1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-22 20:43:44 +02:00
llvm-mirror/test/CodeGen/AMDGPU
Marek Olsak e93050ba9d AMDGPU/SI: Increase SGPR limit to 96 on Tonga/Iceland
Summary:
This is the setting of the Vulkan closed source driver.

It decreases the max wave count from 10 to 8.

26010 shaders in 14650 tests
Totals:
VGPRS: 829593 -> 808440 (-2.55 %)
Spilled SGPRs: 81878 -> 42226 (-48.43 %)
Spilled VGPRs: 367 -> 358 (-2.45 %)
Scratch VGPRs: 1764 -> 1748 (-0.91 %) dwords per thread
Code Size: 36677864 -> 35923932 (-2.06 %) bytes

There is a massive decrease in SGPR spilling in general and -7.4% spilled
VGPRs for DiRT Showdown (= SGPRs spilled to scratch?)

Reviewers: arsenm, tstellarAMD, nhaehnle

Subscribers: arsenm, llvm-commits, kzhuravl

Differential Revision: https://reviews.llvm.org/D23034

llvm-svn: 277867
2016-08-05 21:23:29 +00:00
..
GlobalISel GlobalISel: omit braces on MachineInstr types when there's only one. 2016-07-26 17:28:01 +00:00
32-bit-local-address-space.ll AMDGPU: Emit error if too much LDS is used 2016-04-28 19:37:35 +00:00
add_i64.ll
add-debug.ll
add.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
addrspacecast-constantexpr.ll AMDGPU: Fix constantexpr addrspacecasts 2016-06-06 20:03:31 +00:00
addrspacecast.ll AMDGPU/SI: Enable the post-ra scheduler 2016-04-30 00:23:06 +00:00
amdgcn.private-memory.ll AMDGPU: Define priorities for register classes 2016-05-21 03:55:07 +00:00
amdgpu-codegenprepare.ll AMDGPU: Use rcp for fdiv 1, x with fpmath metadata 2016-07-26 23:25:44 +00:00
amdgpu-shader-calling-convention.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
amdgpu.private-memory.ll AMDGPU: Remove dead check in AMDGPUPromoteAlloca 2016-07-18 18:34:53 +00:00
amdgpu.work-item-intrinsics.deprecated.ll AMDGPU: Remove read_workdim intrinsic 2016-07-25 20:17:02 +00:00
and-gcn.ll
and.ll MachineScheduler: Fully compare top/bottom candidates 2016-06-25 00:23:00 +00:00
annotate-kernel-features-hsa.ll AMDGPU: Implement addrspacecast 2016-04-25 19:27:24 +00:00
annotate-kernel-features.ll
anyext.ll
array-ptr-calc-i32.ll AMDGPU: Fix promote alloca pass creating huge arrays 2016-05-16 21:19:59 +00:00
array-ptr-calc-i64.ll AMDGPU: Remove llvm.SI.tid intrinsic 2016-06-17 21:18:41 +00:00
atomic_cmp_swap_local.ll MachineScheduler: Fully compare top/bottom candidates 2016-06-25 00:23:00 +00:00
atomic_load_add.ll
atomic_load_sub.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
basic-branch.ll AMDGPU: Track physical registers in SIWholeQuadMode 2016-08-02 19:17:37 +00:00
basic-loop.ll
bfe_uint.ll
bfi_int.ll
bfm.ll
big_alu.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
bitcast.ll AMDGPU: Fix v2i64/v2f64 bitcasts 2016-05-25 18:07:36 +00:00
bitreverse-inline-immediates.ll AMDGPU: Make i64 loads/stores promote to v2i32 2016-05-02 20:07:26 +00:00
bitreverse.ll AMDGPU: Remove brev intrinsic 2016-07-15 21:27:13 +00:00
branch-uniformity.ll AMDGPU: Fix missing verify-machineinstrs in control flow test 2016-07-25 19:39:06 +00:00
bswap.ll
bug-vopc-commute.ll AMDGPU: Guard VOPC instructions against incorrect commute 2016-04-19 21:58:22 +00:00
build_vector.ll
call_fs.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
call.ll AMDGPU: Fix assert when erroring on a call 2016-05-18 16:10:11 +00:00
calling-conventions.ll
captured-frame-index.ll Revert "RegScavenging: Add scavengeRegisterBackwards()" 2016-07-20 00:21:32 +00:00
cayman-loop-bug.ll AMDGPU: Fix a few slightly broken tests 2016-05-18 15:48:44 +00:00
cf_end.ll
cf-loop-on-constant.ll AMDGPU: Un-xfail and add tests 2016-06-24 06:58:01 +00:00
cf-stack-bug.ll
cgp-addressing-modes-flat.ll AMDGPU/SI: Assembler: Unify parsing/printing of operands. 2016-04-29 09:02:30 +00:00
cgp-addressing-modes.ll AMDGPU: Merge / reorganize tests 2016-07-09 08:02:28 +00:00
cgp-bitfield-extract.ll DAGCombiner: Reduce 64-bit BFE pattern to pattern on 32-bit component 2016-04-21 18:03:06 +00:00
ci-use-flat-for-global.ll
cndmask-no-def-vcc.ll AMDGPU: Preserve undef flag on vcc when shrinking v_cndmask_b32 2016-06-20 18:34:00 +00:00
coalescer_distribute.ll
coalescer_remat.ll
codegen-prepare-addrmode-sext.ll
combine_vloads.ll
commute_modifiers.ll AMDGPU: Run SIFoldOperands after PeepholeOptimizer 2016-04-14 21:58:24 +00:00
commute-compares.ll
commute-shifts.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
complex-folding.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
concat_vectors.ll
convergent-inlineasm.ll AMDGPU: Add convergent flag to INLINEASM instruction. 2016-06-22 18:51:08 +00:00
copy-illegal-type.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
copy-to-reg.ll
ctlz_zero_undef.ll AMDGPU: Define a schedule class for COPY. 2016-06-24 23:52:11 +00:00
ctlz.ll AMDGPU: Define a schedule class for COPY. 2016-06-24 23:52:11 +00:00
ctpop64.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
ctpop.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
cttz_zero_undef.ll
cube.ll
cvt_f32_ubyte.ll AMDGPU: Expand unaligned accesses early 2016-07-01 22:55:55 +00:00
cvt_flr_i32_f32.ll
cvt_rpi_i32_f32.ll
