shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/llvm/test/CodeGen/NVPTX
History
Quentin Colombet bb206cb131 [NVPTX] Apply global var demotion to private symbols 
When emitting the assembly we perform some late global variables demotion.
Prior to this patch, this optimization was only performed on variables with
the internal linkage whereas any local global variable can be demoted.

Fix that by using `hasLocalLinkage` instead of `hasInternalLinkage`.

Without this change, global variables with the `private` linkage wouldn't
be demoted.

Differential Revision: https://reviews.llvm.org/D154507
2023-08-09 14:41:01 +02:00
..
access-non-generic.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
add-sub-128bit.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
addrspacecast-gvar.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
addrspacecast.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
aggr-param.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
aggregate-return.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
alias-errors.ll
[NVPTX] Add initial support for '.alias' in PTX
2023-07-21 16:43:46 -05:00
alias.ll
[NVPTX] Fix lack of .noreturn on certain functions for aliases
2023-07-24 07:01:05 -05:00
annotations.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
anonymous-fn-param.ll
[NVPTX] Sync generation of parameter names in a function signature with the function body.
2023-03-11 03:40:48 +01:00
APIntLoadStore.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
APIntParam.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
APIntSextParam.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
APIntZextParam.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
arg-lowering.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
arithmetic-fp-sm20.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
arithmetic-int.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
async-copy.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
atomic-lower-local.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
atomicrmw-expand.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
atomics-sm60.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
atomics-with-scope.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
atomics.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
b52037.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
barrier.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
bf16-instructions.ll
[NVPTX] Expand select_cc on bfloat16 type
2023-07-24 17:01:31 +02:00
bf16.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
bfe.ll
Fix shr/and pair replace with bfe
2023-07-11 14:43:35 +01:00
branch-fold.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
branch-fold.mir
…
bug17709.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
bug21465.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
bug22246.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
bug22322.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
bug26185-2.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
bug26185.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
bug41651.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
bug52623.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
bypass-div.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
call_bitcast_byval.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
call-with-alloca-buffer.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
callchain.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
calling-conv.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
calls-with-phi.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
chain-different-as.ll
DAG: Prevent store value forwarding to distinct addrspace load
2022-12-29 18:19:55 -05:00
combine-min-max.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
compare-int.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
constant-vectors.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
convergent-mir-call.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
convert-fp.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
convert-int-sm20.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
convert-sm80.ll
adding bf16 support to NVPTX
2023-06-28 11:57:13 -07:00
ctlz.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
ctpop.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
cttz.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
dag-cse.ll
[SelectionDAG] Add memory size for CSEMap ID calculation
2023-06-26 16:12:48 -07:00
demote-vars.ll
[NVPTX] Apply global var demotion to private symbols
2023-08-09 14:41:01 +02:00
disable-opt.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
div-ri.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
divrem-combine.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
empty-type.ll
[NVPTX] Report fatal error on empty argument type.
2023-03-18 01:27:43 +01:00
envreg.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
extloadv.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
f16-ex2.ll
…
f16-instructions.ll
adding bf16 support to NVPTX
2023-06-28 11:57:13 -07:00
f16x2-instructions.ll
[NVPTX] Lower v2f16 and v2bf16 stores as 32-bit scalars.
2023-06-23 10:58:44 -07:00
fast-math.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
fcos-no-fast-math.ll
…
filetype-null.ll
…
fma-assoc.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
fma-disable.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
fma.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
fminimum-fmaximum.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
fns.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
fp16.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
fp-contract.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
fp-literals.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
fsin-no-fast-math.ll
…
function-align.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
generic-to-nvvm-ir.ll
[NVPTX] Port GenericToNVVM to the new PM.
2023-03-23 00:56:14 +01:00
generic-to-nvvm.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
global-addrspace.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
global-ctor-empty.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
global-ctor.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
global-dtor.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
global-ordering.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
global-variable-big.ll
[NVPTX] Fix integer overflow affecting array size calculation.
2023-03-24 10:35:25 -07:00
global-visibility.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
globals_init.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
globals_lowering.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
gvar-init.ll
…
half.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
i1-global.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
i1-int-to-fp.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
i1-param.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
i8-param.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
i128-global.ll
…
i128-param.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
i128-retval.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
i128-struct.ll
…
idioms.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
imad.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
inline-asm.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
inlineasm-output-template.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
intrin-nocapture.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
intrinsic-old.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
intrinsics-sm90.ll
Coalesce 16-bit FP types to use integer register classes.
2023-06-05 12:21:52 -07:00
intrinsics.ll
Revert "[NVPTX] Allow using v4i32 for memcpy lowering."
2023-06-14 10:03:30 -07:00
isspacep.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
ld-addrspace.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
ld-generic.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
ld-st-addrrspace.py
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
ldg-invariant.ll
