Google Git
Sign in
llvm/llvm-project/88305251fe809ba384ea4ff4893bf671757504fb/./llvm/test/CodeGen/NVPTX
tree: 1dede6ca31ec9d82040b944fe3e66a1521b651a1 [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-b128.ll
  30. atomics-sm60.ll
  31. atomics-sm70.ll
  32. atomics-sm90.ll
  33. atomics-with-scope.ll
  34. atomics.ll
  35. b52037.ll
  36. barrier.ll
  37. bf16-instructions.ll
  38. bf16.ll
  39. bf16x2-instructions-approx.ll
  40. bf16x2-instructions.ll
  41. bfe.ll
  42. blocksareclusters-kernel-attr.ll
  43. bmsk.ll
  44. boolean-patterns.ll
  45. branch-fold.ll
  46. branch-fold.mir
  47. brkpt.ll
  48. bswap.ll
  49. bug17709.ll
  50. bug21465.ll
  51. bug22246.ll
  52. bug22322.ll
  53. bug26185-2.ll
  54. bug26185.ll
  55. bug41651.ll
  56. bug52623.ll
  57. bypass-div.ll
  58. byval-arg-vectorize.ll
  59. byval-const-global.ll
  60. call-with-alloca-buffer.ll
  61. call_bitcast_byval.ll
  62. callchain.ll
  63. calling-conv.ll
  64. calls-with-phi.ll
  65. chain-different-as.ll
  66. cluster-dim.ll
  67. clusterlaunchcontrol-multicast.ll
  68. clusterlaunchcontrol.ll
  69. cmpxchg-sm60.ll
  70. cmpxchg-sm70.ll
  71. cmpxchg-sm90.ll
  72. cmpxchg-unsupported-syncscope.err.ll
  73. cmpxchg.ll
  74. cmpxchg.py
  75. combine-mad.ll
  76. combine-min-max.ll
  77. combine-wide.ll
  78. common-linkage.ll
  79. compare-int.ll
  80. compute-ptx-value-vts.ll
  81. constant-vectors.ll
  82. convergent-mir-call.ll
  83. convert-call-to-indirect.ll
  84. convert-fp-i8.ll
  85. convert-fp.ll
  86. convert-int-sm20.ll
  87. convert-sm100.ll
  88. convert-sm100a.ll
  89. convert-sm103a.ll
  90. convert-sm80-sf.ll
  91. convert-sm80.ll
  92. convert-sm89.ll
  93. convert-sm90.ll
  94. copysign.ll
  95. cp-async-bulk-ptx86.ll
  96. cp-async-bulk-s2g-sm100.ll
  97. cp-async-bulk-tensor-g2s-1cta.ll
  98. cp-async-bulk-tensor-g2s-2cta.ll
  99. cp-async-bulk-tensor-g2s-cta-sm100.ll
  100. cp-async-bulk-tensor-g2s-cta-sm100a.ll
  101. cp-async-bulk-tensor-g2s-cta-sm90.ll
  102. cp-async-bulk-tensor-g2s-gather4.ll
  103. cp-async-bulk-tensor-g2s-im2colw.ll
  104. cp-async-bulk-tensor-g2s-im2colw128.ll
  105. cp-async-bulk-tensor-g2s-invalid.ll
  106. cp-async-bulk-tensor-g2s.ll
  107. cp-async-bulk-tensor-prefetch-sm100a.ll
  108. cp-async-bulk-tensor-prefetch.ll
  109. cp-async-bulk-tensor-reduce.ll
  110. cp-async-bulk-tensor-s2g-scatter4.ll
  111. cp-async-bulk-tensor-s2g.ll
  112. cp-async-bulk.ll
  113. cse-mov-sym.ll
  114. ctlz.ll
  115. ctpop.ll
  116. cttz.ll
  117. dag-cse.ll
  118. demote-vars.ll
  119. disable-opt.ll
  120. discard.ll
  121. disjoint-or-addr.ll
  122. distributed-shared-cluster.ll
  123. div-ri.ll
  124. div.ll
  125. divrem-combine.ll