dagcombine-reassociate-bug.ll AMDGPU: Add volatile to test loads and stores 2016-04-12 13:38:18 +00:00
dagcombiner-bug-illegal-vec4-int-to-fp.ll
debug.ll
debugger-emit-prologue.ll [AMDGPU] Emit debugger prologue and emit the rest of the debugger fields in the kernel code header 2016-06-25 03:11:28 +00:00
debugger-insert-nops.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
debugger-reserve-regs.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
default-fp-mode.ll AMDGPU: Simplify tests with per function subtargets 2016-07-09 07:55:03 +00:00
detect-dead-lanes.mir MIRParser: Use dot instead of colon to mark subregisters 2016-07-26 21:49:34 +00:00
disconnected-predset-break-bug.ll
drop-mem-operand-move-smrd.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
ds_read2_offset_order.ll MachineScheduler: Fully compare top/bottom candidates 2016-06-25 00:23:00 +00:00
ds_read2_superreg.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
ds_read2.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
ds_read2st64.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
ds_write2.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
ds_write2st64.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
ds-negative-offset-addressing-mode-loop.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
ds-sub-offset.ll
dynamic_stackalloc.ll [AMDGPU] Remove exit-on-error in test (PR27761) 2016-06-23 09:19:16 +00:00
elf.ll AMDGPU/SI: Increase SGPR limit to 96 on Tonga/Iceland 2016-08-05 21:23:29 +00:00
elf.r600.ll
else.ll AMDGPU: add execfix flag to SI_ELSE 2016-07-28 11:39:24 +00:00
empty-function.ll
endcf-loop-header.ll
extload-private.ll AMDGPU: Move subtarget feature checks into passes 2016-06-27 20:32:13 +00:00
extload.ll AMDGPU: Cleanup load tests 2016-06-02 19:54:26 +00:00
extract_vector_elt-f64.ll AMDGPU: Cleanup vector insert/extract tests 2016-05-28 00:51:06 +00:00
extract_vector_elt-i8.ll AMDGPU: Cleanup vector insert/extract tests 2016-05-28 00:51:06 +00:00
extract_vector_elt-i16.ll AMDGPU: Cleanup vector insert/extract tests 2016-05-28 00:51:06 +00:00
extract_vector_elt-i64.ll AMDGPU: Cleanup vector insert/extract tests 2016-05-28 00:51:06 +00:00
extract-vector-elt-build-vector-combine.ll AMDGPU: Un-xfail and add tests 2016-06-24 06:58:01 +00:00
extractelt-to-trunc.ll DAGCombiner: Don't narrow volatile vector loads + extract 2016-06-27 19:31:04 +00:00
fabs.f64.ll
fabs.ll
fadd64.ll
fadd.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
fcanonicalize.ll AMDGPU: Simplify tests with per function subtargets 2016-07-09 07:55:03 +00:00
fceil64.ll [AMDGPU][llvm-mc] v_cndmask_b32: src2 is mandatory; do not enforce VOP2 when src2 == VCC. 2016-06-06 15:23:43 +00:00
fceil.ll
fcmp64.ll
fcmp-cnd.ll
fcmp-cnde-int-args.ll
fcmp.ll
fconst64.ll
fcopysign.f32.ll
fcopysign.f64.ll
fdiv.f64.ll AMDGPU/SI: Assembler: Unify parsing/printing of operands. 2016-04-29 09:02:30 +00:00
fdiv.ll AMDGPU: Change fdiv lowering based on !fpmath metadata 2016-07-19 23:16:53 +00:00
fetch-limits.r600.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
fetch-limits.r700+.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
ffloor.f64.ll AMDGPU: Simplify tests with per function subtargets 2016-07-09 07:55:03 +00:00
ffloor.ll
flat_atomics_i64.ll AMDGPU: Fix flat atomics 2016-06-09 23:42:54 +00:00
flat_atomics.ll AMDGPU: Fix flat atomics 2016-06-09 23:42:54 +00:00
flat-address-space.ll
flat-scratch-reg.ll AMDGPU: Add missing tests for xnack option for HSA 2016-07-26 16:45:50 +00:00
floor.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
fma-combine.ll AMDGPU: Add volatile to test loads and stores 2016-04-12 13:38:18 +00:00
fma.f64.ll
fma.ll AMDGPU: Run SIFoldOperands after PeepholeOptimizer 2016-04-14 21:58:24 +00:00
fmad.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
fmax3.f64.ll AMDGPU/SI: Assembler: Unify parsing/printing of operands. 2016-04-29 09:02:30 +00:00
fmax3.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
fmax_legacy.f64.ll
fmax_legacy.ll AMDGPU: Add volatile to test loads and stores 2016-04-12 13:38:18 +00:00
fmax.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
fmaxnum.f64.ll
fmaxnum.ll
fmed3.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
fmin3.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
fmin_legacy.f64.ll
fmin_legacy.ll AMDGPU: Add volatile to test loads and stores 2016-04-12 13:38:18 +00:00
fmin.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
fminnum.f64.ll
fminnum.ll
fmul64.ll
fmul-2-combine-multi-use.ll AMDGPU: Add volatile to test loads and stores 2016-04-12 13:38:18 +00:00
fmul.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
fmuladd.ll AMDGPU: Add volatile to test loads and stores 2016-04-12 13:38:18 +00:00
fnearbyint.ll
fneg-fabs.f64.ll MachineScheduler: Fully compare top/bottom candidates 2016-06-25 00:23:00 +00:00
fneg-fabs.ll
fneg.f64.ll AMDGPU: Run SIFoldOperands after PeepholeOptimizer 2016-04-14 21:58:24 +00:00
fneg.ll
fp16_to_fp.ll
fp32_to_fp16.ll
fp_to_sint.f64.ll AMDGPU: Fix i1 fp_to_int 2016-07-22 17:01:21 +00:00
