Google Git
Sign in
llvm / llvm-project / refs/heads/main / . / llvm / test / CodeGen / NVPTX
tree: 8d3914cd1834b351c9978d8ead30dba9159cb18a [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-mul-wide-type.ll
  78. combine-wide.ll
  79. common-linkage.ll
  80. compare-int.ll
  81. compute-ptx-value-vts.ll
  82. constant-vectors.ll
  83. convergent-mir-call.ll
  84. convert-call-to-indirect.ll
  85. convert-fp-i8.ll
  86. convert-fp.ll
  87. convert-int-sm20.ll
  88. convert-sm100.ll
  89. convert-sm100a.ll
  90. convert-sm103a.ll
  91. convert-sm80-sf.ll
  92. convert-sm80.ll
  93. convert-sm89.ll
  94. convert-sm90.ll
  95. copysign.ll
  96. cp-async-bulk-ptx86.ll
  97. cp-async-bulk-s2g-sm100.ll
  98. cp-async-bulk-tensor-g2s-1cta.ll
  99. cp-async-bulk-tensor-g2s-2cta.ll
  100. cp-async-bulk-tensor-g2s-cta-sm100.ll
  101. cp-async-bulk-tensor-g2s-cta-sm100a.ll
  102. cp-async-bulk-tensor-g2s-cta-sm90.ll
  103. cp-async-bulk-tensor-g2s-gather4.ll
  104. cp-async-bulk-tensor-g2s-im2colw.ll
  105. cp-async-bulk-tensor-g2s-im2colw128.ll
  106. cp-async-bulk-tensor-g2s-invalid.ll
  107. cp-async-bulk-tensor-g2s.ll
  108. cp-async-bulk-tensor-prefetch-sm100a.ll
  109. cp-async-bulk-tensor-prefetch.ll
  110. cp-async-bulk-tensor-reduce.ll
  111. cp-async-bulk-tensor-s2g-scatter4.ll
  112. cp-async-bulk-tensor-s2g.ll
  113. cp-async-bulk.ll
  114. cse-mov-sym.ll
  115. ctlz.ll
  116. ctpop.ll
  117. cttz.ll
  118. dag-cse.ll
  119. demote-vars.ll
  120. disable-opt.ll
  121. discard.ll
  122. disjoint-or-addr.ll
  123. distributed-shared-cluster.ll
  124. div-ri.ll
  125. div.ll
  126. divrem-combine.ll
  127. dot-product.ll
  128. dynamic-stackalloc-regression.ll
  129. dynamic_stackalloc.ll
  130. elect.ll
  131. empty-type.ll
  132. envreg.ll
  133. extloadv.ll
  134. extractelement.ll
  135. f16-abs.ll
  136. f16-ex2.ll
  137. f16-instructions.ll
  138. f16x2-instructions.ll
  139. f32-ex2.ll
  140. f32-lg2.ll
  141. f32x2-convert-i32x2.ll
  142. f32x2-instructions.ll
  143. fabs-intrinsics.ll
  144. fast-math.ll
  145. fcos-no-fast-math.ll
  146. fence-cluster.ll
  147. fence-nocluster.ll
  148. fence-proxy-sm90-ptx86.ll
  149. fence-proxy-sm90.ll
  150. fence-proxy-tensormap-invalid.ll
  151. fence-proxy-tensormap.ll
  152. fence-proxy.ll
  153. fence.py
  154. fexp2.ll
  155. filetype-null.ll
  156. flo.ll
  157. flog2.ll
  158. fma-assoc.ll
  159. fma-disable.ll
  160. fma-relu-contract.ll
  161. fma-relu-fma-intrinsic.ll
  162. fma-relu-instruction-flag.ll
  163. fma.ll
  164. fmax3.ll
  165. fminimum-fmaximum.ll
  166. fns.ll
  167. fold-movs.ll
  168. forward-ld-param.ll
  169. fp-arith-sat.ll
  170. fp-contract-f32x2.ll
  171. fp-contract.ll
  172. fp-fold-sub.ll
  173. fp-literals.ll
  174. fp128-storage-type.ll
  175. fp16.ll
  176. frameindex-lifetime.ll
  177. frem.ll
  178. fsin-no-fast-math.ll
  179. function-align.ll
  180. funnel-shift-clamp.ll
  181. generic-to-nvvm-ir.ll
  182. generic-to-nvvm.ll
  183. global-addrspace.ll
  184. global-ctor-empty.ll
  185. global-incomplete-init.ll
  186. global-ordering.ll
  187. global-variable-big.ll
  188. global-visibility.ll
  189. globals_init.ll
  190. globals_lowering.ll
  191. griddepcontrol.ll
  192. gvar-init.ll
  193. half.ll
  194. i1-array-global.ll
  195. i1-ext-load.ll
  196. i1-global.ll
  197. i1-icmp.ll
  198. i1-int-to-fp.ll
  199. i1-load-lower.ll
  200. i1-param.ll
  201. i1-select.ll
  202. i128-array.ll
  203. i128-global.ll
  204. i128-ld-st.ll
  205. i128-param.ll
  206. i128-retval.ll
  207. i128-struct.ll
  208. i128.ll
  209. i16x2-instructions.ll
  210. i32x2-instructions.ll
  211. i8-param.ll
  212. i8x2-instructions.ll
  213. i8x4-instructions.ll
  214. idioms.ll
  215. imad.ll
  216. indirect_byval.ll
  217. inline-asm-b128-test1.ll
  218. inline-asm-b128-test2.ll
  219. inline-asm-b128-test3.ll
  220. inline-asm.ll
