:47:42 +08:00
; CHECK: [[TRUNC4:%[0-9]+]]:_(s48) = G_TRUNC [[OR1]](s64)
; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[TRUNC4]](s48)
AMDGPU/GlobalISel: Fix bit ops for non-power-of-2 sizes llvm-svn: 354825
2019-02-26 05:32:48 +08:00
; 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)
GlobalISel: Implement widenScalar for G_UNMERGE_VALUES For the scalar case only. Also move the similar G_MERGE_VALUES handling to a separate function and cleanup to make them look more similar. llvm-svn: 352979
2019-02-03 08:07:33 +08:00
%0:_(s32) = COPY $vgpr0
%1:_(s3) = G_TRUNC %0
%2:_(s1), %3:_(s1), %4:_(s1) = G_UNMERGE_VALUES %1
%5:_(s32) = G_ANYEXT %2
%6:_(s32) = G_ANYEXT %3
%7:_(s32) = G_ANYEXT %4
$vgpr0 = COPY %5
$vgpr1 = COPY %6
$vgpr2 = COPY %7
...
---
name: test_unmerge_s1_s8
body: |
bb.0:
liveins: $vgpr0
; CHECK-LABEL: name: test_unmerge_s1_s8
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 255
; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
; CHECK: [[ANYEXT:%[0-9]+]]:_(s128) = G_ANYEXT [[COPY]](s32)
; CHECK: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[ANYEXT]](s128)
; CHECK: [[AND:%[0-9]+]]:_(s64) = G_AND [[UV]], [[C]]
; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[UV1]], [[C1]]
; CHECK: [[MV:%[0-9]+]]:_(s128) = G_MERGE_VALUES [[AND]](s64), [[AND1]](s64)
; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 15
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[MV1:%[0-9]+]]:_(s128) = G_MERGE_VALUES [[C2]](s64), [[C1]](s64)
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[MV1]](s128)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 64
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[MV]](s128)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SUB:%[0-9]+]]:_(s32) = G_SUB [[TRUNC]], [[C3]]
; CHECK: [[SUB1:%[0-9]+]]:_(s32) = G_SUB [[C3]], [[TRUNC]]
; CHECK: [[C4:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; CHECK: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[TRUNC]](s32), [[C3]]
; CHECK: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[TRUNC]](s32), [[C4]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SHL:%[0-9]+]]:_(s64) = G_SHL [[UV3]], [[TRUNC]](s32)
; CHECK: [[SHL1:%[0-9]+]]:_(s64) = G_SHL [[UV3]], [[TRUNC]](s32)
; CHECK: [[LSHR:%[0-9]+]]:_(s64) = G_LSHR [[UV2]], [[SUB1]](s32)
; CHECK: [[OR:%[0-9]+]]:_(s64) = G_OR [[SHL1]], [[LSHR]]
; CHECK: [[SHL2:%[0-9]+]]:_(s64) = G_SHL [[UV2]], [[SUB]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SELECT:%[0-9]+]]:_(s64) = G_SELECT [[ICMP]](s1), [[SHL]], [[C1]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SELECT1:%[0-9]+]]:_(s64) = G_SELECT [[ICMP]](s1), [[OR]], [[SHL2]]
; CHECK: [[SELECT2:%[0-9]+]]:_(s64) = G_SELECT [[ICMP1]](s1), [[UV3]], [[SELECT1]]
; CHECK: [[UV4:%[0-9]+]]:_(s64), [[UV5:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[MV]](s128)