fp_to_sint.ll AMDGPU: Fix i1 fp_to_int 2016-07-22 17:01:21 +00:00
fp_to_uint.f64.ll AMDGPU: Fix i1 fp_to_int 2016-07-22 17:01:21 +00:00
fp_to_uint.ll AMDGPU: Fix i1 fp_to_int 2016-07-22 17:01:21 +00:00
fp-classify.ll
fpext.ll AMDGPU: Cleanup load tests 2016-06-02 19:54:26 +00:00
fptrunc.ll
fract.f64.ll AMDGPU: Add fract intrinsic 2016-05-28 00:19:52 +00:00
fract.ll AMDGPU: Add fract intrinsic 2016-05-28 00:19:52 +00:00
frem.ll AMDGPU/SI: Fix 32-bit fdiv lowering 2016-06-09 19:17:15 +00:00
fsqrt.f64.ll AMDGPU: Merge / reorganize tests 2016-07-09 08:02:28 +00:00
fsqrt.ll AMDGPU: Merge / reorganize tests 2016-07-09 08:02:28 +00:00
fsub64.ll AMDGPU: Run SIFoldOperands after PeepholeOptimizer 2016-04-14 21:58:24 +00:00
fsub.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
ftrunc.f64.ll AMDGPU: Define a schedule class for COPY. 2016-06-24 23:52:11 +00:00
ftrunc.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
gep-address-space.ll
global_atomics_i64.ll AMDGPU: Fix i64 global cmpxchg 2016-06-09 23:42:48 +00:00
global_atomics.ll AMDGPU: Fix missing and broken check lines in atomic tests 2016-06-09 23:42:44 +00:00
global-constant.ll Revert "[AMDGPU] Emit read-only data to .rodata for hsa" 2016-07-22 23:46:40 +00:00
global-directive.ll
global-variable-relocs.ll AMDGPU/SI: Add support for R_AMDGPU_GOTPCREL 2016-07-13 14:23:33 +00:00
gv-const-addrspace.ll AMDGPU/R600: Fold global address operand 2016-05-13 20:39:31 +00:00
gv-offset-folding.ll AMDGPU/SI: Make sure not to fold offsets into local address space globals 2016-06-25 01:59:16 +00:00
half.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
hsa-default-device.ll
hsa-fp-mode.ll AMDGPU: Simplify tests with per function subtargets 2016-07-09 07:55:03 +00:00
hsa-func.ll AMDGPU/SI: Add support for R_AMDGPU_GOTPCREL 2016-07-13 14:23:33 +00:00
hsa-globals.ll Revert "[AMDGPU] Emit read-only data to .rodata for hsa" 2016-07-22 23:46:40 +00:00
hsa-group-segment.ll
hsa-note-no-func.ll AMDGPU/SI: Add support for R_AMDGPU_GOTPCREL 2016-07-13 14:23:33 +00:00
hsa.ll AMDGPU/SI: Add support for R_AMDGPU_GOTPCREL 2016-07-13 14:23:33 +00:00
i1-copy-implicit-def.ll
i1-copy-phi.ll AMDGPU: Fix a few slightly broken tests 2016-05-18 15:48:44 +00:00
i8-to-double-to-float.ll
icmp64.ll
icmp-select-sete-reverse-args.ll
image-attributes.ll
image-resource-id.ll
imm.ll AMDGPU: Make i64 loads/stores promote to v2i32 2016-05-02 20:07:26 +00:00
indirect-addressing-si.ll AMDGPU: Fix phis from blocks split due to register indexing 2016-07-21 09:40:57 +00:00
indirect-private-64.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
infinite-loop-evergreen.ll
infinite-loop.ll
inline-asm.ll TII: Fix inlineasm size counting comments as insts 2016-07-01 23:26:50 +00:00
inline-calls.ll
inline-constraints.ll
input-mods.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
insert_subreg.ll
insert_vector_elt.ll AMDGPU: Expand register indexing pseudos in custom inserter 2016-07-19 00:35:03 +00:00
invalid-addrspacecast.ll AMDGPU: Implement addrspacecast 2016-04-25 19:27:24 +00:00
invalid-opencl-version-metadata1.ll AMDGPU: Fix bug causing crash due to invalid opencl version metadata. 2016-07-20 14:38:06 +00:00
invalid-opencl-version-metadata2.ll AMDGPU: Fix bug causing crash due to invalid opencl version metadata. 2016-07-20 14:38:06 +00:00
invalid-opencl-version-metadata3.ll AMDGPU: Fix bug causing crash due to invalid opencl version metadata. 2016-07-20 14:38:06 +00:00
invariant-load-no-alias-store.ll AMDGPU/SI: Enable the post-ra scheduler 2016-04-30 00:23:06 +00:00
jump-address.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
kcache-fold.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
kernarg-stack-alignment.ll AMDGPU: Fix kernel argument alignment impacting stack size 2016-06-18 05:15:53 +00:00
kernel-args.ll AMDGPU: Cleanup load tests 2016-06-02 19:54:26 +00:00
large-alloca-compute.ll AMDGPU: Emit R_AMDGPU_ABS32_{HI,LO} for scratch buffer relocations 2016-06-20 16:59:44 +00:00
large-alloca-graphics.ll AMDGPU/SI: Set INDEX_STRIDE for scratch coalescing 2016-06-13 16:05:57 +00:00
large-constant-initializer.ll
large-work-group-promote-alloca.ll AMDGPU: Add more tests for LDS size with occupancy 2016-07-26 23:15:59 +00:00
large-work-group-registers.ll AMDGPU: Fix a slow test by using basic regalloc 2016-08-04 07:04:54 +00:00
lds-alignment.ll
lds-initializer.ll
lds-m0-init-in-loop.ll AMDGPU: Handle cbranch vccz/vccnz 2016-05-21 00:29:40 +00:00
lds-oqap-crash.ll
lds-output-queue.ll AMDGPU/R600: Replace barrier intrinsics 2016-07-18 18:34:59 +00:00
lds-size.ll AMDGPU: Include LDS size in printed comment 2016-04-14 22:11:51 +00:00
lds-zero-initializer.ll
legalizedag-bug-expand-setcc.ll
lit.local.cfg
literals.ll AMDGPU/R600: Delete/rename intrinsics no longer used by mesa 2016-07-14 05:47:17 +00:00
liveness.mir MIRParser: Use dot instead of colon to mark subregisters 2016-07-26 21:49:34 +00:00
llvm.amdgcn.atomic.dec.ll AMDGPU: Fix flat atomics 2016-06-09 23:42:54 +00:00
llvm.amdgcn.atomic.inc.ll AMDGPU: Fix flat atomics 2016-06-09 23:42:54 +00:00
