Google Git
Sign in
llvm / llvm-project / af44d87e0d80cda78451d8de723c974bf58ccac0 / . / llvm / test / CodeGen / NVPTX
tree: 85aeb6ce5e329a55bf4cf56c9d1fc44919d9daa0 [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.err.ll
  28. atomicrmw-expand.ll
  29. atomics-sm60.ll
  30. atomics-sm70.ll
  31. atomics-sm90.ll
  32. atomics-with-scope.ll
  33. atomics.ll
  34. b52037.ll
  35. barrier.ll
  36. bf16-instructions.ll
  37. bf16.ll
  38. bf16x2-instructions-approx.ll
  39. bf16x2-instructions.ll
  40. bfe.ll
  41. bmsk.ll
  42. boolean-patterns.ll
  43. branch-fold.ll
  44. branch-fold.mir
  45. brkpt.ll
  46. bswap.ll
  47. bug17709.ll
  48. bug21465.ll
  49. bug22246.ll
  50. bug22322.ll
  51. bug26185-2.ll
  52. bug26185.ll
  53. bug41651.ll
  54. bug52623.ll
  55. bypass-div.ll
  56. byval-const-global.ll
  57. call-with-alloca-buffer.ll
  58. call_bitcast_byval.ll
  59. callchain.ll
  60. calling-conv.ll
  61. calls-with-phi.ll
  62. chain-different-as.ll
  63. cluster-dim.ll
  64. clusterlaunchcontrol-multicast.ll
  65. clusterlaunchcontrol.ll
  66. cmpxchg-sm60.ll
  67. cmpxchg-sm70.ll
  68. cmpxchg-sm90.ll
  69. cmpxchg.ll
  70. cmpxchg.py
  71. combine-mad.ll
  72. combine-min-max.ll
  73. common-linkage.ll
  74. compare-int.ll
  75. compute-ptx-value-vts.ll
  76. constant-vectors.ll
  77. convergent-mir-call.ll
  78. convert-call-to-indirect.ll
  79. convert-fp-i8.ll
  80. convert-fp.ll
  81. convert-int-sm20.ll
  82. convert-sm100.ll
  83. convert-sm100a.ll
  84. convert-sm80.ll
  85. convert-sm89.ll
  86. convert-sm90.ll
  87. copysign.ll
  88. cp-async-bulk-s2g-sm100.ll
  89. cp-async-bulk-tensor-g2s-1cta.ll
  90. cp-async-bulk-tensor-g2s-2cta.ll
  91. cp-async-bulk-tensor-g2s-cta-sm100.ll
  92. cp-async-bulk-tensor-g2s-cta-sm100a.ll
  93. cp-async-bulk-tensor-g2s-cta-sm90.ll
  94. cp-async-bulk-tensor-g2s-gather4.ll
  95. cp-async-bulk-tensor-g2s-im2colw.ll
  96. cp-async-bulk-tensor-g2s-im2colw128.ll
  97. cp-async-bulk-tensor-g2s-invalid.ll
  98. cp-async-bulk-tensor-g2s.ll
  99. cp-async-bulk-tensor-prefetch-sm100a.ll
  100. cp-async-bulk-tensor-prefetch.ll
  101. cp-async-bulk-tensor-reduce.ll
  102. cp-async-bulk-tensor-s2g-scatter4.ll
  103. cp-async-bulk-tensor-s2g.ll
  104. cp-async-bulk.ll
  105. ctlz.ll
  106. ctpop.ll
  107. cttz.ll
  108. dag-cse.ll
  109. demote-vars.ll
  110. disable-opt.ll
  111. discard.ll
  112. disjoint-or-addr.ll
  113. distributed-shared-cluster.ll
  114. div-ri.ll
  115. div.ll
  116. divrem-combine.ll
  117. dot-product.ll
  118. dynamic-stackalloc-regression.ll
  119. dynamic_stackalloc.ll
  120. elect.ll
  121. empty-type.ll
  122. envreg.ll
  123. extloadv.ll
  124. extractelement.ll
  125. f16-abs.ll
  126. f16-ex2.ll
  127. f16-instructions.ll
  128. f16x2-instructions.ll
  129. f32-ex2.ll
  130. f32-lg2.ll
  131. f32x2-instructions.ll
  132. fabs-intrinsics.ll
  133. fast-math.ll
  134. fcos-no-fast-math.ll
  135. fence-cluster.ll
  136. fence-nocluster.ll
  137. fence-proxy-tensormap.ll
  138. fence.py
  139. fexp2.ll
  140. filetype-null.ll
  141. flo.ll
  142. flog2.ll
  143. fma-assoc.ll
  144. fma-disable.ll
  145. fma-relu-contract.ll