; CHECK: [[OR1:%[0-9]+]]:_(s64) = G_OR [[UV4]], [[SELECT]]
; CHECK: [[OR2:%[0-9]+]]:_(s64) = G_OR [[UV5]], [[SELECT2]]
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[C5:%[0-9]+]]:_(s64) = G_CONSTANT i64 30
; CHECK: [[MV2:%[0-9]+]]:_(s128) = G_MERGE_VALUES [[C5]](s64), [[C1]](s64)
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[TRUNC1:%[0-9]+]]:_(s32) = G_TRUNC [[MV2]](s128)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SUB2:%[0-9]+]]:_(s32) = G_SUB [[TRUNC1]], [[C3]]
; CHECK: [[SUB3:%[0-9]+]]:_(s32) = G_SUB [[C3]], [[TRUNC1]]
; CHECK: [[ICMP2:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[TRUNC1]](s32), [[C3]]
; CHECK: [[ICMP3:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[TRUNC1]](s32), [[C4]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SHL3:%[0-9]+]]:_(s64) = G_SHL [[OR2]], [[TRUNC1]](s32)
; CHECK: [[SHL4:%[0-9]+]]:_(s64) = G_SHL [[OR2]], [[TRUNC1]](s32)
; CHECK: [[LSHR1:%[0-9]+]]:_(s64) = G_LSHR [[OR1]], [[SUB3]](s32)
; CHECK: [[OR3:%[0-9]+]]:_(s64) = G_OR [[SHL4]], [[LSHR1]]
; CHECK: [[SHL5:%[0-9]+]]:_(s64) = G_SHL [[OR1]], [[SUB2]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SELECT3:%[0-9]+]]:_(s64) = G_SELECT [[ICMP2]](s1), [[SHL3]], [[C1]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SELECT4:%[0-9]+]]:_(s64) = G_SELECT [[ICMP2]](s1), [[OR3]], [[SHL5]]
; CHECK: [[SELECT5:%[0-9]+]]:_(s64) = G_SELECT [[ICMP3]](s1), [[OR2]], [[SELECT4]]
; CHECK: [[OR4:%[0-9]+]]:_(s64) = G_OR [[OR1]], [[SELECT3]]
; CHECK: [[OR5:%[0-9]+]]:_(s64) = G_OR [[OR2]], [[SELECT5]]
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[C6:%[0-9]+]]:_(s64) = G_CONSTANT i64 45
; CHECK: [[MV3:%[0-9]+]]:_(s128) = G_MERGE_VALUES [[C6]](s64), [[C1]](s64)
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[TRUNC2:%[0-9]+]]:_(s32) = G_TRUNC [[MV3]](s128)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SUB4:%[0-9]+]]:_(s32) = G_SUB [[TRUNC2]], [[C3]]
; CHECK: [[SUB5:%[0-9]+]]:_(s32) = G_SUB [[C3]], [[TRUNC2]]
; CHECK: [[ICMP4:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[TRUNC2]](s32), [[C3]]
; CHECK: [[ICMP5:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[TRUNC2]](s32), [[C4]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SHL6:%[0-9]+]]:_(s64) = G_SHL [[OR5]], [[TRUNC2]](s32)
; CHECK: [[SHL7:%[0-9]+]]:_(s64) = G_SHL [[OR5]], [[TRUNC2]](s32)
; CHECK: [[LSHR2:%[0-9]+]]:_(s64) = G_LSHR [[OR4]], [[SUB5]](s32)
; CHECK: [[OR6:%[0-9]+]]:_(s64) = G_OR [[SHL7]], [[LSHR2]]
; CHECK: [[SHL8:%[0-9]+]]:_(s64) = G_SHL [[OR4]], [[SUB4]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SELECT6:%[0-9]+]]:_(s64) = G_SELECT [[ICMP4]](s1), [[SHL6]], [[C1]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SELECT7:%[0-9]+]]:_(s64) = G_SELECT [[ICMP4]](s1), [[OR6]], [[SHL8]]
