Google Git
Sign in
llvm / llvm-project / llvm / 4065f8ffaff7fd23a176d4c968bba1ebac135a19 / . / test / CodeGen / NVPTX
tree: 3af1955b632d9ca21b7af4d6ad572a9b213713b0 [path history] [tgz]
  1. access-non-generic.ll
  2. activemask.ll
  3. add-sub-128bit.ll
  4. addr-mode.ll
  5. addrspacecast-cse.ll
  6. addrspacecast-folding.ll
  7. addrspacecast-gvar.ll
  8. addrspacecast-ptx64.ll
  9. addrspacecast.ll
  10. aggr-param.ll
  11. aggregate-return.ll
  12. alias-errors.ll
  13. alias.ll
  14. and-or-setcc.ll
  15. annotations.ll
  16. anonymous-fn-param.ll
  17. APIntLoadStore.ll
  18. APIntParam.ll
  19. APIntSextParam.ll
  20. APIntZextParam.ll
  21. applypriority.ll
  22. arg-lowering.ll
  23. arithmetic-fp-sm20.ll
  24. arithmetic-int.ll
  25. async-copy.ll
  26. atomic-lower-local.ll
  27. atomicrmw-expand.ll
  28. atomics-sm60.ll
  29. atomics-sm70.ll
  30. atomics-sm90.ll
  31. atomics-with-scope.ll
  32. atomics.ll
  33. b52037.ll
  34. barrier.ll
  35. bf16-instructions.ll
  36. bf16.ll
  37. bf16x2-instructions-approx.ll
  38. bf16x2-instructions.ll
  39. bfe.ll
  40. bmsk.ll
  41. boolean-patterns.ll
  42. branch-fold.ll
  43. branch-fold.mir
  44. brkpt.ll
  45. bswap.ll
  46. bug17709.ll
  47. bug21465.ll
  48. bug22246.ll
  49. bug22322.ll
  50. bug26185-2.ll
  51. bug26185.ll
  52. bug41651.ll
  53. bug52623.ll
  54. bypass-div.ll
  55. byval-const-global.ll
  56. call-with-alloca-buffer.ll
  57. call_bitcast_byval.ll
  58. callchain.ll
  59. calling-conv.ll
  60. calls-with-phi.ll
  61. chain-different-as.ll
  62. cluster-dim.ll
  63. clusterlaunchcontrol-multicast.ll
  64. clusterlaunchcontrol.ll
  65. cmpxchg-sm60.ll
  66. cmpxchg-sm70.ll
  67. cmpxchg-sm90.ll
  68. cmpxchg.ll
  69. cmpxchg.py
  70. combine-mad.ll
  71. combine-min-max.ll
  72. common-linkage.ll
  73. compare-int.ll
  74. compute-ptx-value-vts.ll
  75. constant-vectors.ll
  76. convergent-mir-call.ll
  77. convert-call-to-indirect.ll
  78. convert-fp-i8.ll
  79. convert-fp.ll
  80. convert-int-sm20.ll
  81. convert-sm100.ll
  82. convert-sm100a.ll
  83. convert-sm80.ll
  84. convert-sm89.ll
  85. convert-sm90.ll
  86. copysign.ll
  87. cp-async-bulk-s2g-sm100.ll
  88. cp-async-bulk-tensor-g2s-1cta.ll
  89. cp-async-bulk-tensor-g2s-2cta.ll
  90. cp-async-bulk-tensor-g2s-invalid.ll
  91. cp-async-bulk-tensor-g2s.ll
  92. cp-async-bulk-tensor-prefetch.ll
  93. cp-async-bulk-tensor-reduce.ll
  94. cp-async-bulk-tensor-s2g.ll
  95. cp-async-bulk.ll
  96. ctlz.ll
  97. ctpop.ll
  98. cttz.ll
  99. dag-cse.ll
  100. demote-vars.ll
  101. disable-opt.ll
  102. discard.ll
  103. disjoint-or-addr.ll
  104. distributed-shared-cluster.ll
  105. div-ri.ll
  106. div.ll
  107. divrem-combine.ll
  108. dot-product.ll
  109. dynamic-stackalloc-regression.ll
  110. dynamic_stackalloc.ll
  111. elect.ll
  112. empty-type.ll
  113. envreg.ll
  114. extloadv.ll
  115. extractelement.ll
  116. f16-abs.ll
  117. f16-ex2.ll
  118. f16-instructions.ll
  119. f16x2-instructions.ll
  120. f32-ex2.ll
  121. f32-lg2.ll
  122. fabs-intrinsics.ll
  123. fast-math.ll
  124. fcos-no-fast-math.ll
  125. fence-cluster.ll
  126. fence-nocluster.ll