llvm.amdgcn.buffer.atomic.ll AMDGPU: Fix MUBUF offset bugs affecting llvm.amdgcn.buffer.* intrinsics 2016-06-15 07:13:05 +00:00
llvm.amdgcn.buffer.load.format.ll AMDGPU: Fix MUBUF offset bugs affecting llvm.amdgcn.buffer.* intrinsics 2016-06-15 07:13:05 +00:00
llvm.amdgcn.buffer.load.ll AMDGPU: Fix MUBUF offset bugs affecting llvm.amdgcn.buffer.* intrinsics 2016-06-15 07:13:05 +00:00
llvm.amdgcn.buffer.store.format.ll AMDGPU/SI: Assembler: Unify parsing/printing of operands. 2016-04-29 09:02:30 +00:00
llvm.amdgcn.buffer.store.ll AMDGPU/SI: Assembler: Unify parsing/printing of operands. 2016-04-29 09:02:30 +00:00
llvm.amdgcn.buffer.wbinvl1.ll
llvm.amdgcn.buffer.wbinvl1.sc.ll
llvm.amdgcn.buffer.wbinvl1.vol.ll
llvm.amdgcn.class.ll AMDGPU: Fold more custom nodes to undef 2016-06-20 18:33:56 +00:00
llvm.amdgcn.cos.ll
llvm.amdgcn.cubeid.ll
llvm.amdgcn.cubema.ll
llvm.amdgcn.cubesc.ll
llvm.amdgcn.cubetc.ll
llvm.amdgcn.dispatch.id.ll AMDGPU: Add HSA dispatch id intrinsic 2016-07-22 17:01:30 +00:00
llvm.amdgcn.dispatch.ptr.ll
llvm.amdgcn.div.fixup.ll
llvm.amdgcn.div.fmas.ll AMDGPU: Run SIFoldOperands after PeepholeOptimizer 2016-04-14 21:58:24 +00:00
llvm.amdgcn.div.scale.ll AMDGPU: Add volatile to test loads and stores 2016-04-12 13:38:18 +00:00
llvm.amdgcn.ds.bpermute.ll AMDGPU/SI: Make sure to emit TargetConstant nodes when matching ds_*permute 2016-06-10 00:01:04 +00:00
llvm.amdgcn.ds.permute.ll AMDGPU/SI: Add offset field to ds_permute/ds_bpermute instructions 2016-04-29 14:34:26 +00:00
llvm.amdgcn.ds.swizzle.ll AMDGPU/SI: Define an intrinsic to expose ds_swizzle_b32 2016-06-22 21:33:49 +00:00
llvm.amdgcn.fcmp.ll AMDGPU : Add intrinsics for compare with the full wavefront result 2016-07-28 16:42:13 +00:00
llvm.amdgcn.fdiv.fast.ll AMDGPU: Change fdiv lowering based on !fpmath metadata 2016-07-19 23:16:53 +00:00
llvm.amdgcn.fmul.legacy.ll AMDGPU: Add fp legacy instruction intrinsics 2016-07-26 16:45:45 +00:00
llvm.amdgcn.fract.ll AMDGPU: Fold more custom nodes to undef 2016-06-20 18:33:56 +00:00
llvm.amdgcn.frexp.exp.ll
llvm.amdgcn.frexp.mant.ll
llvm.amdgcn.groupstaticsize.ll AMDGPU: Fix groupstaticsize for large LDS 2016-07-22 17:01:33 +00:00
llvm.amdgcn.icmp.ll AMDGPU : Add intrinsics for compare with the full wavefront result 2016-07-28 16:42:13 +00:00
llvm.amdgcn.image.atomic.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.amdgcn.image.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.amdgcn.interp.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.amdgcn.kernarg.segment.ptr.ll AMDGPU: Add implicitarg.ptr intrinsic. 2016-06-21 20:46:20 +00:00
llvm.amdgcn.ldexp.ll AMDGPU: Remove AMDGPU.ldexp 2016-07-15 21:26:56 +00:00
llvm.amdgcn.lerp.ll AMDGPU: Add LLVM IR Intrinsic for v_lerp_u8 2016-07-12 18:02:14 +00:00
llvm.amdgcn.log.clamp.ll
llvm.amdgcn.mbcnt.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.amdgcn.mov.dpp.ll AMDGPU/SI: Use hazard recognizer to detect DPP hazards 2016-05-02 16:23:09 +00:00
llvm.amdgcn.ps.live.ll AMDGPU/SI: add llvm.amdgcn.ps.live intrinsic 2016-04-22 04:04:08 +00:00
llvm.amdgcn.queue.ptr.ll AMDGPU: Add queue ptr intrinsic 2016-04-25 19:27:18 +00:00
llvm.amdgcn.rcp.legacy.ll AMDGPU: Add fp legacy instruction intrinsics 2016-07-26 16:45:45 +00:00
llvm.amdgcn.rcp.ll AMDGPU: Simplify tests with per function subtargets 2016-07-09 07:55:03 +00:00
llvm.amdgcn.rsq.clamp.ll MachineScheduler: Fully compare top/bottom candidates 2016-06-25 00:23:00 +00:00
llvm.amdgcn.rsq.legacy.ll AMDGPU: Fold more custom nodes to undef 2016-06-20 18:33:56 +00:00
llvm.amdgcn.rsq.ll AMDGPU: Fold more custom nodes to undef 2016-06-20 18:33:56 +00:00
llvm.amdgcn.s.barrier.ll
llvm.amdgcn.s.dcache.inv.ll AMDGPU: Implement AnalyzeBranch 2016-05-21 00:29:27 +00:00
llvm.amdgcn.s.dcache.inv.vol.ll AMDGPU: Implement AnalyzeBranch 2016-05-21 00:29:27 +00:00
llvm.amdgcn.s.dcache.wb.ll AMDGPU: Implement AnalyzeBranch 2016-05-21 00:29:27 +00:00
llvm.amdgcn.s.dcache.wb.vol.ll AMDGPU: Implement AnalyzeBranch 2016-05-21 00:29:27 +00:00
llvm.amdgcn.s.getreg.ll [AMDGPU][llvm-mc] s_getreg/setreg* - Support symbolic names of hardware registers. 2016-04-27 15:17:03 +00:00
llvm.amdgcn.s.memrealtime.ll
llvm.amdgcn.s.memtime.ll
llvm.amdgcn.s.sleep.ll
llvm.amdgcn.s.waitcnt.ll AMDGPU/SI: Add llvm.amdgcn.s.waitcnt.all intrinsic 2016-04-27 15:46:01 +00:00
llvm.amdgcn.sffbh.ll AMDGPU: Add intrinsic for s_flbit_i32/v_ffbh_i32 2016-07-18 18:35:05 +00:00
llvm.amdgcn.sin.ll
llvm.amdgcn.trig.preop.ll
llvm.amdgcn.workgroup.id.ll
llvm.amdgcn.workitem.id.ll
llvm.AMDGPU.bfe.i32.ll
llvm.AMDGPU.bfe.u32.ll
llvm.AMDGPU.clamp.ll AMDGPU: Remove last AMDIL intrinsics 2016-07-13 19:42:06 +00:00
llvm.AMDGPU.cube.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
llvm.AMDGPU.kill.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.amdgpu.kilp.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.cos.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
llvm.dbg.value.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
llvm.exp2.ll
llvm.log2.ll
llvm.memcpy.ll AMDGPU: Fix shouldConvertConstantLoadToIntImm behavior 2016-07-30 01:40:36 +00:00