  126. dot-product.ll
  127. dynamic-stackalloc-regression.ll
  128. dynamic_stackalloc.ll
  129. elect.ll
  130. empty-type.ll
  131. envreg.ll
  132. extloadv.ll
  133. extractelement.ll
  134. f16-abs.ll
  135. f16-ex2.ll
  136. f16-instructions.ll
  137. f16x2-instructions.ll
  138. f32-ex2.ll
  139. f32-lg2.ll
  140. f32x2-convert-i32x2.ll
  141. f32x2-instructions.ll
  142. fabs-intrinsics.ll
  143. fast-math.ll
  144. fcos-no-fast-math.ll
  145. fence-cluster.ll
  146. fence-nocluster.ll
  147. fence-proxy-sm90-ptx86.ll
  148. fence-proxy-sm90.ll
  149. fence-proxy-tensormap-invalid.ll
  150. fence-proxy-tensormap.ll
  151. fence-proxy.ll
  152. fence.py
  153. fexp2.ll
  154. filetype-null.ll
  155. flo.ll
  156. flog2.ll
  157. fma-assoc.ll
  158. fma-disable.ll
  159. fma-relu-contract.ll
  160. fma-relu-fma-intrinsic.ll
  161. fma-relu-instruction-flag.ll
  162. fma.ll
  163. fmax3.ll
  164. fminimum-fmaximum.ll
  165. fns.ll
  166. fold-movs.ll
  167. forward-ld-param.ll
  168. fp-contract-f32x2.ll
  169. fp-contract.ll
  170. fp-literals.ll
  171. fp128-storage-type.ll
  172. fp16.ll
  173. frameindex-lifetime.ll
  174. frem.ll
  175. fsin-no-fast-math.ll
  176. function-align.ll
  177. funnel-shift-clamp.ll
  178. generic-to-nvvm-ir.ll
  179. generic-to-nvvm.ll
  180. global-addrspace.ll
  181. global-ctor-empty.ll
  182. global-incomplete-init.ll
  183. global-ordering.ll
  184. global-variable-big.ll
  185. global-visibility.ll
  186. globals_init.ll
  187. globals_lowering.ll
  188. griddepcontrol.ll
  189. gvar-init.ll
  190. half.ll
  191. i1-array-global.ll
  192. i1-ext-load.ll
  193. i1-global.ll
  194. i1-icmp.ll
  195. i1-int-to-fp.ll
  196. i1-load-lower.ll
  197. i1-param.ll
  198. i1-select.ll
  199. i128-array.ll
  200. i128-global.ll
  201. i128-ld-st.ll
  202. i128-param.ll
  203. i128-retval.ll
  204. i128-struct.ll
  205. i128.ll
  206. i16x2-instructions.ll
  207. i32x2-instructions.ll
  208. i8-param.ll
  209. i8x2-instructions.ll
  210. i8x4-instructions.ll
  211. idioms.ll
  212. imad.ll
  213. indirect_byval.ll
  214. inline-asm-b128-test1.ll
  215. inline-asm-b128-test2.ll
  216. inline-asm-b128-test3.ll
  217. inline-asm.ll
  218. inlineasm-output-template.ll
  219. insertelt-dynamic.ll
  220. intr-range.ll
  221. intrinsic-old.ll
  222. intrinsics-sm90.ll
  223. intrinsics.ll
  224. isspacep.ll
  225. jump-table.ll
  226. kernel-param-align.ll
  227. ld-addrspace.ll
  228. ld-generic.ll
  229. ld-param-sink.ll
  230. ld-st-addrrspace.py
  231. ldg-invariant-256.ll
  232. ldg-invariant.ll
  233. ldparam-v4.ll
  234. ldu-i8.ll
  235. ldu-ldg.ll
  236. ldu-reg-plus-offset.ll
  237. lit.local.cfg
  238. load-sext-i1.ll