; CHECK: [[SELECT8:%[0-9]+]]:_(s64) = G_SELECT [[ICMP5]](s1), [[OR5]], [[SELECT7]]
; CHECK: [[OR7:%[0-9]+]]:_(s64) = G_OR [[OR4]], [[SELECT6]]
; CHECK: [[OR8:%[0-9]+]]:_(s64) = G_OR [[OR5]], [[SELECT8]]
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[C7:%[0-9]+]]:_(s64) = G_CONSTANT i64 60
; CHECK: [[MV4:%[0-9]+]]:_(s128) = G_MERGE_VALUES [[C7]](s64), [[C1]](s64)
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[TRUNC3:%[0-9]+]]:_(s32) = G_TRUNC [[MV4]](s128)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SUB6:%[0-9]+]]:_(s32) = G_SUB [[TRUNC3]], [[C3]]
; CHECK: [[SUB7:%[0-9]+]]:_(s32) = G_SUB [[C3]], [[TRUNC3]]
; CHECK: [[ICMP6:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[TRUNC3]](s32), [[C3]]
; CHECK: [[ICMP7:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[TRUNC3]](s32), [[C4]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SHL9:%[0-9]+]]:_(s64) = G_SHL [[OR8]], [[TRUNC3]](s32)
; CHECK: [[SHL10:%[0-9]+]]:_(s64) = G_SHL [[OR8]], [[TRUNC3]](s32)
; CHECK: [[LSHR3:%[0-9]+]]:_(s64) = G_LSHR [[OR7]], [[SUB7]](s32)
; CHECK: [[OR9:%[0-9]+]]:_(s64) = G_OR [[SHL10]], [[LSHR3]]
; CHECK: [[SHL11:%[0-9]+]]:_(s64) = G_SHL [[OR7]], [[SUB6]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SELECT9:%[0-9]+]]:_(s64) = G_SELECT [[ICMP6]](s1), [[SHL9]], [[C1]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SELECT10:%[0-9]+]]:_(s64) = G_SELECT [[ICMP6]](s1), [[OR9]], [[SHL11]]
; CHECK: [[SELECT11:%[0-9]+]]:_(s64) = G_SELECT [[ICMP7]](s1), [[OR8]], [[SELECT10]]
; CHECK: [[OR10:%[0-9]+]]:_(s64) = G_OR [[OR7]], [[SELECT9]]
; CHECK: [[OR11:%[0-9]+]]:_(s64) = G_OR [[OR8]], [[SELECT11]]
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[C8:%[0-9]+]]:_(s64) = G_CONSTANT i64 75
; CHECK: [[MV5:%[0-9]+]]:_(s128) = G_MERGE_VALUES [[C8]](s64), [[C1]](s64)
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[TRUNC4:%[0-9]+]]:_(s32) = G_TRUNC [[MV5]](s128)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SUB8:%[0-9]+]]:_(s32) = G_SUB [[TRUNC4]], [[C3]]
; CHECK: [[SUB9:%[0-9]+]]:_(s32) = G_SUB [[C3]], [[TRUNC4]]
; CHECK: [[ICMP8:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[TRUNC4]](s32), [[C3]]
; CHECK: [[ICMP9:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[TRUNC4]](s32), [[C4]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SHL12:%[0-9]+]]:_(s64) = G_SHL [[OR11]], [[TRUNC4]](s32)
; CHECK: [[SHL13:%[0-9]+]]:_(s64) = G_SHL [[OR11]], [[TRUNC4]](s32)
; CHECK: [[LSHR4:%[0-9]+]]:_(s64) = G_LSHR [[OR10]], [[SUB9]](s32)
; CHECK: [[OR12:%[0-9]+]]:_(s64) = G_OR [[SHL13]], [[LSHR4]]
; CHECK: [[SHL14:%[0-9]+]]:_(s64) = G_SHL [[OR10]], [[SUB8]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SELECT12:%[0-9]+]]:_(s64) = G_SELECT [[ICMP8]](s1), [[SHL12]], [[C1]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SELECT13:%[0-9]+]]:_(s64) = G_SELECT [[ICMP8]](s1), [[OR12]], [[SHL14]]