llvm.pow.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
llvm.r600.dot4.ll AMDGPU/R600: Delete/rename intrinsics no longer used by mesa 2016-07-14 05:47:17 +00:00
llvm.r600.group.barrier.ll AMDGPU/R600: Replace barrier intrinsics 2016-07-18 18:34:59 +00:00
llvm.r600.read.local.size.ll
llvm.r600.recipsqrt.clamped.ll AMDGPU: Remove legacy rsq.clamped intrinsic 2016-07-15 21:26:52 +00:00
llvm.r600.recipsqrt.ieee.ll AMDGPU: Remove legacy rsq.clamped intrinsic 2016-07-15 21:26:52 +00:00
llvm.r600.tex.ll AMDGPU/R600: Delete/rename intrinsics no longer used by mesa 2016-07-14 05:47:17 +00:00
llvm.rint.f64.ll
llvm.rint.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
llvm.round.f64.ll AMDGPU/SI: Enable the post-ra scheduler 2016-04-30 00:23:06 +00:00
llvm.round.ll AMDGPU/SI: Enable the post-ra scheduler 2016-04-30 00:23:06 +00:00
llvm.SI.fs.interp.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.SI.gather4.ll AMDGPU: Unify MOVRELSOffset and MOVRELDOffset 2016-07-12 08:12:16 +00:00
llvm.SI.getlod.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.SI.image.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.SI.image.sample-masked.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.SI.image.sample.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.SI.image.sample.o.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.SI.load.dword.ll AMDGPU/SI: Assembler: Unify parsing/printing of operands. 2016-04-29 09:02:30 +00:00
llvm.SI.packf16.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.SI.sendmsg-m0.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
llvm.SI.sendmsg.ll [AMDGPU][llvm-mc] Add support for sendmsg(...) syntax. 2016-05-06 17:48:48 +00:00
llvm.SI.tbuffer.store.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
llvm.sin.ll AMDGPU: Simplify tests with per function subtargets 2016-07-09 07:55:03 +00:00
load-constant-f64.ll AMDGPU: Cleanup load tests 2016-06-02 19:54:26 +00:00
load-constant-i1.ll AMDGPU: Cleanup load tests 2016-06-02 19:54:26 +00:00
load-constant-i8.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
load-constant-i16.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
load-constant-i32.ll AMDGPU/SI: Increase SGPR limit to 96 on Tonga/Iceland 2016-08-05 21:23:29 +00:00
load-constant-i64.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
load-global-f32.ll AMDGPU: Cleanup load tests 2016-06-02 19:54:26 +00:00
load-global-f64.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
load-global-i1.ll AMDGPU: Cleanup load tests 2016-06-02 19:54:26 +00:00
load-global-i8.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
load-global-i16.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
load-global-i32.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
load-global-i64.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
load-input-fold.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
load-local-f32.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
load-local-f64.ll AMDGPU: Cleanup load tests 2016-06-02 19:54:26 +00:00
load-local-i1.ll AMDGPU: Cleanup load tests 2016-06-02 19:54:26 +00:00
load-local-i8.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
load-local-i16.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
load-local-i32.ll AMDGPU: Define a schedule class for COPY. 2016-06-24 23:52:11 +00:00
load-local-i64.ll AMDGPU: Cleanup load tests 2016-06-02 19:54:26 +00:00
load-weird-sizes.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
local-64.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
local-atomics64.ll
local-atomics.ll AMDGPU: Add atomic_inc + atomic_dec intrinsics 2016-04-12 14:05:04 +00:00
local-memory.amdgcn.ll AMDGPU/R600: Replace barrier intrinsics 2016-07-18 18:34:59 +00:00
local-memory.ll AMDGPU/R600: Replace barrier intrinsics 2016-07-18 18:34:59 +00:00
local-memory.r600.ll AMDGPU/R600: Replace barrier intrinsics 2016-07-18 18:34:59 +00:00
local-stack-slot-bug.ll AMDGPU: fix local stack slot allocation bugs 2016-07-11 21:44:40 +00:00
loop_break.ll AMDGPU: Add missing test coverage for control flow breaks 2016-07-20 15:20:35 +00:00
loop-address.ll
loop-idiom.ll
lower-range-metadata-intrinsic-call.ll
lshl.ll
lshr.ll
m0-spill.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
mad24-get-global-id.ll AMDGPU: Un-xfail and add tests 2016-06-24 06:58:01 +00:00
mad_int24.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
mad_uint24.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
mad-combine.ll AMDGPU/SI: Enable the post-ra scheduler 2016-04-30 00:23:06 +00:00
mad-sub.ll AMDGPU: Add volatile to test loads and stores 2016-04-12 13:38:18 +00:00
madak.ll AMDGPU: Fix folding SGPRs into madak/madmk src0 2016-07-05 17:09:01 +00:00
madmk.ll AMDGPU: Run SIFoldOperands after PeepholeOptimizer 2016-04-14 21:58:24 +00:00
max3.ll
max-literals.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
max.ll SelectionDAG: Implement expansion of {S,U}MIN/MAX in integer legalization 2016-06-09 16:04:00 +00:00
merge-stores.ll AMDGPU/SI: Assembler: Unify parsing/printing of operands. 2016-04-29 09:02:30 +00:00