  239. load-store-256-addressing-invariant.ll
  240. load-store-256-addressing.ll
  241. load-store-atomic.err.ll
  242. load-store-scalars.ll
  243. load-store-sm-70.ll
  244. load-store-sm-90.ll
  245. load-store-vectors-256.ll
  246. load-store-vectors.ll
  247. load-with-non-coherent-cache.ll
  248. LoadStoreVectorizer.ll
  249. local-stack-frame.ll
  250. loop-vectorize.ll
  251. lower-aggr-copies.ll
  252. lower-alloca.ll
  253. lower-args-alignment.ll
  254. lower-args-gridconstant.ll
  255. lower-args.ll
  256. lower-byval-args.ll
  257. lower-ctor-dtor.ll
  258. lower-kernel-ptr-arg.ll
  259. machine-sink.ll
  260. machinelicm-no-preheader.mir
  261. MachineSink-call.ll
  262. MachineSink-convergent.ll
  263. managed.ll
  264. match.ll
  265. math-intrins-sm53-ptx42.ll
  266. math-intrins-sm80-ptx70-autoupgrade.ll
  267. math-intrins-sm80-ptx70-instcombine.ll
  268. math-intrins-sm80-ptx70.ll
  269. math-intrins-sm86-ptx72-autoupgrade.ll
  270. math-intrins-sm86-ptx72.ll
  271. math-intrins.ll
  272. max-align.ll
  273. maxclusterrank.ll
  274. mbarrier.ll
  275. mbarrier_arr.ll
  276. mbarrier_arr_relaxed.ll
  277. mbarrier_tx.ll
  278. mbarrier_wait_sm80_ptx70.ll
  279. mbarrier_wait_sm80_ptx71.ll
  280. mbarrier_wait_sm90_ptx78.ll
  281. mbarrier_wait_sm90_ptx80.ll
  282. mbarrier_wait_sm90_ptx86.ll
  283. minmax-negative.ll
  284. misaligned-vector-ldst.ll
  285. misched_func_call.ll
  286. mma-no-sink-after-laneid-check.ll
  287. module-inline-asm.ll
  288. mulhi-intrins.ll
  289. mulwide.ll
  290. naked-fn-with-frame-pointer.ll
  291. nanosleep.ll
  292. no-extra-parens.ll
  293. no-f32x2.ll
  294. no-stack-protector-libcall-error.ll
  295. noduplicate-syncthreads.ll
  296. nofunc.ll
  297. noreturn.ll
  298. nounroll.ll
  299. nvcl-param-align.ll
  300. nvptx-aa-inline-asm.ll
  301. nvptx-aa.ll
  302. nvptx-prec-divf32-flag.ll
  303. NVPTXAA_before_BasicAA.ll
  304. nvvm-annotations-D120129.ll
  305. nvvm-reflect-arch-O0.ll
  306. nvvm-reflect-arch.ll
  307. nvvm-reflect-module-flag.ll
  308. nvvm-reflect-ocl.ll
  309. nvvm-reflect-opaque.ll
  310. nvvm-reflect-options.ll
  311. nvvm-reflect.ll
  312. op-fence.ll
  313. packed-aggr.ll
  314. param-add.ll
  315. param-align.ll
  316. param-load-store.ll
  317. param-overalign.ll
  318. param-vectorize-device.ll
  319. param-vectorize-kernel.ll
  320. pass-name.ll
  321. pm-event.ll
  322. pow2_mask_cmp.ll
  323. pr126337.ll
  324. pr13291-i1-store.ll
  325. pr16278.ll
  326. pr17529.ll
  327. prefetch-inferas-test.ll
  328. prefetch.ll
  329. prmt-const-folding.ll
  330. prmt.ll
  331. proxy-reg-erasure-ptx.ll
  332. proxy-reg-erasure.mir
  333. rcp-opt.ll
  334. read-global-variable-constant.ll
