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-bitcast.mir

183 lines
5.0 KiB
Plaintext
Raw Normal View History

Canonicalize a large number of mir tests using update_mir_test_checks This converts a large and somewhat arbitrary set of tests to use update_mir_test_checks. I ran the script on all of the tests I expect to need to modify for an upcoming mir syntax change and kept the ones that obviously didn't change the tests in ways that might make it harder to understand. llvm-svn: 316137
2017-10-19 07:18:12 +08:00
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
[globalisel] Remove redundant -global-isel option from tests that use -run-pass. NFC As Roman Tereshin pointed out in https://reviews.llvm.org/D45541, the -global-isel option is redundant when -run-pass is given. -global-isel sets up the GlobalISel passes in the pass manager but -run-pass skips that entirely and configures it's own pipeline. llvm-svn: 331603
2018-05-06 05:19:59 +08:00
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -run-pass=legalizer %s -o - | FileCheck %s
AMDGPU/GlobalISel: Mark G_BITCAST s32 <--> <2 x s16> legal Reviewers: arsenm Reviewed By: arsenm Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, rovka, kristof.beyls, igorb, dstuttard, tpr, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D34129 llvm-svn: 305692
2017-06-19 21:15:45 +08:00
---
AMDGPU: Legalize more bitcasts llvm-svn: 351700
2019-01-21 03:45:18 +08:00
name: test_bitcast_s32_to_v2s16
AMDGPU/GlobalISel: Mark G_BITCAST s32 <--> <2 x s16> legal Reviewers: arsenm Reviewed By: arsenm Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, rovka, kristof.beyls, igorb, dstuttard, tpr, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D34129 llvm-svn: 305692
2017-06-19 21:15:45 +08:00
body: |
bb.0:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
liveins: $vgpr0
AMDGPU/GlobalISel: Mark G_BITCAST s32 <--> <2 x s16> legal Reviewers: arsenm Reviewed By: arsenm Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, rovka, kristof.beyls, igorb, dstuttard, tpr, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D34129 llvm-svn: 305692
2017-06-19 21:15:45 +08:00
AMDGPU: Legalize more bitcasts llvm-svn: 351700
2019-01-21 03:45:18 +08:00
; CHECK-LABEL: name: test_bitcast_s32_to_v2s16
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
MIR: Print the register class or bank in vreg defs This updates the MIRPrinter to include the regclass when printing virtual register defs, which is already valid syntax for the parser. That is, given 64 bit %0 and %1 in a "gpr" regbank, %1(s64) = COPY %0(s64) would now be written as %1:gpr(s64) = COPY %0(s64) While this change alone introduces a bit of redundancy with the registers block, it allows us to update the tests to be more concise and understandable and brings us closer to being able to remove the registers block completely. Note: We generally only print the class in defs, but there is one exception. If there are uses without any defs whatsoever, we'll print the class on all uses. I'm not completely convinced this comes up in meaningful machine IR, but for now the MIRParser and MachineVerifier both accept that kind of stuff, so we don't want to have a situation where we can print something we can't parse. llvm-svn: 316479
2017-10-25 02:04:54 +08:00
; CHECK: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[COPY]](s32)
AMDGPU: Legalize more bitcasts llvm-svn: 351700
2019-01-21 03:45:18 +08:00
; CHECK: $vgpr0 = COPY [[BITCAST]](<2 x s16>)
AMDGPU/GlobalISel: Test cleanups Remove IR and registers sections llvm-svn: 349011
2018-12-13 16:11:45 +08:00
%0:_(s32) = COPY $vgpr0
%1:_(<2 x s16>) = G_BITCAST %0
AMDGPU: Legalize more bitcasts llvm-svn: 351700
2019-01-21 03:45:18 +08:00
$vgpr0 = COPY %1
...
---
name: test_bitcast_v2s16_to_s32
body: |
bb.0:
liveins: $vgpr0
; CHECK-LABEL: name: test_bitcast_v2s16_to_s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
; CHECK: $vgpr0 = COPY [[BITCAST]](s32)
%0:_(<2 x s16>) = COPY $vgpr0
%1:_(s32) = G_BITCAST %0
$vgpr0 = COPY %1
...
---
name: test_bitcast_v2s32_to_s64
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_bitcast_v2s32_to_s64
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[BITCAST:%[0-9]+]]:_(s64) = G_BITCAST [[COPY]](<2 x s32>)
; CHECK: $vgpr0_vgpr1 = COPY [[BITCAST]](s64)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(s64) = G_BITCAST %0
$vgpr0_vgpr1 = COPY %1
...
