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
History
Matt Arsenault c06574ffc0 AMDGPU: Add pass to replace out arguments 
It is better to return arguments directly in registers
if we are making a call rather than introducing expensive
stack usage. In one of sample compile from one of
Blender's many kernel variants, this fires on about
~20 different functions. Future improvements may be to
recognize simple cases where the pointer is indexing a small
array. This also fails when the store to the out argument
is in a separate block from the return, which happens in
a few of the Blender functions. This should also probably
be using MemorySSA which might help with that.

I'm not sure this is correct as a FunctionPass, but
MemoryDependenceAnalysis seems to not work with
a ModulePass.

I'm also not sure where it should run.I think it should
run  before DeadArgumentElimination, so maybe either
EP_CGSCCOptimizerLate or EP_ScalarOptimizerLate.

llvm-svn: 309416
 		2017-07-28 18:40:05 +00:00
..
GlobalISel AMDGPU/GlobalISel: Mark 32-bit G_OR as legal 2017-07-26 20:00:53 +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: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +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: Add macro fusion schedule DAG mutation 2017-07-06 20:57:05 +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] Untangle SDWA pass from SIShrinkInstructions 2017-06-03 17:39:47 +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-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
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: Setup SP/FP in callee function prolog/epilog 2017-06-26 17:53:59 +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] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +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
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: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +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: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +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] fcaninicalize optimization for GFX9+ 2017-07-13 23:59:15 +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] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +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: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +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] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +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: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +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: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +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: Setup SP/FP in callee function prolog/epilog 2017-06-26 17:53:59 +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: Implement memory model 2017-07-21 21:19:23 +00:00
global_atomics_i64.ll AMDGPU: Implement memory model 2017-07-21 21:19:23 +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] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +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] Untangle SDWA pass from SIShrinkInstructions 2017-06-03 17:39:47 +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][MC] Corrected several VI opcodes to avoid printing _e64 2017-05-15 14:28:23 +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: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +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: Make auto waitcnt before barrier a feature 2017-06-02 17:40:26 +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: Temporarily disable packed inlinable literals (v2f16, v2i16) 2017-04-21 19:45:22 +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] Add INDIRECT_BASE_ADDR to R600_Reg32 class (PR33045) 2017-05-23 21:27:15 +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-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/GFX9: Do not use v_pack_b32_f16 when packing 2017-04-13 23:17:00 +00:00
pack.v2i16.ll AMDGPU/GFX9: Do not use v_pack_b32_f16 when packing 2017-04-13 23:17:00 +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: Add pass to replace out arguments 2017-07-28 18:40:05 +00:00
rewrite-out-arguments.ll AMDGPU: Add pass to replace out arguments 2017-07-28 18:40:05 +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] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +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] Untangle SDWA pass from SIShrinkInstructions 2017-06-03 17:39:47 +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] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +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] Switch scalarize global loads ON by default 2017-07-04 17:32:00 +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] Add INDIRECT_BASE_ADDR to R600_Reg32 class (PR33045) 2017-05-23 21:27:15 +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: Allow SIShrinkInstructions to work in non-SSA 2017-07-10 19:53:57 +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: Mark all unspecified CC functions in tests as amdgpu_kernel 2017-03-21 21:39:51 +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.