llvm-project/llvm/test/CodeGen/AMDGPU
Stanislav Mekhanoshin 37e7f959c0 [AMDGPU] Collapse adjacent SI_END_CF
Add a pass to remove redundant S_OR_B64 instructions enabling lanes in
the exec. If two SI_END_CF (lowered as S_OR_B64) come together without any
vector instructions between them we can only keep outer SI_END_CF, given
that CFG is structured and exec bits of the outer end statement are always
not less than exec bit of the inner one.

This needs to be done before the RA to eliminate saved exec bits registers
but after register coalescer to have no vector registers copies in between
of different end cf statements.

Differential Revision: https://reviews.llvm.org/D35967

llvm-svn: 309762
2017-08-01 23:14:32 +00:00
..
GlobalISel AMDGPU/GlobalISel: Add support for amdgpu_vs calling convention 2017-08-01 12:38:33 +00:00
32-bit-local-address-space.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
README
add-debug.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
add.i16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
add.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
add.v2i16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
add_i64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
add_i128.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
addrspacecast-captured.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
addrspacecast-constantexpr.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
addrspacecast.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
alignbit-pat.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
always-uniform.ll DivergencyAnalysis patch for review 2017-06-15 19:33:10 +00:00
amdgcn.bitcast.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
amdgcn.private-memory.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
amdgpu-alias-analysis.ll AMDGPU/R600: Fix amdgpu alias analysis pass. 2017-03-31 19:26:23 +00:00
amdgpu-codegenprepare-fdiv.ll [AMDGPU] Always use rcp + mul with fast math 2017-07-06 20:34:21 +00:00
amdgpu-codegenprepare-i16-to-i32.ll AMDGPU: Change DivergenceAnalysis for function arguments 2017-04-19 17:42:34 +00:00
amdgpu-shader-calling-convention.ll AMDGPU: Refactor argument lowering 2017-04-11 22:29:24 +00:00
amdgpu.private-memory.ll [AMDGPU] Generate range metadata for workitem id 2017-04-12 20:48:56 +00:00
amdgpu.work-item-intrinsics.deprecated.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
and-gcn.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
and.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
annotate-kernel-features-hsa-call.ll AMDGPU: Annotate implicitarg.ptr usage 2017-07-28 15:52:08 +00:00
annotate-kernel-features-hsa.ll AMDGPU: Detect kernarg segment pointer 2017-07-14 00:11:13 +00:00
annotate-kernel-features.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
anonymous-gv.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
any_extend_vector_inreg.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
anyext.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
array-ptr-calc-i32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
array-ptr-calc-i64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
ashr.v2i16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
atomic_cmp_swap_local.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
atomic_load_add.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
atomic_load_sub.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
attr-amdgpu-flat-work-group-size.ll AMDGPU: Detect kernarg segment pointer 2017-07-14 00:11:13 +00:00
attr-amdgpu-num-sgpr.ll RegScavenging: Add scavengeRegisterBackwards() 2017-06-17 02:08:18 +00:00
attr-amdgpu-num-vgpr.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
attr-amdgpu-waves-per-eu.ll AMDGPU: Fix amdgpu-flat-work-group-size/amdgpu-waves-per-eu check 2017-07-16 19:38:47 +00:00
attr-unparseable.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
barrier-elimination.ll [AMDGPU] Eliminate barrier if workgroup size is not greater than wavefront size 2017-04-06 16:48:30 +00:00
basic-branch.ll [AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. 2017-06-02 14:19:25 +00:00
basic-call-return.ll AMDGPU: Initial implementation of calls 2017-08-01 19:54:18 +00:00
basic-loop.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
bfe-combine.ll [AMDGPU] Allow SDWA in instructions with immediates and SGPRs 2017-05-30 16:49:24 +00:00
bfe-patterns.ll [AMDGPU] Narrow lshl from 64 to 32 bit if possible 2017-05-22 16:58:10 +00:00
bfe_uint.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
bfi_int.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
bfm.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
big_alu.ll AMDGPU: Remove llvm.AMDGPU.clamp intrinsic 2017-02-21 23:46:04 +00:00
bitcast-vector-extract.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
bitreverse-inline-immediates.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
bitreverse.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
br_cc.f16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
branch-condition-and.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
branch-relax-spill.ll AMDGPU: Use correct register names in inline assembly 2017-06-08 19:03:20 +00:00
branch-relaxation.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
branch-uniformity.ll
bswap.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
bug-vopc-commute.ll AMDGPU: Remove SITypeRewriter 2017-06-28 21:38:50 +00:00
build_vector.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
byval-frame-setup.ll AMDGPU: Initial implementation of calls 2017-08-01 19:54:18 +00:00
call-argument-types.ll AMDGPU: Initial implementation of calls 2017-08-01 19:54:18 +00:00
call-preserved-registers.ll AMDGPU: Initial implementation of calls 2017-08-01 19:54:18 +00:00
call-return-types.ll AMDGPU: Initial implementation of calls 2017-08-01 19:54:18 +00:00
call.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
call_fs.ll
callee-frame-setup.ll AMDGPU: Initial implementation of calls 2017-08-01 19:54:18 +00:00
calling-conventions.ll AMDGPU: Refactor SIMachineFunctionInfo slightly 2017-04-11 22:29:28 +00:00
captured-frame-index.ll Add address space mangling to lifetime intrinsics 2017-04-10 20:18:21 +00:00
cayman-loop-bug.ll
cf-loop-on-constant.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
cf-stack-bug.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
cf_end.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
cgp-addressing-modes-flat.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
cgp-addressing-modes.ll AMDGPU: Teach isLegalAddressingMode about global_* instructions 2017-07-29 01:12:31 +00:00
cgp-bitfield-extract.ll [AMDGPU] Add pattern for v_alignbit_b32 with immediate 2017-06-28 02:52:39 +00:00
clamp-modifier.ll AMDGPU: Keep track of modifiers when converting v_mac to v_mad 2017-03-11 05:40:40 +00:00
clamp-omod-special-case.mir AMDGPU: Remove unnecessary IR from MIR tests 2017-07-06 20:56:57 +00:00
clamp.ll [AMDGPU] Remove getBidirectionalReasonRank 2017-03-11 00:29:27 +00:00
cndmask-no-def-vcc.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
coalescer-subrange-crash.ll AMDGPU: Convert image intrinsic uses in tests 2017-03-21 16:24:12 +00:00
coalescer-subreg-join.mir Move .mir tests to appropriate directories 2016-12-09 19:08:15 +00:00
coalescer_distribute.ll AMDGPU: Remove old intrinsic uses 2017-05-17 21:38:21 +00:00
coalescer_remat.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
code-object-metadata-deduce-ro-arg.ll [AMDGPU] set read_only access qualifier for pointers 2017-04-14 19:11:40 +00:00
code-object-metadata-from-llvm-ir-full.ll Fix ODR violations due to abuse of LLVM_YAML_IS_(FLOW_)?SEQUENCE_VECTOR 2017-06-30 20:56:57 +00:00
code-object-metadata-images.ll AMDGPU: Fix ValueKind code object metadata for images 2017-04-25 20:38:26 +00:00
code-object-metadata-invalid-ocl-version-1.ll [AMDGPU] Do not emit isa info as code object metadata 2017-03-22 23:27:09 +00:00
code-object-metadata-invalid-ocl-version-2.ll [AMDGPU] Do not emit isa info as code object metadata 2017-03-22 23:27:09 +00:00
code-object-metadata-invalid-ocl-version-3.ll [AMDGPU] Do not emit isa info as code object metadata 2017-03-22 23:27:09 +00:00
code-object-metadata-kernel-code-props.ll [AMDGPU] Emit kernel code properties as code object metadata 2017-03-22 22:54:39 +00:00
code-object-metadata-kernel-debug-props.ll RegScavenging: Add scavengeRegisterBackwards() 2017-06-17 02:08:18 +00:00
codegen-prepare-addrmode-sext.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