  127. fence-proxy-tensormap.ll
  128. fence.py
  129. fexp2.ll
  130. filetype-null.ll
  131. flo.ll
  132. flog2.ll
  133. fma-assoc.ll
  134. fma-disable.ll
  135. fma-relu-contract.ll
  136. fma-relu-fma-intrinsic.ll
  137. fma-relu-instruction-flag.ll
  138. fma.ll
  139. fminimum-fmaximum.ll
  140. fns.ll
  141. forward-ld-param.ll
  142. fp-contract.ll
  143. fp-literals.ll
  144. fp128-storage-type.ll
  145. fp16.ll
  146. frem.ll
  147. fsin-no-fast-math.ll
  148. function-align.ll
  149. funnel-shift-clamp.ll
  150. generic-to-nvvm-ir.ll
  151. generic-to-nvvm.ll
  152. global-addrspace.ll
  153. global-ctor-empty.ll
  154. global-incomplete-init.ll
  155. global-ordering.ll
  156. global-variable-big.ll
  157. global-visibility.ll
  158. globals_init.ll
  159. globals_lowering.ll
  160. griddepcontrol.ll
  161. gvar-init.ll
  162. half.ll
  163. i1-array-global.ll
  164. i1-ext-load.ll
  165. i1-global.ll
  166. i1-icmp.ll
  167. i1-int-to-fp.ll
  168. i1-load-lower.ll
  169. i1-param.ll
  170. i1-select.ll
  171. i128-array.ll
  172. i128-global.ll
  173. i128-ld-st.ll
  174. i128-param.ll
  175. i128-retval.ll
  176. i128-struct.ll
  177. i128.ll
  178. i16x2-instructions.ll
  179. i8-param.ll
  180. i8x2-instructions.ll
  181. i8x4-instructions.ll
  182. idioms.ll
  183. imad.ll
  184. indirect_byval.ll
  185. inline-asm-b128-test1.ll
  186. inline-asm-b128-test2.ll
  187. inline-asm-b128-test3.ll
  188. inline-asm.ll
  189. inlineasm-output-template.ll
  190. intr-range.ll
  191. intrinsic-old.ll
  192. intrinsics-sm90.ll
  193. intrinsics.ll
  194. isspacep.ll
  195. jump-table.ll
  196. kernel-param-align.ll
  197. ld-addrspace.ll
  198. ld-generic.ll
  199. ld-st-addrrspace.py
  200. ldg-invariant-256.ll
  201. ldg-invariant.ll
  202. ldparam-v4.ll
  203. ldu-i8.ll
  204. ldu-ldg.ll
  205. ldu-reg-plus-offset.ll
  206. lit.local.cfg
  207. load-sext-i1.ll
  208. load-store-256-addressing-invariant.ll
  209. load-store-256-addressing.ll
  210. load-store-scalars.ll
  211. load-store-sm-70.ll
  212. load-store-sm-90.ll
  213. load-store-vectors-256.ll
  214. load-store-vectors.ll
  215. load-with-non-coherent-cache.ll
  216. LoadStoreVectorizer.ll
  217. local-stack-frame.ll
  218. loop-vectorize.ll
  219. lower-aggr-copies.ll
  220. lower-alloca.ll
  221. lower-args-gridconstant.ll
  222. lower-args.ll
  223. lower-byval-args.ll
  224. lower-ctor-dtor.ll
  225. lower-kernel-ptr-arg.ll
  226. machine-sink.ll
  227. MachineSink-call.ll
  228. MachineSink-convergent.ll
  229. managed.ll
  230. match.ll
  231. math-intrins-sm53-ptx42.ll
  232. math-intrins-sm80-ptx70-autoupgrade.ll
  233. math-intrins-sm80-ptx70-instcombine.ll
  234. math-intrins-sm80-ptx70.ll
  235. math-intrins-sm86-ptx72-autoupgrade.ll
  236. math-intrins-sm86-ptx72.ll
  237. math-intrins.ll
  238. max-align.ll
  239. maxclusterrank.ll
  240. mbarrier.ll
  241. minmax-negative.ll
  242. misaligned-vector-ldst.ll
  243. misched_func_call.ll
  244. mma-no-sink-after-laneid-check.ll
  245. module-inline-asm.ll
  246. mulhi-intrins.ll
  247. mulwide.ll
  248. naked-fn-with-frame-pointer.ll
  249. nanosleep.ll