  146. fma-relu-fma-intrinsic.ll
  147. fma-relu-instruction-flag.ll
  148. fma.ll
  149. fminimum-fmaximum.ll
  150. fns.ll
  151. forward-ld-param.ll
  152. fp-contract-f32x2.ll
  153. fp-contract.ll
  154. fp-literals.ll
  155. fp128-storage-type.ll
  156. fp16.ll
  157. frameindex-lifetime.ll
  158. frem.ll
  159. fsin-no-fast-math.ll
  160. function-align.ll
  161. funnel-shift-clamp.ll
  162. generic-to-nvvm-ir.ll
  163. generic-to-nvvm.ll
  164. global-addrspace.ll
  165. global-ctor-empty.ll
  166. global-incomplete-init.ll
  167. global-ordering.ll
  168. global-variable-big.ll
  169. global-visibility.ll
  170. globals_init.ll
  171. globals_lowering.ll
  172. griddepcontrol.ll
  173. gvar-init.ll
  174. half.ll
  175. i1-array-global.ll
  176. i1-ext-load.ll
  177. i1-global.ll
  178. i1-icmp.ll
  179. i1-int-to-fp.ll
  180. i1-load-lower.ll
  181. i1-param.ll
  182. i1-select.ll
  183. i128-array.ll
  184. i128-global.ll
  185. i128-ld-st.ll
  186. i128-param.ll
  187. i128-retval.ll
  188. i128-struct.ll
  189. i128.ll
  190. i16x2-instructions.ll
  191. i8-param.ll
  192. i8x2-instructions.ll
  193. i8x4-instructions.ll
  194. idioms.ll
  195. imad.ll
  196. indirect_byval.ll
  197. inline-asm-b128-test1.ll
  198. inline-asm-b128-test2.ll
  199. inline-asm-b128-test3.ll
  200. inline-asm.ll
  201. inlineasm-output-template.ll
  202. intr-range.ll
  203. intrinsic-old.ll
  204. intrinsics-sm90.ll
  205. intrinsics.ll
  206. isspacep.ll
  207. jump-table.ll
  208. kernel-param-align.ll
  209. ld-addrspace.ll
  210. ld-generic.ll
  211. ld-st-addrrspace.py
  212. ldg-invariant-256.ll
  213. ldg-invariant.ll
  214. ldparam-v4.ll
  215. ldu-i8.ll
  216. ldu-ldg.ll
  217. ldu-reg-plus-offset.ll
  218. lit.local.cfg
  219. load-sext-i1.ll
  220. load-store-256-addressing-invariant.ll
  221. load-store-256-addressing.ll
  222. load-store-scalars.ll
  223. load-store-sm-70.ll
  224. load-store-sm-90.ll
  225. load-store-vectors-256.ll
  226. load-store-vectors.ll
  227. load-with-non-coherent-cache.ll
  228. LoadStoreVectorizer.ll
  229. local-stack-frame.ll
  230. loop-vectorize.ll
  231. lower-aggr-copies.ll
  232. lower-alloca.ll
  233. lower-args-gridconstant.ll
  234. lower-args.ll
  235. lower-byval-args.ll
  236. lower-ctor-dtor.ll
  237. lower-kernel-ptr-arg.ll
  238. machine-sink.ll
  239. MachineSink-call.ll
  240. MachineSink-convergent.ll
  241. managed.ll
  242. match.ll
  243. math-intrins-sm53-ptx42.ll
  244. math-intrins-sm80-ptx70-autoupgrade.ll
  245. math-intrins-sm80-ptx70-instcombine.ll
  246. math-intrins-sm80-ptx70.ll
  247. math-intrins-sm86-ptx72-autoupgrade.ll
  248. math-intrins-sm86-ptx72.ll
  249. math-intrins.ll
  250. max-align.ll
  251. maxclusterrank.ll
  252. mbarrier.ll
  253. minmax-negative.ll
  254. misaligned-vector-ldst.ll
  255. misched_func_call.ll
  256. mma-no-sink-after-laneid-check.ll
  257. module-inline-asm.ll
  258. mulhi-intrins.ll
  259. mulwide.ll
  260. naked-fn-with-frame-pointer.ll
  261. nanosleep.ll
  262. no-extra-parens.ll
  263. no-stack-protector-libcall-error.ll
  264. noduplicate-syncthreads.ll
  265. nofunc.ll
  266. noreturn.ll
  267. nounroll.ll