collapse-endcf.ll [AMDGPU] Collapse adjacent SI_END_CF 2017-08-01 23:14:32 +00:00
combine-and-sext-bool.ll [AMDGPU] Combine and x, (sext cc from i1) => select cc, x, 0 2017-06-27 18:25:26 +00:00
combine-cond-add-sub.ll [AMDGPU] Combine and x, (sext cc from i1) => select cc, x, 0 2017-06-27 18:25:26 +00:00
combine_vloads.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
commute-compares.ll [AMDGPU] Preserve operand order in SIFoldOperands 2017-06-03 00:41:52 +00:00
commute-shifts.ll AMDGPU: Convert image intrinsic uses in tests 2017-03-21 16:24:12 +00:00
commute_modifiers.ll [AMDGPU] Allow SDWA in instructions with immediates and SGPRs 2017-05-30 16:49:24 +00:00
complex-folding.ll
concat_vectors.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
constant-fold-imm-immreg.mir AMDGPU: Remove unnecessary IR from MIR tests 2017-07-06 20:56:57 +00:00
constant-fold-mi-operands.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
control-flow-fastregalloc.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
convergent-inlineasm.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
copy-illegal-type.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
copy-to-reg.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
ctlz.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
ctlz_zero_undef.ll AMDGPU: Add macro fusion schedule DAG mutation 2017-07-06 20:57:05 +00:00
ctpop.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
ctpop64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
cttz_zero_undef.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
cube.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
cvt_f32_ubyte.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
cvt_flr_i32_f32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
cvt_rpi_i32_f32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
dagcombine-reassociate-bug.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
dagcombiner-bug-illegal-vec4-int-to-fp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
debug.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
debugger-emit-prologue.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
debugger-insert-nops.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
debugger-reserve-regs.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
default-fp-mode.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
detect-dead-lanes.mir AMDGPU: Remove unnecessary IR from MIR tests 2017-07-06 20:56:57 +00:00
disconnected-predset-break-bug.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
drop-mem-operand-move-smrd.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
ds-combine-large-stride.ll [AMDGPU] added SIInstrInfo::getAddNoCarry() helper 2017-04-14 00:33:44 +00:00
ds-negative-offset-addressing-mode-loop.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
ds-sub-offset.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
ds_read2.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
ds_read2_offset_order.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
ds_read2_superreg.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
ds_read2st64.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
ds_write2.ll [AMDGPU] Narrow lshl from 64 to 32 bit if possible 2017-05-22 16:58:10 +00:00
ds_write2st64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
dynamic_stackalloc.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
early-if-convert-cost.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
early-if-convert.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
early-inline-alias.ll [AMDGPU] Run always inliner early in opt 2017-03-20 18:06:45 +00:00
early-inline.ll Verifier: Check some amdgpu calling convention restrictions 2017-04-04 18:43:11 +00:00
elf.ll AMDGPU: Remove some uses of llvm.SI.export in tests 2017-02-22 00:02:21 +00:00
elf.r600.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
else.ll AMDGPU: Convert image intrinsic uses in tests 2017-03-21 16:24:12 +00:00
empty-function.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
enable-no-signed-zeros-fp-math.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
endcf-loop-header.ll AMDGPU: Remove old intrinsic uses 2017-05-17 21:38:21 +00:00
env-amdgiz.ll [AMDGPU] Add A5 to data layout for amdgiz environment 2017-04-11 17:18:13 +00:00
env-amdgizcl.ll [AMDGPU] Add A5 to data layout for amdgiz environment 2017-04-11 17:18:13 +00:00
exceed-max-sgprs.ll AMDGPU: Use correct register names in inline assembly 2017-06-08 19:03:20 +00:00
extend-bit-ops-i16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
extload-align.ll CodeGen: Rename DEBUG_TYPE to match passnames 2017-05-25 21:26:32 +00:00
extload-private.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
extload.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
extract-vector-elt-build-vector-combine.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
extract_vector_elt-f16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
extract_vector_elt-f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
extract_vector_elt-i8.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
extract_vector_elt-i16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
extract_vector_elt-i64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
extractelt-to-trunc.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fabs.f16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
fabs.f64.ll [AMDGPU] Allow SDWA in instructions with immediates and SGPRs 2017-05-30 16:49:24 +00:00
fabs.ll [AMDGPU] Allow SDWA in instructions with immediates and SGPRs 2017-05-30 16:49:24 +00:00
fadd-fma-fmul-combine.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fadd.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fadd.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fadd64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fcanonicalize-elimination.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
fcanonicalize.f16.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fcanonicalize.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fceil.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fceil64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fcmp-cnd.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fcmp-cnde-int-args.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fcmp.f16.ll AMDGPU: Add macro fusion schedule DAG mutation 2017-07-06 20:57:05 +00:00
fcmp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fcmp64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fconst64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fcopysign.f16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
fcopysign.f32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fcopysign.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fdiv.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fdiv.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fdiv.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fence-amdgiz.ll AMDGPU: Implement memory model 2017-07-21 21:19:23 +00:00
fetch-limits.r600.ll
fetch-limits.r700+.ll
ffloor.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
ffloor.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fix-vgpr-copies.mir [AMDGPU] Add VGPR copies post regalloc fix pass 2017-01-24 17:46:17 +00:00
flat-address-space.ll AMDGPU: Start selecting flat instruction offsets 2017-06-12 16:53:51 +00:00
flat-for-global-subtarget-feature.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
flat-scratch-reg.ll AMDGPU: Use correct register names in inline assembly 2017-06-08 19:03:20 +00:00
flat_atomics.ll AMDGPU: Implement memory model 2017-07-21 21:19:23 +00:00
flat_atomics_i64.ll AMDGPU: Implement memory model 2017-07-21 21:19:23 +00:00
floor.ll
fma-combine.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fma.f64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fma.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fmad.ll
fmax.ll
fmax3.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fmax3.ll AMDGPU: Fix min3/max3 combines for f16/i16 2017-05-17 19:25:06 +00:00
fmax_legacy.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fmax_legacy.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fmaxnum.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fmaxnum.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fmed3.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
fmin.ll
fmin3.ll AMDGPU: Fix min3/max3 combines for f16/i16 2017-05-17 19:25:06 +00:00