min3.ll
min.ll AMDGPU: Run pointer optimization passes 2016-06-15 00:11:01 +00:00
missing-store.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
move-addr64-rsrc-dead-subreg-writes.ll MachineScheduler: Fully compare top/bottom candidates 2016-06-25 00:23:00 +00:00
move-to-valu-atomicrmw.ll
mubuf.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
mul_int24.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
mul_uint24.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
mul.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
mulhu.ll
multilevel-break.ll AMDGPU/SI: Fix a mis-compilation of multi-level breaks 2016-04-12 16:10:38 +00:00
no-hsa-graphics-shaders.ll [AMDGPU] Remove exit-on-error flag from test (PR27762) 2016-05-26 15:24:55 +00:00
no-initializer-constant-addrspace.ll AMDGPU/R600: Fix GlobalValue regressions. 2016-06-25 18:24:16 +00:00
no-shrink-extloads.ll AMDGPU: Un-xfail and add tests 2016-06-24 06:58:01 +00:00
opencl-image-metadata.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
operand-folding.ll
operand-spacing.ll
or.ll AMDGPU: Fix a few slightly broken tests 2016-05-18 15:48:44 +00:00
over-max-lds-size.ll Generalize DiagnosticInfoStackSize to support other limits 2016-06-20 18:13:04 +00:00
packetizer.ll
parallelandifcollapse.ll AMDGPU: Move subtarget feature checks into passes 2016-06-27 20:32:13 +00:00
parallelorifcollapse.ll
partially-dead-super-register-immediate.ll
predicate-dp4.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
predicates.ll AMDGPU: Remove disable-irstructurizer subtarget feature 2016-06-24 06:30:22 +00:00
private-element-size.ll AMDGPU: Add some private element size tests 2016-05-16 22:17:27 +00:00
private-memory-atomics.ll
private-memory-broken.ll [AMDGPU] Remove exit-on-error in test (PR27761) 2016-06-23 09:19:16 +00:00
private-memory-r600.ll AMDGPU: Fix promote alloca pass creating huge arrays 2016-05-16 21:19:59 +00:00
promote-alloca-array-allocation.ll AMDGPU: Fix mishandling array allocations when promoting alloca 2016-04-28 18:38:48 +00:00
promote-alloca-bitcast-function.ll [AMDGPU] Remove exit-on-error in test (PR27761) 2016-06-23 09:19:16 +00:00
promote-alloca-globals.ll AMDGPU: Fix promote alloca pass creating huge arrays 2016-05-16 21:19:59 +00:00
promote-alloca-invariant-markers.ll Invariant start/end intrinsics overloaded for address space 2016-07-22 17:49:40 +00:00
promote-alloca-lifetime.ll AMDGPU: Fix test not actually testing anything 2016-07-14 05:23:15 +00:00
promote-alloca-mem-intrinsics.ll AMDGPU: Fix promote alloca pass creating huge arrays 2016-05-16 21:19:59 +00:00
promote-alloca-no-opts.ll AMDGPU: Fix promote alloca pass creating huge arrays 2016-05-16 21:19:59 +00:00
promote-alloca-padding-size-estimate.ll AMDGPU: Fix promote alloca pass creating huge arrays 2016-05-16 21:19:59 +00:00
promote-alloca-shaders.ll AMDGPU: Disable AMDGPUPromoteAlloca pass for shader calling conventions. 2016-07-18 09:02:47 +00:00
promote-alloca-stored-pointer-value.ll
promote-alloca-to-lds-icmp.ll AMDGPU: Handle alloca promoting with null operands 2016-05-18 15:57:21 +00:00
promote-alloca-to-lds-phi.ll AMDGPU: Handle alloca promoting with null operands 2016-05-18 15:57:21 +00:00
promote-alloca-to-lds-select.ll AMDGPU: Handle alloca promoting with null operands 2016-05-18 15:57:21 +00:00
promote-alloca-unhandled-intrinsic.ll AMDGPU: Fix test not actually testing anything 2016-07-14 05:23:15 +00:00
promote-alloca-volatile.ll AMDGPU: Fix promote alloca for pointer loads 2016-05-18 23:20:24 +00:00
pv-packing.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
pv.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
r600-encoding.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
r600-export-fix.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
r600-infinite-loop-bug-while-reorganizing-vector.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
r600.private-memory.ll AMDGPU: Split private memory tests 2016-05-11 17:24:45 +00:00
r600.work-item-intrinsics.ll AMDGPU: Remove read_workdim intrinsic 2016-07-25 20:17:02 +00:00
r600cfg.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
rcp-pattern.ll AMDGPU: fdiv -1, x -> rcp -x 2016-08-02 22:25:04 +00:00
read_register.ll
read-register-invalid-subtarget.ll
read-register-invalid-type-i32.ll
read-register-invalid-type-i64.ll
readcyclecounter.ll
README
reduce-load-width-alignment.ll AMDGPU/SI: Assembler: Unify parsing/printing of operands. 2016-04-29 09:02:30 +00:00
reduce-store-width-alignment.ll DAGCombiner: Relax alignment restriction when changing store type 2016-04-22 21:01:41 +00:00
reg-coalescer-sched-crash.ll
register-count-comments.ll AMDGPU: Remove llvm.SI.tid intrinsic 2016-06-17 21:18:41 +00:00
rename-disconnected-bug.ll LiveIntervalAnalysis: Fix missing defs in renameDisconnectedComponents(). 2016-05-20 19:46:13 +00:00
rename-independent-subregs.mir RenameIndependentSubregs: Fix liveness query in rewriteOperands() 2016-08-03 22:37:47 +00:00
reorder-stores.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