; CHECK: [[SELECT14:%[0-9]+]]:_(s64) = G_SELECT [[ICMP9]](s1), [[OR11]], [[SELECT13]]
; CHECK: [[OR13:%[0-9]+]]:_(s64) = G_OR [[OR10]], [[SELECT12]]
; CHECK: [[OR14:%[0-9]+]]:_(s64) = G_OR [[OR11]], [[SELECT14]]
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[C9:%[0-9]+]]:_(s64) = G_CONSTANT i64 90
; CHECK: [[MV6:%[0-9]+]]:_(s128) = G_MERGE_VALUES [[C9]](s64), [[C1]](s64)
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[TRUNC5:%[0-9]+]]:_(s32) = G_TRUNC [[MV6]](s128)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SUB10:%[0-9]+]]:_(s32) = G_SUB [[TRUNC5]], [[C3]]
; CHECK: [[SUB11:%[0-9]+]]:_(s32) = G_SUB [[C3]], [[TRUNC5]]
; CHECK: [[ICMP10:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[TRUNC5]](s32), [[C3]]
; CHECK: [[ICMP11:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[TRUNC5]](s32), [[C4]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SHL15:%[0-9]+]]:_(s64) = G_SHL [[OR14]], [[TRUNC5]](s32)
; CHECK: [[SHL16:%[0-9]+]]:_(s64) = G_SHL [[OR14]], [[TRUNC5]](s32)
; CHECK: [[LSHR5:%[0-9]+]]:_(s64) = G_LSHR [[OR13]], [[SUB11]](s32)
; CHECK: [[OR15:%[0-9]+]]:_(s64) = G_OR [[SHL16]], [[LSHR5]]
; CHECK: [[SHL17:%[0-9]+]]:_(s64) = G_SHL [[OR13]], [[SUB10]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SELECT15:%[0-9]+]]:_(s64) = G_SELECT [[ICMP10]](s1), [[SHL15]], [[C1]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SELECT16:%[0-9]+]]:_(s64) = G_SELECT [[ICMP10]](s1), [[OR15]], [[SHL17]]
; CHECK: [[SELECT17:%[0-9]+]]:_(s64) = G_SELECT [[ICMP11]](s1), [[OR14]], [[SELECT16]]
; CHECK: [[OR16:%[0-9]+]]:_(s64) = G_OR [[OR13]], [[SELECT15]]
; CHECK: [[OR17:%[0-9]+]]:_(s64) = G_OR [[OR14]], [[SELECT17]]
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[C10:%[0-9]+]]:_(s64) = G_CONSTANT i64 105
; CHECK: [[MV7:%[0-9]+]]:_(s128) = G_MERGE_VALUES [[C10]](s64), [[C1]](s64)
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[TRUNC6:%[0-9]+]]:_(s32) = G_TRUNC [[MV7]](s128)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SUB12:%[0-9]+]]:_(s32) = G_SUB [[TRUNC6]], [[C3]]
; CHECK: [[SUB13:%[0-9]+]]:_(s32) = G_SUB [[C3]], [[TRUNC6]]
; CHECK: [[ICMP12:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[TRUNC6]](s32), [[C3]]
; CHECK: [[ICMP13:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[TRUNC6]](s32), [[C4]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SHL18:%[0-9]+]]:_(s64) = G_SHL [[OR17]], [[TRUNC6]](s32)
; CHECK: [[SHL19:%[0-9]+]]:_(s64) = G_SHL [[OR17]], [[TRUNC6]](s32)
; CHECK: [[LSHR6:%[0-9]+]]:_(s64) = G_LSHR [[OR16]], [[SUB13]](s32)
; CHECK: [[OR18:%[0-9]+]]:_(s64) = G_OR [[SHL19]], [[LSHR6]]
; CHECK: [[SHL20:%[0-9]+]]:_(s64) = G_SHL [[OR16]], [[SUB12]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[SELECT18:%[0-9]+]]:_(s64) = G_SELECT [[ICMP12]](s1), [[SHL18]], [[C1]]