fmin_fmax_legacy.amdgcn.ll AMDGPU: Fold fneg into fmin/fmax_legacy 2017-02-03 00:51:50 +00:00
fmin_legacy.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fmin_legacy.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fminnum.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fminnum.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fmul-2-combine-multi-use.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fmul.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fmul.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fmul64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fmuladd.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fmuladd.f32.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fmuladd.f64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fmuladd.v2f16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
fnearbyint.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fneg-combines.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fneg-fabs.f16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
fneg-fabs.f64.ll [AMDGPU] Allow SDWA in instructions with immediates and SGPRs 2017-05-30 16:49:24 +00:00
fneg-fabs.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fneg.f16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
fneg.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fneg.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fold-cndmask.mir [AMDGPU] Fold V_CNDMASK with identical source operands 2017-03-24 18:55:20 +00:00
fold-fmul-to-neg-abs.ll Fold fneg and fabs like multiplications 2017-06-28 20:25:50 +00:00
fold-immediate-output-mods.mir AMDGPU: Remove unnecessary IR from MIR tests 2017-07-06 20:56:57 +00:00
fold-operands-order.mir AMDGPU: Remove unnecessary IR from MIR tests 2017-07-06 20:56:57 +00:00
fp-classify.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fp16_to_fp32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fp16_to_fp64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fp32_to_fp16.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fp_to_sint.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fp_to_sint.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fp_to_uint.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fp_to_uint.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fpext.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fpext.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fptosi.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fptoui.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fptrunc.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fptrunc.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
fract.f64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fract.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
frame-index-amdgiz.ll CodeGen: Let frame index value type match alloca addr space 2017-04-20 18:15:34 +00:00
frame-index-elimination.ll AMDGPU: Add test for r308774 2017-08-01 19:54:58 +00:00
frem.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fsqrt.f64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fsqrt.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
fsub.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fsub.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
fsub64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
ftrunc.f64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
ftrunc.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
function-args.ll AMDGPU: Return correct type during argument lowering 2017-07-15 05:52:59 +00:00
function-returns.ll AMDGPU: Start defining a calling convention 2017-05-17 21:56:25 +00:00
gep-address-space.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
global-constant.ll Elide stores which are overwritten without being observed. 2017-05-16 19:43:56 +00:00
global-directive.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
global-extload-i16.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
global-smrd-unknown.ll AMDGPU: Fix converting unanalyzable global loads to SMRD 2017-07-12 23:06:18 +00:00
global-variable-relocs.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
global_atomics.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
global_atomics_i64.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
global_smrd.ll [AMDGPU] Scalarization of global uniform loads. 2016-12-08 17:28:47 +00:00
global_smrd_cfg.ll DivergencyAnalysis patch for review 2017-06-15 19:33:10 +00:00
gv-const-addrspace.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
gv-offset-folding.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
half.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
hoist-cond.ll
hsa-default-device.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
hsa-fp-mode.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
hsa-func-align.ll AMDGPU: Don't align callable functions to 256 2017-04-19 17:42:39 +00:00
hsa-func.ll AMDGPU: Fix using SMRD instructions for argument loads in functions 2017-07-26 20:39:42 +00:00
hsa-globals.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
hsa-group-segment.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
hsa-note-no-func.ll AMDGPU : Fix ISA Version Definitions. 2017-06-10 03:53:19 +00:00
hsa.ll AMDGPU: Detect kernarg segment pointer 2017-07-14 00:11:13 +00:00
i1-copy-implicit-def.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
i1-copy-phi.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
i8-to-double-to-float.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
icmp-select-sete-reverse-args.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
icmp.i16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
icmp64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
illegal-sgpr-to-vgpr-copy.ll AMDGPU: Use correct register names in inline assembly 2017-06-08 19:03:20 +00:00
image-attributes.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
image-resource-id.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
imm.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
imm16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
immv216.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
indirect-addressing-si-noopt.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
indirect-addressing-si.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
indirect-private-64.ll [AMDGPU] Eliminate barrier if workgroup size is not greater than wavefront size 2017-04-06 16:48:30 +00:00
infer-addrpace-pipeline.ll [AMDGPU] Add infer address spaces pass before SROA 2017-06-19 23:17:36 +00:00
infinite-loop-evergreen.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
infinite-loop.ll [AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. 2017-06-02 14:19:25 +00:00
inline-asm.ll AMDGPU: Add macro fusion schedule DAG mutation 2017-07-06 20:57:05 +00:00
inline-calls.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
inline-constraints.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
inlineasm-16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
inlineasm-illegal-type.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
inlineasm-packed.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
input-mods.ll
insert-skips-kill-uncond.mir AMDGPU: Remove spurious out branches after a kill 2017-01-24 22:18:39 +00:00
insert-waits-callee.mir AMDGPU: Insert wait at start of callee functions 2017-04-11 22:29:31 +00:00
insert-waits-exp.mir AMDGPU: Rename SI_RETURN 2017-03-21 22:18:10 +00:00
insert_subreg.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
insert_vector_elt.ll AMDGPU: Remove legacy image intrinsics 2017-04-04 16:34:35 +00:00
insert_vector_elt.v2i16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
inserted-wait-states.mir AMDGPU: Start adding offset fields to flat instructions 2017-06-12 15:55:58 +00:00
internalize.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
invalid-addrspacecast.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
invariant-load-no-alias-store.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
invert-br-undef-vcc.mir MIParser/MIRPrinter: Compute block successors if not explicitely specified 2017-05-05 21:09:30 +00:00
jump-address.ll
kcache-fold.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
kernarg-stack-alignment.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
kernel-args.ll [AMDGPU] Add INDIRECT_BASE_ADDR to R600_Reg32 class (PR33045) 2017-05-23 21:27:15 +00:00
large-alloca-compute.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
large-alloca-graphics.ll AMDGPU: Buffer descriptor changes for GFX9 2017-03-21 17:00:39 +00:00