ret_jump.ll AMDGPU: Fix return of non-void-returning shaders 2016-07-06 08:35:17 +00:00
ret.ll AMDGPU/SI: Add latency for export instructions 2016-04-07 18:30:05 +00:00
rotl.i64.ll
rotl.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
rotr.i64.ll
rotr.ll
rsq.ll AMDGPU: fdiv -1, x -> rcp -x 2016-08-02 22:25:04 +00:00
runtime-metadata.ll [OpenCL] Add missing tests for getOCLTypeName 2016-08-04 19:45:00 +00:00
rv7x0_count3.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
s_addk_i32.ll AMDGPU: Use s_addk_i32 / s_mulk_i32 2016-04-16 01:46:49 +00:00
s_movk_i32.ll
s_mulk_i32.ll AMDGPU: Use s_addk_i32 / s_mulk_i32 2016-04-16 01:46:49 +00:00
saddo.ll
salu-to-valu.ll AMDGPU: Define priorities for register classes 2016-05-21 03:55:07 +00:00
sampler-resource-id.ll
scalar_to_vector.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
schedule-fs-loop-nested-if.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
schedule-fs-loop-nested.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
schedule-fs-loop.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
schedule-global-loads.ll AMDGPU: Make vectorization defeating test changes 2016-05-25 17:42:39 +00:00
schedule-if-2.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
schedule-if.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
schedule-kernel-arg-loads.ll AMDGPU: Define a schedule class for COPY. 2016-06-24 23:52:11 +00:00
schedule-vs-if-nested-loop-failure.ll AMDGPU/R600: Replace barrier intrinsics 2016-07-18 18:34:59 +00:00
schedule-vs-if-nested-loop.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
scratch-buffer.ll
sdiv.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
sdivrem24.ll AMDGPU: Fix high bits after division optimization 2016-05-21 01:53:33 +00:00
sdivrem64.ll AMDGPU: Fold bitcasts of scalar constants to vectors 2016-04-14 21:58:07 +00:00
select64.ll
select-i1.ll SelectionDAG: Select min/max when both are used 2016-05-16 20:58:23 +00:00
select-vectors.ll AMDGPU: Fix inconsistent lowering of select of vectors 2016-05-25 17:34:58 +00:00
select.ll
selectcc-cnd.ll
selectcc-cnde-int.ll
selectcc-icmp-select-float.ll
selectcc-opt.ll
selectcc.ll
selected-stack-object.ll llvm/test/CodeGen/AMDGPU/selected-stack-object.ll REQUIRES +Asserts, since it expects assertion failure. 2016-07-12 02:18:09 +00:00
set-dx10.ll
setcc64.ll
setcc-equivalent.ll
setcc-opt.ll AMDGPU: Run pointer optimization passes 2016-06-15 00:11:01 +00:00
setcc.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
seto.ll
setuo.ll
sext-eliminate.ll
sext-in-reg-failure-r600.ll AMDGPU: Expand unaligned accesses early 2016-07-01 22:55:55 +00:00
sext-in-reg.ll AMDGPU: Expand unaligned accesses early 2016-07-01 22:55:55 +00:00
sgpr-control-flow.ll AMDGPU: Implement AnalyzeBranch 2016-05-21 00:29:27 +00:00
sgpr-copy-duplicate-operand.ll
sgpr-copy.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
shared-op-cycle.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
shift-and-i64-ubfe.ll AMDGPU/SI: Enable the post-ra scheduler 2016-04-30 00:23:06 +00:00
shift-and-i128-ubfe.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
shift-i64-opts.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
shl_add_constant.ll AMDGPU: Define a schedule class for COPY. 2016-06-24 23:52:11 +00:00
shl_add_ptr.ll
shl.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
si-annotate-cf-noloop.ll AMDGPU/SI: Don't handle a loop if there is no loop at all for a terminator BB. 2016-07-28 23:01:45 +00:00
si-annotate-cf.ll AMDGPU: Un-xfail and add tests 2016-06-24 06:58:01 +00:00
si-annotate-cfg-loop-assert.ll AMDGPU: Un-xfail and add tests 2016-06-24 06:58:01 +00:00
si-instr-info-correct-implicit-operands.ll [MIR] Print on the given output instead of stderr. 2016-07-13 20:36:03 +00:00
si-literal-folding.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
si-lod-bias.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
si-lower-control-flow-unreachable-block.ll AMDGPU: Fix crash with unreachable terminators. 2016-04-29 21:52:13 +00:00
si-scheduler.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
si-sgpr-spill.ll AMDGPU: Remove llvm.SI.tid intrinsic 2016-06-17 21:18:41 +00:00
si-spill-cf.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
si-spill-sgpr-stack.ll AMDGPU/SI: Use v_readfirstlane_b32 when restoring SGPRs spilled to scratch 2016-05-02 20:11:44 +00:00
si-triv-disjoint-mem-access.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
si-vector-hang.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
sign_extend.ll AMDGPU: sext_inreg (srl x, K), vt -> bfe x, K, vt.Size 2016-04-22 22:59:16 +00:00
simplify-demanded-bits-build-pair.ll
sint_to_fp.f64.ll AMDGPU: Run SIFoldOperands after PeepholeOptimizer 2016-04-14 21:58:24 +00:00
sint_to_fp.i64.ll [AMDGPU][llvm-mc] v_cndmask_b32: src2 is mandatory; do not enforce VOP2 when src2 == VCC. 2016-06-06 15:23:43 +00:00
sint_to_fp.ll
skip-if-dead.ll AMDGPU: Stay in WQM for non-intrinsic stores 2016-08-02 19:31:14 +00:00
smed3.ll
sminmax.ll SelectionDAG: Implement expansion of {S,U}MIN/MAX in integer legalization 2016-06-09 16:04:00 +00:00