---
name: test_bitcast_s64_to_v2s32
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_bitcast_s64_to_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[BITCAST:%[0-9]+]]:_(<2 x s32>) = G_BITCAST [[COPY]](s64)
; CHECK: $vgpr0_vgpr1 = COPY [[BITCAST]](<2 x s32>)
%0:_(s64) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = G_BITCAST %0
$vgpr0_vgpr1 = COPY %1
...
---
name: test_bitcast_v2s64_to_v4s32
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK-LABEL: name: test_bitcast_v2s64_to_v4s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK: [[BITCAST:%[0-9]+]]:_(<4 x s32>) = G_BITCAST [[COPY]](<2 x s64>)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BITCAST]](<4 x s32>)
%0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<4 x s32>) = G_BITCAST %0
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %1
...
---
name: test_bitcast_v4s32_to_v2s64
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK-LABEL: name: test_bitcast_v4s32_to_v2s64
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK: [[BITCAST:%[0-9]+]]:_(<2 x s64>) = G_BITCAST [[COPY]](<4 x s32>)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BITCAST]](<2 x s64>)
%0:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<2 x s64>) = G_BITCAST %0
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %1
...
---
name: test_bitcast_v4s16_to_s64
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_bitcast_v4s16_to_s64
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
; CHECK: [[BITCAST:%[0-9]+]]:_(s64) = G_BITCAST [[COPY]](<4 x s16>)
; CHECK: $vgpr0_vgpr1 = COPY [[BITCAST]](s64)
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
%1:_(s64) = G_BITCAST %0
$vgpr0_vgpr1 = COPY %1
...
---
name: test_bitcast_s64_to_v4s16
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_bitcast_s64_to_v4s16
; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[BITCAST:%[0-9]+]]:_(<4 x s16>) = G_BITCAST [[COPY]](s64)
; CHECK: $vgpr0_vgpr1 = COPY [[BITCAST]](<4 x s16>)
%0:_(s64) = COPY $vgpr0_vgpr1
%1:_(<4 x s16>) = G_BITCAST %0
$vgpr0_vgpr1 = COPY %1
...
---
name: test_bitcast_p0_to_p1
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_bitcast_p0_to_p1
; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $vgpr0_vgpr1
; CHECK: [[BITCAST:%[0-9]+]]:_(p1) = G_BITCAST [[COPY]](p0)
; CHECK: $vgpr0_vgpr1 = COPY [[BITCAST]](p1)
%0:_(p0) = COPY $vgpr0_vgpr1
%1:_(p1) = G_BITCAST %0
$vgpr0_vgpr1 = COPY %1
...
---
name: test_bitcast_p1_to_p0
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_bitcast_p1_to_p0
; CHECK: [[COPY:%[0-9]+]]:_(p1) = COPY $vgpr0_vgpr1
; CHECK: [[BITCAST:%[0-9]+]]:_(p0) = G_BITCAST [[COPY]](p1)
; CHECK: $vgpr0_vgpr1 = COPY [[BITCAST]](p0)
%0:_(p1) = COPY $vgpr0_vgpr1
%1:_(p0) = G_BITCAST %0
$vgpr0_vgpr1 = COPY %1
...
---
name: test_bitcast_p999_to_p0
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_bitcast_p999_to_p0
; CHECK: [[COPY:%[0-9]+]]:_(p999) = COPY $vgpr0_vgpr1
; CHECK: [[BITCAST:%[0-9]+]]:_(p0) = G_BITCAST [[COPY]](p999)
; CHECK: $vgpr0_vgpr1 = COPY [[BITCAST]](p0)
%0:_(p999) = COPY $vgpr0_vgpr1
%1:_(p0) = G_BITCAST %0
$vgpr0_vgpr1 = COPY %1
...
---
name: test_bitcast_p123_to_p999
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_bitcast_p123_to_p999
; CHECK: [[COPY:%[0-9]+]]:_(p123) = COPY $vgpr0_vgpr1
; CHECK: [[BITCAST:%[0-9]+]]:_(p999) = G_BITCAST [[COPY]](p123)
; CHECK: $vgpr0_vgpr1 = COPY [[BITCAST]](p999)
%0:_(p123) = COPY $vgpr0_vgpr1
%1:_(p999) = G_BITCAST %0
$vgpr0_vgpr1 = COPY %1
AMDGPU/GlobalISel: Mark G_BITCAST s32 <--> <2 x s16> legal Reviewers: arsenm Reviewed By: arsenm Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, rovka, kristof.beyls, igorb, dstuttard, tpr, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D34129 llvm-svn: 305692
2017-06-19 21:15:45 +08:00
...