large-constant-initializer.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
large-work-group-promote-alloca.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
lds-alignment.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
lds-initializer.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
lds-m0-init-in-loop.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
lds-oqap-crash.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
lds-output-queue.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
lds-size.ll AMDGPU/AMDHSA: Set COMPUTE_PGM_RSRC2:LDS_SIZE to 0 2017-05-05 20:13:55 +00:00
lds-zero-initializer.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
legalizedag-bug-expand-setcc.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
limit-coalesce.mir AMDGPU: Start adding offset fields to flat instructions 2017-06-12 15:55:58 +00:00
lit.local.cfg
literals.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
liveness.mir MIParser/MIRPrinter: Compute block successors if not explicitely specified 2017-05-05 21:09:30 +00:00
llvm.AMDGPU.kill.ll AMDGPU: Remove some uses of llvm.SI.export in tests 2017-02-22 00:02:21 +00:00
llvm.SI.load.dword.ll AMDGPU: Remove SITypeRewriter 2017-06-28 21:38:50 +00:00
llvm.SI.tbuffer.store.ll AMDGPU: Remove SITypeRewriter 2017-06-28 21:38:50 +00:00
llvm.amdgcn.alignb.ll [AMDGPU] Add intrinsics for alignbit and alignbyte instructions 2017-06-09 19:03:00 +00:00
llvm.amdgcn.atomic.dec.ll [AMDGPU] Narrow lshl from 64 to 32 bit if possible 2017-05-22 16:58:10 +00:00
llvm.amdgcn.atomic.inc.ll [AMDGPU] Narrow lshl from 64 to 32 bit if possible 2017-05-22 16:58:10 +00:00
llvm.amdgcn.buffer.atomic.ll
llvm.amdgcn.buffer.load.format.ll AMDGPU/SI: Add a MachineMemOperand when lowering llvm.amdgcn.buffer.load.* 2016-12-20 17:19:44 +00:00
llvm.amdgcn.buffer.load.ll AMDGPU/SI: Add a MachineMemOperand when lowering llvm.amdgcn.buffer.load.* 2016-12-20 17:19:44 +00:00
llvm.amdgcn.buffer.store.format.ll [AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. 2017-06-02 14:19:25 +00:00
llvm.amdgcn.buffer.store.ll [AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. 2017-06-02 14:19:25 +00:00
llvm.amdgcn.buffer.wbinvl1.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.buffer.wbinvl1.sc.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.buffer.wbinvl1.vol.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.class.f16.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
llvm.amdgcn.class.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
llvm.amdgcn.cos.f16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.cos.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.cubeid.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.cubema.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.cubesc.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.cubetc.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.cvt.pkrtz.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
llvm.amdgcn.dispatch.id.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.dispatch.ptr.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.div.fixup.f16.ll [AMDGPU] Allow SDWA in instructions with immediates and SGPRs 2017-05-30 16:49:24 +00:00
llvm.amdgcn.div.fixup.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.div.fmas.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
llvm.amdgcn.div.scale.ll AMDGPU: Fix handling of div_scale with undef inputs 2017-08-01 20:49:41 +00:00
llvm.amdgcn.ds.bpermute.ll [AMDGPU] Add a new pass to insert waitcnts. Leave under an option for testing. 2017-04-12 03:25:12 +00:00
llvm.amdgcn.ds.permute.ll [AMDGPU] Add a new pass to insert waitcnts. Leave under an option for testing. 2017-04-12 03:25:12 +00:00
llvm.amdgcn.ds.swizzle.ll [AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. 2017-06-02 14:19:25 +00:00
llvm.amdgcn.exp.compr.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.exp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.fcmp.ll [AMDGPU] Allow SDWA in instructions with immediates and SGPRs 2017-05-30 16:49:24 +00:00
llvm.amdgcn.fdiv.fast.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.fmed3.f16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.fmed3.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.fmul.legacy.ll [AMDGPU] Allow SDWA in instructions with immediates and SGPRs 2017-05-30 16:49:24 +00:00
llvm.amdgcn.fract.f16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.fract.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.frexp.exp.f16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.frexp.exp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.frexp.mant.f16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.frexp.mant.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.groupstaticsize.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.icmp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.image.atomic.ll
llvm.amdgcn.image.gather4.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.image.getlod.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.image.ll [AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. 2017-06-02 14:19:25 +00:00
llvm.amdgcn.image.sample.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.image.sample.o.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.implicit.buffer.ptr.hsa.ll AMDGPU: Partially fix implicit.buffer.ptr intrinsic handling 2017-06-26 03:01:31 +00:00
llvm.amdgcn.implicit.buffer.ptr.ll AMDGPU: Partially fix implicit.buffer.ptr intrinsic handling 2017-06-26 03:01:31 +00:00
llvm.amdgcn.implicitarg.ptr.ll AMDGPU: Annotate implicitarg.ptr usage 2017-07-28 15:52:08 +00:00
llvm.amdgcn.init.exec.ll AMDGPU: Add new amdgcn.init.exec intrinsics 2017-04-28 20:21:58 +00:00
llvm.amdgcn.interp.ll AMDGPU: Add cvt.pkrtz intrinsic 2017-02-22 00:27:34 +00:00
llvm.amdgcn.kernarg.segment.ptr.ll AMDGPU: Detect kernarg segment pointer 2017-07-14 00:11:13 +00:00
llvm.amdgcn.ldexp.f16.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
llvm.amdgcn.ldexp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.lerp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.log.clamp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.mbcnt.ll [AMDGPU][MC] Corrected several VI opcodes to avoid printing _e64 2017-05-15 14:28:23 +00:00
llvm.amdgcn.mov.dpp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.mqsad.pk.u16.u8.ll [AMDGPU] Eliminate SGPR to VGPR copy when possible 2017-06-20 18:32:42 +00:00
llvm.amdgcn.mqsad.u32.u8.ll AMDGPU: Use correct register names in inline assembly 2017-06-08 19:03:20 +00:00
llvm.amdgcn.msad.u8.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.ps.live.ll [llvm] Remove redundant check-prefix=CHECK from tests. NFC. 2017-07-17 17:32:45 +00:00
llvm.amdgcn.qsad.pk.u16.u8.ll [AMDGPU] Eliminate SGPR to VGPR copy when possible 2017-06-20 18:32:42 +00:00
llvm.amdgcn.queue.ptr.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.rcp.f16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.rcp.legacy.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.rcp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.readfirstlane.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.readlane.ll AMDGPU: Move v_readlane lane select from VGPR to SGPR 2017-04-24 17:17:36 +00:00
llvm.amdgcn.rsq.clamp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.rsq.f16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.rsq.legacy.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.rsq.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.s.barrier.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
llvm.amdgcn.s.dcache.inv.ll [AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. 2017-06-02 14:19:25 +00:00
llvm.amdgcn.s.dcache.inv.vol.ll [AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. 2017-06-02 14:19:25 +00:00
llvm.amdgcn.s.dcache.wb.ll [AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. 2017-06-02 14:19:25 +00:00
llvm.amdgcn.s.dcache.wb.vol.ll [AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. 2017-06-02 14:19:25 +00:00
llvm.amdgcn.s.decperflevel.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.s.getpc.ll Resubmit r303859 with test fixed. 2017-05-26 20:38:26 +00:00
llvm.amdgcn.s.getreg.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.s.incperflevel.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.s.memrealtime.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.s.memtime.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.s.sleep.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.s.waitcnt.ll [llvm] Remove redundant check-prefix=CHECK from tests. NFC. 2017-07-17 17:32:45 +00:00