smrd-vccz-bug.ll
smrd.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
spill-alloc-sgpr-init-bug.ll AMDGPU: Remove llvm.SI.tid intrinsic 2016-06-17 21:18:41 +00:00
spill-scavenge-offset.ll AMDGPU: Disable scheduling in some slow tests 2016-06-16 00:56:47 +00:00
split-scalar-i64-add.ll
split-smrd.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
split-vector-memoperand-offsets.ll
sra.ll MachineScheduler: Fully compare top/bottom candidates 2016-06-25 00:23:00 +00:00
srem.ll
srl.ll
ssubo.ll
store_typed.ll
store-barrier.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
store-v3i32.ll
store-v3i64.ll AMDGPU: Cleanup lowering actions 2016-05-21 02:27:49 +00:00
store-vector-ptrs.ll
store.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
store.r600.ll
structurize1.ll AMDGPU: Move subtarget feature checks into passes 2016-06-27 20:32:13 +00:00
structurize.ll AMDGPU: Remove disable-irstructurizer subtarget feature 2016-06-24 06:30:22 +00:00
sub.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
subreg-coalescer-crash.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
subreg-coalescer-undef-use.ll DetectDeadLanes: Increase precision when detecting undef inputs 2016-05-06 22:43:50 +00:00
subreg-eliminate-dead.ll
swizzle-export.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
target-cpu.ll AMDGPU: Implement per-function subtargets 2016-06-27 20:48:03 +00:00
tex-clause-antidep.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
texture-input-merge.ll AMDGPU: Fix TargetPrefix for remaining r600 intrinsics 2016-07-15 21:27:08 +00:00
trap.ll AMDGPU: Temporarily select trap to s_endpgm 2016-06-17 22:27:03 +00:00
trunc-bitcast-vector.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
trunc-cmp-constant.ll
trunc-store-f64-to-f16.ll
trunc-store-i1.ll
trunc-store.ll AMDGPU: Improve load/store of illegal types. 2016-07-01 22:47:50 +00:00
trunc-vector-store-assertion-failure.ll
trunc.ll AMDGPU/SI: Enable the post-ra scheduler 2016-04-30 00:23:06 +00:00
tti-unroll-prefs.ll
uaddo.ll
udiv.ll AMDGPU: Fix high bits after division optimization 2016-05-21 01:53:33 +00:00
udivrem24.ll AMDGPU: Fix high bits after division optimization 2016-05-21 01:53:33 +00:00
udivrem64.ll AMDGPU: Fix high bits after division optimization 2016-05-21 01:53:33 +00:00
udivrem.ll AMDGPU: Fix high bits after division optimization 2016-05-21 01:53:33 +00:00
uint_to_fp.f64.ll AMDGPU: Run SIFoldOperands after PeepholeOptimizer 2016-04-14 21:58:24 +00:00
uint_to_fp.i64.ll
uint_to_fp.ll
umed3.ll
unaligned-load-store.ll AMDGPU: Add feature for unaligned access 2016-07-01 23:03:44 +00:00
undefined-subreg-liverange.ll AMDGPU: Fix verifier error from partially undef copy 2016-07-15 22:32:02 +00:00
unhandled-loop-condition-assertion.ll AMDGPU: Un-xfail and add tests 2016-06-24 06:58:01 +00:00
uniform-branch-intrinsic-cond.ll AMDGPU: Uniform branch conditions can originate with intrinsics 2016-05-05 17:36:36 +00:00
uniform-cfg.ll AMDGPU: Run pointer optimization passes 2016-06-15 00:11:01 +00:00
uniform-crash.ll AMDGPU: Fix a few slightly broken tests 2016-05-18 15:48:44 +00:00
uniform-loop-inside-nonuniform.ll AMDGPU: Handle cbranch vccz/vccnz 2016-05-21 00:29:40 +00:00
unknown-processor.ll AMDGPU: Fix crashes on unknown processor name 2016-06-02 18:37:16 +00:00
unroll.ll
unsupported-cc.ll
urecip.ll
urem.ll
use-sgpr-multiple-times.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
usubo.ll
v1i64-kernel-arg.ll
v_cndmask.ll
v_mac.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
valu-i1.ll AMDGPU: Handle cbranch vccz/vccnz 2016-05-21 00:29:40 +00:00
vector-alloca.ll AMDGPU: Remove dead check in AMDGPUPromoteAlloca 2016-07-18 18:34:53 +00:00
vector-extract-insert.ll Reapply r274829 with fix for FP vectors 2016-07-08 21:25:33 +00:00
vertex-fetch-encoding.ll
vgpr-spill-emergency-stack-slot-compute.ll AMDGPU/SI: Set INDEX_STRIDE for scratch coalescing 2016-06-13 16:05:57 +00:00
vgpr-spill-emergency-stack-slot.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
vi-removed-intrinsics.ll AMDGPU: Fold more custom nodes to undef 2016-06-20 18:33:56 +00:00
vop-shrink.ll
vselect64.ll
vselect.ll AMDGPU: Fix a few slightly broken tests 2016-05-18 15:48:44 +00:00
vtx-fetch-branch.ll
vtx-schedule.ll
wait.ll AMDGPU: Add a shader calling convention 2016-04-06 19:40:20 +00:00
waitcnt-flat.ll AMDGPU: Define priorities for register classes 2016-05-21 03:55:07 +00:00
wqm.ll AMDGPU: Stay in WQM for non-intrinsic stores 2016-08-02 19:31:14 +00:00
write_register.ll
write-register-vgpr-into-sgpr.ll
wrong-transalu-pos-fix.ll AMDGPU: Remove superfluous string attributes from tests 2016-07-11 23:35:48 +00:00
xor.ll AMDGPU/SI: Enable load-store-opt by default. 2016-05-26 19:35:29 +00:00
zero_extend.ll AMDGPU: Run r600 tests last 2016-05-05 20:07:37 +00:00
zext-i64-bit-operand.ll AMDGPU: Eliminate half of i64 or if one operand is zero_extend from i32 2016-04-12 18:24:38 +00:00

+==============================================================================+
| 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.