  268. nvcl-param-align.ll
  269. nvptx-aa-inline-asm.ll
  270. nvptx-aa.ll
  271. nvptx-prec-divf32-flag.ll
  272. NVPTXAA_before_BasicAA.ll
  273. nvvm-annotations-D120129.ll
  274. nvvm-reflect-arch-O0.ll
  275. nvvm-reflect-arch.ll
  276. nvvm-reflect-module-flag.ll
  277. nvvm-reflect-ocl.ll
  278. nvvm-reflect-opaque.ll
  279. nvvm-reflect-options.ll
  280. nvvm-reflect.ll
  281. packed-aggr.ll
  282. param-add.ll
  283. param-align.ll
  284. param-load-store.ll
  285. param-overalign.ll
  286. param-vectorize-device.ll
  287. param-vectorize-kernel.ll
  288. pass-name.ll
  289. pm-event.ll
  290. pow2_mask_cmp.ll
  291. pr126337.ll
  292. pr13291-i1-store.ll
  293. pr16278.ll
  294. pr17529.ll
  295. prefetch.ll
  296. prmt-const-folding.ll
  297. prmt.ll
  298. proxy-reg-erasure-ptx.ll
  299. proxy-reg-erasure.mir
  300. rcp-opt.ll
  301. read-global-variable-constant.ll
  302. reduction-intrinsics.ll
  303. redux-sync-f32.ll
  304. redux-sync.ll
  305. refl1.ll
  306. reg-copy.ll
  307. reg-types.ll
  308. rotate-add.ll
  309. rotate.ll
  310. rotate_64.ll
  311. rsqrt-opt.ll
  312. rsqrt.ll
  313. sad-intrins.ll
  314. sched1.ll
  315. sched2.ll
  316. setmaxnreg-sm100a.ll
  317. setmaxnreg.ll
  318. sext-in-reg.ll
  319. sext-params.ll
  320. sext-setcc.ll
  321. shfl-p.ll
  322. shfl-sync-p.ll
  323. shfl-sync.ll
  324. shfl.ll
  325. shift-opt.ll
  326. shift-parts.ll
  327. short-ptr.ll
  328. shuffle-vec-undef-init.ll
  329. simple-call.ll
  330. sm-version.ll
  331. speculative-execution-divergent-target.ll
  332. sqrt-approx.ll
  333. st-addrspace.ll
  334. st-generic.ll
  335. st-param-imm.ll
  336. st_bulk.ll
  337. stacksaverestore.ll
  338. store-retval.ll
  339. store-undef.ll
  340. surf-read-cuda.ll
  341. surf-read.ll
  342. surf-tex.py
  343. surf-write-cuda.ll
  344. surf-write.ll
  345. symbol-naming.ll
  346. szext.ll
  347. tag-invariant-loads.ll
  348. TailDuplication-convergent.ll
  349. tanhf.ll
  350. tcgen05-alloc.ll
  351. tcgen05-commit.ll
  352. tcgen05-cp.ll
  353. tcgen05-fence.ll
  354. tcgen05-ld.ll
  355. tcgen05-shift.ll
  356. tcgen05-st.ll
  357. tex-read-cuda.ll
  358. tex-read.ll
  359. texsurf-queries.ll
  360. tid-range.ll
  361. trunc-tofp.ll
  362. unaligned-param-load-store.ll
  363. unfold-masked-merge-vector-variablemask.ll
  364. unreachable.ll
  365. unrecognized-sm1x.ll
  366. upgrade-nvvm-annotations.ll
  367. vaargs.ll
  368. variadics-backend.ll
  369. variadics-lowering.ll
  370. vec-param-load.ll
  371. vec8.ll
  372. vector-args.ll
  373. vector-call.ll
  374. vector-compare.ll
  375. vector-global.ll
  376. vector-loads.ll
  377. vector-returns.ll
  378. vector-select.ll
  379. vector-stores.ll
  380. vectorize-misaligned.ll
  381. vote.ll
  382. weak-global.ll
  383. weak-linkage.ll
  384. wgmma-sm90a-fence.ll
  385. wmma-ptx60-sm70.py
  386. wmma-ptx61-sm70.py
  387. wmma-ptx63-sm72.py
  388. wmma-ptx63-sm75.py
  389. wmma-ptx64-sm70.py
  390. wmma-ptx65-sm75.py
  391. wmma-ptx71-sm80.py
  392. wmma-ptx78-sm90.py
  393. wmma-ptx86-sm100a.py
  394. wmma-ptx86-sm101a.py
  395. wmma-ptx86-sm120a.py
  396. wmma.py
  397. zeroext-32bit.ll