llvm.amdgcn.sad.hi.u8.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.sad.u8.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.sad.u16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.sbfe.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
llvm.amdgcn.sendmsg.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.sffbh.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
llvm.amdgcn.sin.f16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.sin.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.tbuffer.load.ll [AMDGPU] Add intrinsics for tbuffer load and store 2017-06-22 16:29:22 +00:00
llvm.amdgcn.tbuffer.store.ll [AMDGPU] Add intrinsics for tbuffer load and store 2017-06-22 16:29:22 +00:00
llvm.amdgcn.trig.preop.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
llvm.amdgcn.ubfe.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
llvm.amdgcn.unreachable.ll Fix test from polluting the source tree 2017-04-22 07:53:40 +00:00
llvm.amdgcn.wave.barrier.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.workgroup.id.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgcn.workitem.id.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.amdgpu.kilp.ll
llvm.ceil.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.cos.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.cos.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.dbg.value.ll [AMDGPU] Move SiShrinkInstruction and SDWAPeephole to SSAOptimization passes 2017-04-07 10:53:12 +00:00
llvm.exp2.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.exp2.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.floor.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.fma.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.fmuladd.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.log2.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.log2.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.maxnum.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.memcpy.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.minnum.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.pow.ll
llvm.r600.cube.ll AMDGPU: Remove llvm.AMDGPU.cube intrinsic 2017-02-16 19:09:04 +00:00
llvm.r600.dot4.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.r600.group.barrier.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.r600.read.local.size.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.r600.recipsqrt.clamped.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.r600.recipsqrt.ieee.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.r600.tex.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.rint.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.rint.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.rint.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.round.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.round.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.sin.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.sin.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
llvm.sqrt.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
llvm.trunc.f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
load-constant-f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
load-constant-i1.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
load-constant-i8.ll [AMDGPU] Add INDIRECT_BASE_ADDR to R600_Reg32 class (PR33045) 2017-05-23 21:27:15 +00:00
load-constant-i16.ll [AMDGPU] Add INDIRECT_BASE_ADDR to R600_Reg32 class (PR33045) 2017-05-23 21:27:15 +00:00
load-constant-i32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
load-constant-i64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
load-global-f32.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
load-global-f64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
load-global-i1.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
load-global-i8.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
load-global-i16.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
load-global-i32.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
load-global-i64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
load-input-fold.ll AMDGPU: Remove llvm.AMDGPU.rsq intrinsic 2017-02-16 19:08:58 +00:00
load-local-f32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
load-local-f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
load-local-i1.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
load-local-i8.ll [AMDGPU] Add INDIRECT_BASE_ADDR to R600_Reg32 class (PR33045) 2017-05-23 21:27:15 +00:00
load-local-i16.ll [AMDGPU] Add INDIRECT_BASE_ADDR to R600_Reg32 class (PR33045) 2017-05-23 21:27:15 +00:00
load-local-i32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
load-local-i64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
load-weird-sizes.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
local-64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
local-atomics.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
local-atomics64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
local-memory.amdgcn.ll [AMDGPU] Generate range metadata for workitem id 2017-04-12 20:48:56 +00:00
local-memory.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
local-memory.r600.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
local-stack-slot-offset.ll Enable FeatureFlatForGlobal on Volcanic Islands 2017-01-24 22:02:15 +00:00
loop-address.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
loop-idiom.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
loop_break.ll Revert "StructurizeCFG: Directly invert cmp instructions" 2017-04-24 20:25:01 +00:00
lower-mem-intrinsics.ll Extend memcpy expansion in Transform/Utils to handle wider operand types. 2017-07-07 02:00:06 +00:00
lower-range-metadata-intrinsic-call.ll [AMDGPU] Generate range metadata for workitem id 2017-04-12 20:48:56 +00:00
lshl64-to-32.ll [AMDGPU] Narrow lshl from 64 to 32 bit if possible 2017-05-22 16:58:10 +00:00
lshr.v2i16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
macro-fusion-cluster-vcc-uses.mir AMDGPU: Add macro fusion schedule DAG mutation 2017-07-06 20:57:05 +00:00
mad-combine.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
mad24-get-global-id.ll [AMDGPU] Allow SDWA in instructions with immediates and SGPRs 2017-05-30 16:49:24 +00:00
mad_int24.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
mad_uint24.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
madak.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
madmk.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
max-literals.ll
max.i16.ll [AMDGPU] Resubmit SDWA peephole: enable by default 2017-04-06 15:03:28 +00:00
max.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
max3.ll AMDGPU: Fix min3/max3 combines for f16/i16 2017-05-17 19:25:06 +00:00
mem-builtins.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
memory-legalizer-atomic-cmpxchg.ll AMDGPU: Implement memory model 2017-07-21 21:19:23 +00:00
memory-legalizer-atomic-fence.ll AMDGPU: Implement memory model 2017-07-21 21:19:23 +00:00
memory-legalizer-atomic-load.ll AMDGPU: Implement memory model 2017-07-21 21:19:23 +00:00
memory-legalizer-atomic-rmw.ll AMDGPU: Implement memory model 2017-07-21 21:19:23 +00:00
memory-legalizer-atomic-store.ll AMDGPU: Implement memory model 2017-07-21 21:19:23 +00:00
memory-legalizer-invalid-syncscope.ll AMDGPU: Implement memory model 2017-07-21 21:19:23 +00:00
merge-m0.mir MIR: remove explicit "noVRegs" property. 2017-05-30 21:28:57 +00:00
merge-store-crash.ll [AMDGPU] Add intrinsics for tbuffer load and store 2017-06-22 16:29:22 +00:00
merge-store-usedef.ll [AMDGPU] Add intrinsics for tbuffer load and store 2017-06-22 16:29:22 +00:00
merge-stores.ll [DAG] Fix typo preventing some stores merges to truncated stores. 2017-07-23 02:06:28 +00:00
mesa_regression.ll Fix for regression after Global Load Scalarization patch 2016-12-15 15:17:19 +00:00
min.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
min3.ll AMDGPU: Fix min3/max3 combines for f16/i16 2017-05-17 19:25:06 +00:00
misched-killflags.mir ScheduleDAGInstrs: Fix fixupKills() adding too many kill flags. 2017-06-27 00:58:48 +00:00
missing-store.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
move-addr64-rsrc-dead-subreg-writes.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
move-to-valu-atomicrmw.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