Coalesce 16-bit FP types to use integer register classes.
2023-06-05 12:21:52 -07:00
ldparam-v4.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
ldu-i8.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
ldu-ldg.ll
Coalesce 16-bit FP types to use integer register classes.
2023-06-05 12:21:52 -07:00
ldu-reg-plus-offset.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
libcall-fulfilled.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
libcall-instruction.ll
…
libcall-intrinsic.ll
…
lit.local.cfg
[NFC][Py Reformat] Reformat lit.local.cfg python files in llvm
2023-05-17 17:03:15 +02:00
load-sext-i1.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
load-store.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
load-with-non-coherent-cache.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
LoadStoreVectorizer.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
local-stack-frame.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
loop-vectorize.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
lower-aggr-copies.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
lower-alloca.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
lower-args.ll
[NVPTX] Infer AS of pointers passed to kernels as integers.
2023-01-27 13:27:56 -08:00
lower-byval-args.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
lower-ctor-dtor.ll
[NVPTX] Add NVPTXCtorDtorLoweringPass to handle global ctors / dtors
2023-05-04 07:13:00 -05:00
lower-kernel-ptr-arg.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
machine-sink.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
MachineSink-call.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
MachineSink-convergent.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
managed.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
match.ll
…
math-intrins-sm53-ptx42.ll
…
math-intrins-sm80-ptx70-autoupgrade.ll
adding bf16 support to NVPTX
2023-06-28 11:57:13 -07:00
math-intrins-sm80-ptx70-instcombine.ll
[NFC] Port codegen NVPTX tests that invoke opt to -passes= syntax
2022-12-09 01:04:47 +03:00
math-intrins-sm80-ptx70.ll
adding bf16 support to NVPTX
2023-06-28 11:57:13 -07:00
math-intrins-sm86-ptx72-autoupgrade.ll
adding bf16 support to NVPTX
2023-06-28 11:57:13 -07:00
math-intrins-sm86-ptx72.ll
adding bf16 support to NVPTX
2023-06-28 11:57:13 -07:00
math-intrins.ll
…
mbarrier.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
minmax-negative.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
misaligned-vector-ldst.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
module-inline-asm.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
mulwide.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
named-barriers.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
no-extra-parens.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
noduplicate-syncthreads.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
nofunc.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
noreturn.ll
[NVPTX] Emit .noreturn directive
2022-12-28 21:45:51 +03:00
nounroll.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
nvcl-param-align.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
nvptx-aa.ll
[NVPTX] Implement NVPTX AliasAnalysis
2023-02-01 16:16:43 +03:00
nvvm-annotations-D120129.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
nvvm-reflect-arch.ll
[NVPTX] Set default version of architecture to SM_30, PTX to 6.0.
2023-01-10 15:22:40 +03:00
nvvm-reflect-module-flag.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
nvvm-reflect-ocl.ll
[NVPTX] Set default version of architecture to SM_30, PTX to 6.0.
2023-01-10 15:22:40 +03:00
nvvm-reflect-opaque.ll
…
nvvm-reflect.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
packed-aggr.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
param-align.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
param-load-store.ll
adding bf16 support to NVPTX
2023-06-28 11:57:13 -07:00
param-vectorize-device.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
param-vectorize-kernel.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
pass-name.ll
…
pow2_mask_cmp.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
pr13291-i1-store.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
pr16278.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
pr17529.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
proxy-reg-erasure-mir.ll
…
proxy-reg-erasure-ptx.ll
Coalesce 16-bit FP types to use integer register classes.
2023-06-05 12:21:52 -07:00
read-global-variable-constant.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
redux-sync.ll
…
refl1.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
reg-copy.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
reg-types.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
rotate_64.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
rotate.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
sched1.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
sched2.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
sext-in-reg.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
sext-params.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
shfl-p.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
shfl-sync-p.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
shfl-sync.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
shfl.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
shift-parts.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
short-ptr.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
simple-call.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
sm-version.ll
[NVPTX] Set default version of architecture to SM_30, PTX to 6.0.
2023-01-10 15:22:40 +03:00
speculative-execution-divergent-target.ll
[NFC] Port codegen NVPTX tests that invoke opt to -passes= syntax
2022-12-09 01:04:47 +03:00
sqrt-approx.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
st-addrspace.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
st-generic.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
store-retval.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
surf-read-cuda.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
surf-read.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
surf-tex.py
[NFC][Py Reformat] Reformat python files in llvm
2023-05-17 10:48:52 +02:00
surf-write-cuda.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
surf-write.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
symbol-naming.ll
[OpenMP][NVPTX] Handle additional invalid PTX characters
2023-06-30 14:58:37 -05:00
TailDuplication-convergent.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
tex-read-cuda.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
tex-read.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
texsurf-queries.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
tid-range.ll
…
unreachable.ll
NVPTX: Lower unreachable to exit to allow ptxas to accurately reconstruct the CFG.
2023-06-21 11:40:31 -07:00
vaargs.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
vec8.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
vec-param-load.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
vector-args.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
vector-call.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
vector-compare.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
vector-global.ll
…
vector-loads.ll
[NVPTX] Correctly lower extending loads for fp16 vectors.
2023-06-23 10:45:49 -07:00
vector-select.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
vector-stores.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
vectorize-misaligned.ll
[NVPTX] Convert some tests to opaque pointers (NFC)
2022-12-19 12:57:23 +01:00
vote.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00
weak-global.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
weak-linkage.ll
[NVPTX] Adapt tests to make them usable with CUDA-12.x
2023-06-06 14:22:12 -07:00
wmma.py
Coalesce 16-bit FP types to use integer register classes.
2023-06-05 12:21:52 -07:00
zeroext-32bit.ll
[NVPTX] Use by default 'sm_60' architecture when expanding %ptxas-verify macro.
2023-02-17 20:49:04 +01:00