GlobalISel: Implement narrowScalar for shift main type This is pretty much directly ported from SelectionDAG. Doesn't include the shift by non-constant but known bits version, since there isn't a globalisel version of computeKnownBits yet. This shows a disadvantage of targets not specifically which type should be used for the shift amount. If type 0 is legalized before type 1, the operations on the shift amount type use the wider type (which are also less likely to legalize). This can be avoided by targets specifying legalization actions on type 1 earlier than for type 0. llvm-svn: 353455
2019-02-08 03:37:44 +08:00
; CHECK: [[SELECT19:%[0-9]+]]:_(s64) = G_SELECT [[ICMP12]](s1), [[OR18]], [[SHL20]]
; CHECK: [[SELECT20:%[0-9]+]]:_(s64) = G_SELECT [[ICMP13]](s1), [[OR17]], [[SELECT19]]
; CHECK: [[OR19:%[0-9]+]]:_(s64) = G_OR [[OR16]], [[SELECT18]]
; CHECK: [[OR20:%[0-9]+]]:_(s64) = G_OR [[OR17]], [[SELECT20]]
; CHECK: [[UV6:%[0-9]+]]:_(s16), [[UV7:%[0-9]+]]:_(s16), [[UV8:%[0-9]+]]:_(s16), [[UV9:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[OR19]](s64)
; CHECK: [[UV10:%[0-9]+]]:_(s16), [[UV11:%[0-9]+]]:_(s16), [[UV12:%[0-9]+]]:_(s16), [[UV13:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[OR20]](s64)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[UV6]](s16)
; CHECK: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[UV7]](s16)
; CHECK: [[ANYEXT3:%[0-9]+]]:_(s32) = G_ANYEXT [[UV8]](s16)
; CHECK: [[ANYEXT4:%[0-9]+]]:_(s32) = G_ANYEXT [[UV9]](s16)
; CHECK: [[ANYEXT5:%[0-9]+]]:_(s32) = G_ANYEXT [[UV10]](s16)
; CHECK: [[ANYEXT6:%[0-9]+]]:_(s32) = G_ANYEXT [[UV11]](s16)
; CHECK: [[ANYEXT7:%[0-9]+]]:_(s32) = G_ANYEXT [[UV12]](s16)
; CHECK: [[ANYEXT8:%[0-9]+]]:_(s32) = G_ANYEXT [[UV13]](s16)
; CHECK: $vgpr0 = COPY [[ANYEXT1]](s32)
; CHECK: $vgpr1 = COPY [[ANYEXT2]](s32)
; CHECK: $vgpr2 = COPY [[ANYEXT3]](s32)
; CHECK: $vgpr3 = COPY [[ANYEXT4]](s32)
; CHECK: $vgpr4 = COPY [[ANYEXT5]](s32)
; CHECK: $vgpr5 = COPY [[ANYEXT6]](s32)
; CHECK: $vgpr6 = COPY [[ANYEXT7]](s32)
; CHECK: $vgpr7 = COPY [[ANYEXT8]](s32)
GlobalISel: Implement widenScalar for G_UNMERGE_VALUES For the scalar case only. Also move the similar G_MERGE_VALUES handling to a separate function and cleanup to make them look more similar. llvm-svn: 352979
2019-02-03 08:07:33 +08:00
%0:_(s32) = COPY $vgpr0
%1:_(s8) = G_TRUNC %0
%2:_(s1), %3:_(s1), %4:_(s1), %5:_(s1), %6:_(s1), %7:_(s1), %8:_(s1), %9:_(s1) = G_UNMERGE_VALUES %1
%10:_(s32) = G_ANYEXT %2
%11:_(s32) = G_ANYEXT %3
%12:_(s32) = G_ANYEXT %4
%13:_(s32) = G_ANYEXT %5
%14:_(s32) = G_ANYEXT %6
%15:_(s32) = G_ANYEXT %7
%16:_(s32) = G_ANYEXT %8
%17:_(s32) = G_ANYEXT %9
$vgpr0 = COPY %10
$vgpr1 = COPY %11
$vgpr2 = COPY %12
$vgpr3 = COPY %13
$vgpr4 = COPY %14
$vgpr5 = COPY %15
$vgpr6 = COPY %16
$vgpr7 = COPY %17
...