move-to-valu-worklist.ll [AMDGPU] Do not insert an instruction into worklist twice in movetovalu 2017-07-14 17:56:55 +00:00
movreld-bug.ll
movrels-bug.mir Move .mir tests to appropriate directories 2016-12-09 19:08:15 +00:00
mubuf-offset-private.ll AMDGPU: Detect kernarg segment pointer 2017-07-14 00:11:13 +00:00
mubuf-shader-vgpr.ll Enable FeatureFlatForGlobal on Volcanic Islands 2017-01-24 22:02:15 +00:00
mubuf.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
mul.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
mul_int24.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
mul_uint24-amdgcn.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
mul_uint24-r600.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
multi-divergent-exit-region.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
multilevel-break.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
nested-calls.ll AMDGPU: Initial implementation of calls 2017-08-01 19:54:18 +00:00
nested-loop-conditions.ll Revert "StructurizeCFG: Directly invert cmp instructions" 2017-04-24 20:25:01 +00:00
no-hsa-graphics-shaders.ll
no-initializer-constant-addrspace.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
no-shrink-extloads.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
nop-data.ll AMDGPU: Actually write nops for writeNopData 2017-04-08 21:28:38 +00:00
not-scalarize-volatile-load.ll AMDGPUAnnotateUniformValue should always treat volatile loads as divergent 2017-06-02 15:25:52 +00:00
nullptr.ll AMDGPU: Treat 0 as private null pointer in addrspacecast lowering 2017-03-13 19:47:31 +00:00
omod.ll AMDGPU: Keep track of modifiers when converting v_mac to v_mad 2017-03-11 05:40:40 +00:00
opencl-image-metadata.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
operand-folding.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
operand-spacing.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
opt-sgpr-to-vgpr-copy.mir [AMDGPU] Eliminate SGPR to VGPR copy when possible 2017-06-20 18:32:42 +00:00
optimize-if-exec-masking.mir MIParser/MIRPrinter: Compute block successors if not explicitely specified 2017-05-05 21:09:30 +00:00
or.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
over-max-lds-size.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
pack.v2f16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
pack.v2i16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
packed-op-sel.ll AMDGPU: Make better use of op_sel with high components 2017-05-17 20:30:58 +00:00
packetizer.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
parallelandifcollapse.ll fix typos in comments; NFC 2017-07-16 08:11:56 +00:00
parallelorifcollapse.ll fix typos in comments; NFC 2017-07-16 08:11:56 +00:00
partial-sgpr-to-vgpr-spills.ll AMDGPU: Use correct register names in inline assembly 2017-06-08 19:03:20 +00:00
partially-dead-super-register-immediate.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
predicate-dp4.ll
predicates.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
private-access-no-objects.ll AMDGPU: Detect kernarg segment pointer 2017-07-14 00:11:13 +00:00
private-element-size.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
private-memory-atomics.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
private-memory-broken.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
private-memory-r600.ll [AMDGPU] Generate range metadata for workitem id 2017-04-12 20:48:56 +00:00
promote-alloca-addrspacecast.ll AMDGPU: Fix AMDGPUPromoteAlloca breaking addrspacecasts 2016-12-10 00:52:50 +00:00
promote-alloca-array-aggregate.ll [AMDGPU] Fix for issue in alloca to vector promotion pass 2017-06-09 14:16:22 +00:00
promote-alloca-array-allocation.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
promote-alloca-bitcast-function.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
promote-alloca-calling-conv.ll AMDGPU: Don't promote alloca to LDS for leaf functions 2017-05-02 18:33:18 +00:00
promote-alloca-globals.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
promote-alloca-invariant-markers.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
promote-alloca-lifetime.ll Add address space mangling to lifetime intrinsics 2017-04-10 20:18:21 +00:00
promote-alloca-mem-intrinsics.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
promote-alloca-no-opts.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
promote-alloca-padding-size-estimate.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
promote-alloca-stored-pointer-value.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
promote-alloca-to-lds-icmp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
promote-alloca-to-lds-phi.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
promote-alloca-to-lds-select.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
promote-alloca-unhandled-intrinsic.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
promote-alloca-volatile.ll AMDGPU/SI: Don't promote to vector if the load/store is volatile. 2017-05-12 20:31:12 +00:00
pv-packing.ll
pv.ll AMDGPU: Remove llvm.AMDGPU.clamp intrinsic 2017-02-21 23:46:04 +00:00
r600-constant-array-fixup.ll
r600-encoding.ll
r600-export-fix.ll
r600-infinite-loop-bug-while-reorganizing-vector.ll AMDGPU: Remove llvm.AMDGPU.cube intrinsic 2017-02-16 19:09:04 +00:00
r600-legalize-umax-bug.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
r600.alu-limits.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
r600.amdgpu-alias-analysis.ll AMDGPU/R600: Fix amdgpu alias analysis pass. 2017-03-31 19:26:23 +00:00
r600.bitcast.ll [AMDGPU] Add INDIRECT_BASE_ADDR to R600_Reg32 class (PR33045) 2017-05-23 21:27:15 +00:00
r600.global_atomics.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
r600.private-memory.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
r600.work-item-intrinsics.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
r600cfg.ll
rcp-pattern.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
read-register-invalid-subtarget.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
read-register-invalid-type-i32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
read-register-invalid-type-i64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
read_register.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
readcyclecounter.ll AMDGPU: Fix crash when scheduling non-memory SMRD instructions 2017-04-24 16:53:52 +00:00
reduce-load-width-alignment.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
reduce-store-width-alignment.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
reg-coalescer-sched-crash.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
regcoal-subrange-join.mir [RegisterCoalescer] Fix for SubRange join unreachable 2017-07-06 10:07:57 +00:00
regcoalesce-dbg.mir AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
regcoalesce-prune.mir Fix typo in test 2017-05-19 17:25:20 +00:00
register-count-comments.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
rename-disconnected-bug.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
rename-independent-subregs-mac-operands.mir [AMDGPU] resubmit r308179: CodeGen: check dst operand type to determine if omod is supported for VOP3 instructions 2017-07-18 14:23:26 +00:00
rename-independent-subregs.mir MIParser/MIRPrinter: Compute block successors if not explicitely specified 2017-05-05 21:09:30 +00:00
reorder-stores.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
ret.ll AMDGPU: Remove some uses of llvm.SI.export in tests 2017-02-22 00:02:21 +00:00
ret_jump.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
rewrite-out-arguments-address-space.ll AMDGPU: Look through a bitcast user of an out argument 2017-07-28 19:06:16 +00:00
rewrite-out-arguments.ll AMDGPU: Look through a bitcast user of an out argument 2017-07-28 19:06:16 +00:00
rotl.i64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
rotl.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
rotr.i64.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
rotr.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
rsq.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
rv7x0_count3.ll
s_addk_i32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
s_movk_i32.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
s_mulk_i32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
sad.ll AMDGPU: Add macro fusion schedule DAG mutation 2017-07-06 20:57:05 +00:00
saddo.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
salu-to-valu.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
sampler-resource-id.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