  335. reduction-intrinsics.ll
  336. redux-sync-f32.ll
  337. redux-sync.ll
  338. refl1.ll
  339. reg-copy.ll
  340. reg-types.ll
  341. rotate-add.ll
  342. rotate.ll
  343. rotate_64.ll
  344. rsqrt-opt.ll
  345. rsqrt.ll
  346. sad-intrins.ll
  347. sched1.ll
  348. sched2.ll
  349. setmaxnreg-sm100a.ll
  350. setmaxnreg.ll
  351. sext-in-reg.ll
  352. sext-params.ll
  353. sext-setcc.ll
  354. shfl-p.ll
  355. shfl-sync-p.ll
  356. shfl-sync.ll
  357. shfl.ll
  358. shift-opt.ll
  359. shift-parts.ll
  360. short-ptr.ll
  361. shuffle-vec-undef-init.ll
  362. simple-call.ll
  363. sm-version.ll
  364. speculative-execution-divergent-target.ll
  365. sqrt-approx.ll
  366. st-addrspace.ll
  367. st-generic.ll
  368. st-param-imm.ll
  369. st_bulk.ll
  370. stacksaverestore.ll
  371. store-retval.ll
  372. store-undef.ll
  373. surf-read-cuda.ll
  374. surf-read.ll
  375. surf-tex.py
  376. surf-write-cuda.ll
  377. surf-write.ll
  378. symbol-naming.ll
  379. szext.ll
  380. tag-invariant-loads.ll
  381. TailDuplication-convergent.ll
  382. tanhf.ll
  383. tcgen05-alloc.ll
  384. tcgen05-commit.ll
  385. tcgen05-cp.ll
  386. tcgen05-fence.ll
  387. tcgen05-ld.ll
  388. tcgen05-mma-block-scale-invalid.ll
  389. tcgen05-mma-block-scale-ptx88.ll
  390. tcgen05-mma-block-scale.ll
  391. tcgen05-mma-disable-output-lane.ll
  392. tcgen05-mma-invalid.ll
  393. tcgen05-mma-scale-d-invalid.ll
  394. tcgen05-mma-scale-d.ll
  395. tcgen05-mma-tensor-formatted.ll
  396. tcgen05-mma-ws.ll
  397. tcgen05-mma.ll
  398. tcgen05-shift.ll
  399. tcgen05-st.ll
  400. tex-read-cuda.ll
  401. tex-read.ll
  402. texsurf-queries.ll
  403. thread-fence.ll
  404. tid-range.ll
  405. trunc-setcc.ll
  406. trunc-tofp.ll
  407. unaligned-param-load-store.ll
  408. unfold-masked-merge-vector-variablemask.ll
  409. unreachable.ll
  410. unrecognized-sm1x.ll
  411. upgrade-nvvm-annotations.ll
  412. vaargs.ll
  413. variadics-backend.ll
  414. variadics-lowering.ll
  415. vec-param-load.ll
  416. vec8.ll
  417. vector-args.ll
  418. vector-call.ll
  419. vector-compare.ll
  420. vector-global.ll
  421. vector-loads.ll
  422. vector-returns.ll
  423. vector-select.ll
  424. vector-stores.ll
  425. vectorize-misaligned.ll
  426. vote.ll
  427. weak-global.ll
  428. weak-linkage.ll
  429. wgmma-sm90a-fence.ll
  430. wmma-ptx60-sm70.py
  431. wmma-ptx61-sm70.py
  432. wmma-ptx63-sm72.py
  433. wmma-ptx63-sm75.py
  434. wmma-ptx64-sm70.py
  435. wmma-ptx65-sm75.py
  436. wmma-ptx71-sm80.py
  437. wmma-ptx78-sm90.py
  438. wmma-ptx86-sm100a.py
  439. wmma-ptx86-sm101a.py
  440. wmma-ptx86-sm120a.py
  441. wmma-ptx87-sm120a.py
  442. wmma.py
  443. zeroext-32bit.ll