  250. no-extra-parens.ll
  251. noduplicate-syncthreads.ll
  252. nofunc.ll
  253. noreturn.ll
  254. nounroll.ll
  255. nvcl-param-align.ll
  256. nvptx-aa-inline-asm.ll
  257. nvptx-aa.ll
  258. nvptx-prec-divf32-flag.ll
  259. NVPTXAA_before_BasicAA.ll
  260. nvvm-annotations-D120129.ll
  261. nvvm-reflect-arch-O0.ll
  262. nvvm-reflect-arch.ll
  263. nvvm-reflect-module-flag.ll
  264. nvvm-reflect-ocl.ll
  265. nvvm-reflect-opaque.ll
  266. nvvm-reflect-options.ll
  267. nvvm-reflect.ll
  268. packed-aggr.ll
  269. param-add.ll
  270. param-align.ll
  271. param-load-store.ll
  272. param-overalign.ll
  273. param-vectorize-device.ll
  274. param-vectorize-kernel.ll
  275. pass-name.ll
  276. pm-event.ll
  277. pow2_mask_cmp.ll
  278. pr13291-i1-store.ll
  279. pr16278.ll
  280. pr17529.ll
  281. prefetch.ll
  282. prmt.ll
  283. proxy-reg-erasure-ptx.ll
  284. proxy-reg-erasure.mir
  285. rcp-opt.ll
  286. read-global-variable-constant.ll
  287. reduction-intrinsics.ll
  288. redux-sync-f32.ll
  289. redux-sync.ll
  290. refl1.ll
  291. reg-copy.ll
  292. reg-types.ll
  293. rotate-add.ll
  294. rotate.ll
  295. rotate_64.ll
  296. rsqrt-opt.ll
  297. rsqrt.ll
  298. sad-intrins.ll
  299. sched1.ll
  300. sched2.ll
  301. setmaxnreg-sm100a.ll
  302. setmaxnreg.ll
  303. sext-in-reg.ll
  304. sext-params.ll
  305. sext-setcc.ll
  306. shfl-p.ll
  307. shfl-sync-p.ll
  308. shfl-sync.ll
  309. shfl.ll
  310. shift-opt.ll
  311. shift-parts.ll
  312. short-ptr.ll
  313. shuffle-vec-undef-init.ll
  314. simple-call.ll
  315. sm-version.ll
  316. speculative-execution-divergent-target.ll
  317. sqrt-approx.ll
  318. st-addrspace.ll
  319. st-generic.ll
  320. st-param-imm.ll
  321. st_bulk.ll
  322. stacksaverestore.ll
  323. store-retval.ll
  324. store-undef.ll
  325. surf-read-cuda.ll
  326. surf-read.ll
  327. surf-tex.py
  328. surf-write-cuda.ll
  329. surf-write.ll
  330. symbol-naming.ll
  331. szext.ll
  332. tag-invariant-loads.ll
  333. TailDuplication-convergent.ll
  334. tcgen05-alloc.ll
  335. tcgen05-commit.ll
  336. tcgen05-cp.ll
  337. tcgen05-fence.ll
  338. tcgen05-ld.ll
  339. tcgen05-shift.ll
  340. tcgen05-st.ll
  341. tex-read-cuda.ll
  342. tex-read.ll
  343. texsurf-queries.ll
  344. tid-range.ll
  345. unaligned-param-load-store.ll
  346. unfold-masked-merge-vector-variablemask.ll
  347. unreachable.ll
  348. unrecognized-sm1x.ll
  349. upgrade-nvvm-annotations.ll
  350. vaargs.ll
  351. variadics-backend.ll
  352. variadics-lowering.ll
  353. vec-param-load.ll
  354. vec8.ll
  355. vector-args.ll
  356. vector-call.ll
  357. vector-compare.ll
  358. vector-global.ll
  359. vector-loads.ll
  360. vector-returns.ll
  361. vector-select.ll
  362. vector-stores.ll
  363. vectorize-misaligned.ll
  364. vote.ll
  365. weak-global.ll
  366. weak-linkage.ll
  367. wgmma-sm90a-fence.ll
  368. wmma-ptx60-sm70.py
  369. wmma-ptx61-sm70.py
  370. wmma-ptx63-sm72.py
  371. wmma-ptx63-sm75.py
  372. wmma-ptx64-sm70.py
  373. wmma-ptx65-sm75.py
  374. wmma-ptx71-sm80.py
  375. wmma-ptx86-sm100a.py
  376. wmma-ptx86-sm101a.py
  377. wmma-ptx86-sm120a.py
  378. wmma.py
  379. zeroext-32bit.ll