scalar-store-cache-flush.mir AMDGPU: Rename SI_RETURN 2017-03-21 22:18:10 +00:00
scalar_to_vector.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
schedule-fs-loop-nested-if.ll AMDGPU: Remove llvm.AMDGPU.clamp intrinsic 2017-02-21 23:46:04 +00:00
schedule-fs-loop-nested.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
schedule-fs-loop.ll AMDGPU: Remove llvm.AMDGPU.clamp intrinsic 2017-02-21 23:46:04 +00:00
schedule-global-loads.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
schedule-if-2.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
schedule-if.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
schedule-kernel-arg-loads.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
schedule-regpressure-limit.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
schedule-regpressure-limit2.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
schedule-regpressure.mir CodeGen: Rename DEBUG_TYPE to match passnames 2017-05-25 21:26:32 +00:00
schedule-vs-if-nested-loop-failure.ll
schedule-vs-if-nested-loop.ll
scheduler-subrange-crash.ll AMDGPU: Remove SITypeRewriter 2017-06-28 21:38:50 +00:00
scratch-buffer.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
scratch-simple.ll AMDGPU: Figure out private memory regs after lowering 2017-07-18 16:44:56 +00:00
sdiv.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
sdivrem24.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
sdivrem64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
sdwa-gfx9.mir [AMDGPU] SDWA: add support for GFX9 in peephole pass 2017-06-22 06:26:41 +00:00
sdwa-peephole-instr.mir [AMDGPU] resubmit r308179: CodeGen: check dst operand type to determine if omod is supported for VOP3 instructions 2017-07-18 14:23:26 +00:00
sdwa-peephole.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
sdwa-scalar-ops.mir [AMDGPU] SDWA: add support for GFX9 in peephole pass 2017-06-22 06:26:41 +00:00
sdwa-vop2-64bit.mir [AMDGPU] resubmit r308179: CodeGen: check dst operand type to determine if omod is supported for VOP3 instructions 2017-07-18 14:23:26 +00:00
select-fabs-fneg-extract-legacy.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
select-fabs-fneg-extract.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
select-i1.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
select-opt.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
select-vectors.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
select.f16.ll AMDGPU: Add macro fusion schedule DAG mutation 2017-07-06 20:57:05 +00:00
select.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
select64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
selectcc-cnd.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
selectcc-cnde-int.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
selectcc-icmp-select-float.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
selectcc-opt.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
selectcc.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
selected-stack-object.ll [test] Remove a unwanted match for `XFAIL:`. 2017-01-20 02:01:04 +00:00
set-dx10.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
setcc-equivalent.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
setcc-fneg-constant.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
setcc-opt.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
setcc-sext.ll [AMDGPU] Simplify setcc (sext from i1 b), -1|0, cc 2017-06-27 18:53:03 +00:00
setcc.ll AMDGPU: Add macro fusion schedule DAG mutation 2017-07-06 20:57:05 +00:00
setcc64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
seto.ll AMDGPU: Remove some uses of llvm.SI.export in tests 2017-02-22 00:02:21 +00:00
setuo.ll AMDGPU: Remove some uses of llvm.SI.export in tests 2017-02-22 00:02:21 +00:00
sext-eliminate.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
sext-in-reg-failure-r600.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
sext-in-reg.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
sgpr-control-flow.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
sgpr-copy-duplicate-operand.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
sgpr-copy.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
sgprcopies.ll AMDGPU : Fix common dominator of two incoming blocks terminates with uniform branch issue. 2017-04-12 23:51:47 +00:00
shared-op-cycle.ll
shift-and-i64-ubfe.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
shift-and-i128-ubfe.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
shift-i64-opts.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
shl-add-to-add-shl.ll [AMDGPU] Convert shl (add) into add (shl) 2017-05-23 15:59:58 +00:00
shl.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
shl.v2i16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
shl_add_constant.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
shl_add_ptr.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
shrink-add-sub-constant.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
shrink-carry.mir [AMDGPU] Fix illegal shrink of V_SUBB_U32 and V_ADDC_U32 2017-06-20 20:33:44 +00:00
shrink-vop3-carry-out.mir AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
si-annotate-cf-noloop.ll AMDGPU: Unify divergent function exits. 2017-03-24 19:52:05 +00:00
si-annotate-cf-unreachable.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
si-annotate-cf.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
si-annotate-cfg-loop-assert.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
si-fix-sgpr-copies.mir MIParser/MIRPrinter: Compute block successors if not explicitely specified 2017-05-05 21:09:30 +00:00
si-instr-info-correct-implicit-operands.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
si-lod-bias.ll AMDGPU: Remove SITypeRewriter 2017-06-28 21:38:50 +00:00
si-lower-control-flow-unreachable-block.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
si-scheduler.ll AMDGPU: Convert image intrinsic uses in tests 2017-03-21 16:24:12 +00:00
si-sgpr-spill.ll AMDGPU: Remove SITypeRewriter 2017-06-28 21:38:50 +00:00
si-spill-cf.ll AMDGPU: Remove SITypeRewriter 2017-06-28 21:38:50 +00:00
si-spill-sgpr-stack.ll AMDGPU: Use correct register names in inline assembly 2017-06-08 19:03:20 +00:00
si-triv-disjoint-mem-access.ll AMDGPU: Make areMemAccessesTriviallyDisjoint more aware of segment flat 2017-07-29 01:26:21 +00:00
si-vector-hang.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
sign_extend.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
sint_to_fp.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
sint_to_fp.i64.ll [AMDGPU] Eliminate SGPR to VGPR copy when possible 2017-06-20 18:32:42 +00:00
sint_to_fp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
sitofp.f16.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
skip-if-dead.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
smed3.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
sminmax.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
sminmax.v2i16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
smrd-vccz-bug.ll [AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. 2017-06-02 14:19:25 +00:00
smrd.ll AMDGPU: Remove SITypeRewriter 2017-06-28 21:38:50 +00:00
sopk-compares.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
spill-alloc-sgpr-init-bug.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
spill-cfg-position.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
spill-empty-live-interval.mir RA: Remove another assert on empty intervals 2017-07-22 00:24:01 +00:00
spill-m0.ll RegisterScavenging: Followup to r305625 2017-06-20 18:43:14 +00:00
spill-scavenge-offset.ll AMDGPU: Use correct register names in inline assembly 2017-06-08 19:03:20 +00:00
spill-to-smem-m0.ll AMDGPU: M0 operands to spill/restore opcodes are dead 2017-06-27 08:04:13 +00:00
spill-wide-sgpr.ll AMDGPU: Always allocate emergency stack slot at offset 0 2017-02-22 21:05:25 +00:00
split-scalar-i64-add.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
split-smrd.ll AMDGPU: Remove SITypeRewriter 2017-06-28 21:38:50 +00:00
split-vector-memoperand-offsets.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
splitkit.mir SplitKit: Fix subreg copy related problems 2017-03-21 21:58:08 +00:00
sra.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
srem.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
srl.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
ssubo.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
stack-slot-color-sgpr-vgpr-spills.mir Add an ID field to StackObjects 2017-07-20 21:03:45 +00:00
store-barrier.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
store-global.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
store-local.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
store-private.ll [AMDGPU] Add INDIRECT_BASE_ADDR to R600_Reg32 class (PR33045) 2017-05-23 21:27:15 +00:00
store-v3i64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
store-vector-ptrs.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
store_typed.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
structurize.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
structurize1.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
sub.i16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
sub.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
sub.v2i16.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
subreg-coalescer-crash.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
subreg-coalescer-undef-use.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
subreg-eliminate-dead.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
subreg-intervals.mir MIParser/MIRPrinter: Compute block successors if not explicitely specified 2017-05-05 21:09:30 +00:00
subreg_interference.mir AMDGPU: Start defining a calling convention 2017-05-17 21:56:25 +00:00
swizzle-export.ll
syncscopes.ll AMDGPU: Implement memory model 2017-07-21 21:19:23 +00:00
target-cpu.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
tex-clause-antidep.ll
texture-input-merge.ll
trap.ll AMDGPU: Detect kernarg segment pointer 2017-07-14 00:11:13 +00:00
trunc-bitcast-vector.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
trunc-cmp-constant.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
trunc-store-f64-to-f16.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
trunc-store-i1.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
trunc-store.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
trunc-vector-store-assertion-failure.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
trunc.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
tti-unroll-prefs.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
uaddo.ll AMDGPU: Add macro fusion schedule DAG mutation 2017-07-06 20:57:05 +00:00
udiv.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
udivrem.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
udivrem24.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
udivrem64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
uint_to_fp.f64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
uint_to_fp.i64.ll [AMDGPU] Eliminate SGPR to VGPR copy when possible 2017-06-20 18:32:42 +00:00
uint_to_fp.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
uitofp.f16.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
umed3.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
unaligned-load-store.ll AMDGPU : Widen extending scalar loads to 32-bits. 2017-07-26 21:07:28 +00:00
undefined-subreg-liverange.ll AMDGPU: Use correct register names in inline assembly 2017-06-08 19:03:20 +00:00
unhandled-loop-condition-assertion.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
uniform-branch-intrinsic-cond.ll AMDGPU: Implement early ifcvt target hooks. 2017-01-25 04:25:02 +00:00
uniform-cfg.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
uniform-crash.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
uniform-loop-inside-nonuniform.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
unify-metadata.ll [AMDGPU] Turn AMDGPUUnifyMetadata back into module pass 2017-01-27 16:38:10 +00:00
unigine-liveness-crash.ll AMDGPU: Convert image intrinsic uses in tests 2017-03-21 16:24:12 +00:00
unknown-processor.ll [AMDGPU] Add INDIRECT_BASE_ADDR to R600_Reg32 class (PR33045) 2017-05-23 21:27:15 +00:00
unroll.ll [AMDGPU] Unroll more to eliminate phis and conditions 2017-04-07 16:26:28 +00:00
unsupported-cc.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
urem.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
use-sgpr-multiple-times.ll [AMDGPU] Allow SDWA in instructions with immediates and SGPRs 2017-05-30 16:49:24 +00:00
usubo.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
v1i64-kernel-arg.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
v_cndmask.ll AMDGPU: Add macro fusion schedule DAG mutation 2017-07-06 20:57:05 +00:00
v_cvt_pk_u8_f32.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
v_mac.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
v_mac_f16.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
v_madak_f16.ll [AMDGPU][MC] Corrected v_madak/madmk to avoid printing "_e32" in disassembler output 2017-05-10 13:00:28 +00:00
valu-i1.ll [AMDGPU] Optimize SI_IF lowering for simple if regions 2017-07-26 21:29:15 +00:00
vccz-corrupt-bug-workaround.mir [AMDGPU] resubmit r308179: CodeGen: check dst operand type to determine if omod is supported for VOP3 instructions 2017-07-18 14:23:26 +00:00
vector-alloca.ll AMDGPU/SI: Move the local memory usage related checking after calling convention checking in PromoteAlloca 2017-05-23 20:25:41 +00:00
vector-extract-insert.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
vectorize-global-local.ll [AMDGPU] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +00:00
vertex-fetch-encoding.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
vgpr-spill-emergency-stack-slot-compute.ll AMDGPU: Figure out private memory regs after lowering 2017-07-18 16:44:56 +00:00
vgpr-spill-emergency-stack-slot.ll AMDGPU: Figure out private memory regs after lowering 2017-07-18 16:44:56 +00:00
vi-removed-intrinsics.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
vop-shrink-frame-index.mir AMDGPU: Allow SIShrinkInstructions to fold FrameIndexes 2017-07-10 20:04:35 +00:00
vop-shrink-non-ssa.mir AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
vop-shrink.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
vselect.ll AMDGPU: Add macro fusion schedule DAG mutation 2017-07-06 20:57:05 +00:00
vselect64.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
vtx-fetch-branch.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
vtx-schedule.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
wait.ll AMDGPU: Remove llvm.SI.vs.load.input 2017-04-03 21:45:13 +00:00
waitcnt-flat.ll AMDGPU: Start selecting global instructions 2017-07-29 01:03:53 +00:00
waitcnt-looptest.ll [AMDGPU] In the new waitcnt insertion pass, use getHeader 2017-05-05 21:10:17 +00:00
waitcnt-permute.mir AMDGPU: Remove unnecessary IR from MIR tests 2017-07-06 20:56:57 +00:00
waitcnt.mir AMDGPU: Start adding offset fields to flat instructions 2017-06-12 15:55:58 +00:00
widen_extending_scalar_loads.ll AMDGPU : Widen extending scalar loads to 32-bits. 2017-07-26 21:07:28 +00:00
wqm.ll [AMDGPU] Allow SDWA in instructions with immediates and SGPRs 2017-05-30 16:49:24 +00:00
write-register-vgpr-into-sgpr.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
write_register.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
wrong-transalu-pos-fix.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
xfail.r600.bitcast.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
xor.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
zero_extend.ll AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +00:00
zext-i64-bit-operand.ll AMDGPU: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +00:00
zext-lid.ll AMDGPU: Make intrinsics speculatable 2017-05-02 16:57:44 +00:00

README

+==============================================================================+
| How to organize the lit tests                                                |
+==============================================================================+

- If you write a test for matching a single DAG opcode or intrinsic, it should
  go in a file called {opcode_name,intrinsic_name}.ll (e.g. fadd.ll)

- If you write a test that matches several DAG opcodes and checks for a single
  ISA instruction, then that test should go in a file called {ISA_name}.ll (e.g.
  bfi_int.ll

- For all other tests, use your best judgement for organizing tests and naming
  the files.

+==============================================================================+
| Naming conventions                                                           |
+==============================================================================+

- Use dash '-' and not underscore '_' to separate words in file names, unless
  the file is named after a DAG opcode or ISA instruction that has an
  underscore '_' in its name.