  221. inlineasm-output-template.ll
  222. insertelt-dynamic.ll
  223. intr-range.ll
  224. intrinsic-old.ll
  225. intrinsics-sm90-ptx81.ll
  226. intrinsics-sm90.ll
  227. intrinsics.ll
  228. isspacep.ll
  229. jump-table.ll
  230. kernel-param-align.ll
  231. ld-addrspace.ll
  232. ld-generic.ll
  233. ld-param-sink.ll
  234. ld-st-addrrspace.py
  235. ldg-invariant-256.ll
  236. ldg-invariant.ll
  237. ldparam-v4.ll
  238. ldu-i8.ll
  239. ldu-ldg.ll
  240. ldu-reg-plus-offset.ll
  241. lit.local.cfg
  242. load-sext-i1.ll
  243. load-store-256-addressing-invariant.ll
  244. load-store-256-addressing.ll
  245. load-store-atomic.err.ll
  246. load-store-scalars.ll
  247. load-store-sm-70.ll
  248. load-store-sm-90.ll
  249. load-store-vectors-256.ll
  250. load-store-vectors.ll
  251. load-with-non-coherent-cache.ll
  252. LoadStoreVectorizer.ll
  253. local-stack-frame.ll
  254. loop-vectorize.ll
  255. lower-aggr-copies.ll
  256. lower-alloca.ll
  257. lower-args-alignment.ll
  258. lower-args-gridconstant.ll
  259. lower-args.ll
  260. lower-byval-args.ll
  261. lower-ctor-dtor.ll
  262. lower-kernel-ptr-arg.ll
  263. machine-sink.ll
  264. machinelicm-no-preheader.mir
  265. MachineSink-call.ll
  266. MachineSink-convergent.ll
  267. managed.ll
  268. masked-load-3xhalf.ll
  269. masked-load-vectors.ll
  270. masked-store-variable-mask.ll
  271. masked-store-vectors-256.ll
  272. match.ll
  273. math-intrins-sm53-ptx42.ll
  274. math-intrins-sm80-ptx70-autoupgrade.ll
  275. math-intrins-sm80-ptx70-instcombine.ll
  276. math-intrins-sm80-ptx70.ll
  277. math-intrins-sm86-ptx72-autoupgrade.ll
  278. math-intrins-sm86-ptx72.ll
  279. math-intrins.ll
  280. max-align.ll
  281. maxclusterrank.ll
  282. mbarrier.ll
  283. mbarrier_arr.ll
  284. mbarrier_arr_relaxed.ll
  285. mbarrier_tx.ll
  286. mbarrier_wait_sm80_ptx70.ll
  287. mbarrier_wait_sm80_ptx71.ll
  288. mbarrier_wait_sm90_ptx78.ll
  289. mbarrier_wait_sm90_ptx80.ll
  290. mbarrier_wait_sm90_ptx86.ll
  291. minmax-negative.ll
  292. misaligned-vector-ldst.ll
  293. misched_func_call.ll
  294. mixed-precision-fp.ll
  295. mma-no-sink-after-laneid-check.ll
  296. module-inline-asm.ll
  297. mulhi-intrins.ll
  298. mulwide.ll
  299. naked-fn-with-frame-pointer.ll
  300. nanosleep.ll
  301. no-extra-parens.ll
  302. no-f32x2.ll
  303. no-stack-protector-libcall-error.ll
  304. noduplicate-syncthreads.ll
  305. nofunc.ll
  306. noreturn.ll
  307. nounroll.ll
  308. nvcl-param-align.ll
  309. nvptx-aa-inline-asm.ll
  310. nvptx-aa.ll
  311. nvptx-fold-fma.ll
  312. nvptx-prec-divf32-flag.ll
  313. NVPTXAA_before_BasicAA.ll
  314. nvvm-annotations-D120129.ll
  315. nvvm-reflect-arch-O0.ll
  316. nvvm-reflect-arch.ll
  317. nvvm-reflect-module-flag.ll
  318. nvvm-reflect-ocl.ll
  319. nvvm-reflect-opaque.ll
  320. nvvm-reflect-options.ll
  321. nvvm-reflect.ll
  322. op-fence.ll
  323. packed-aggr.ll
  324. param-add.ll
  325. param-align.ll
  326. param-load-store.ll
  327. param-overalign.ll
  328. param-vectorize-device.ll
  329. param-vectorize-kernel.ll
  330. pass-name.ll
  331. pm-event.ll
  332. pow2_mask_cmp.ll
  333. pr126337.ll
  334. pr13291-i1-store.ll
  335. pr16278.ll
  336. pr17529.ll
  337. prefetch-inferas-test.ll
  338. prefetch.ll
  339. prmt-const-folding.ll
  340. prmt.ll
  341. proxy-reg-erasure-ptx.ll
  342. proxy-reg-erasure.mir
  343. rcp-opt.ll
  344. read-global-variable-constant.ll
  345. reduction-intrinsics.ll
  346. redux-sync-f32.ll
  347. redux-sync.ll
  348. refl1.ll
  349. reg-copy.ll
  350. reg-types.ll
  351. rotate-add.ll
  352. rotate.ll
  353. rotate_64.ll
  354. rsqrt-opt.ll
  355. rsqrt.ll
  356. sad-intrins.ll
  357. sched1.ll
  358. sched2.ll
  359. setmaxnreg-sm100a.ll
  360. setmaxnreg.ll
  361. sext-in-reg.ll
  362. sext-params.ll
  363. sext-setcc.ll
  364. shfl-p.ll
  365. shfl-sync-p.ll
  366. shfl-sync.ll
  367. shfl.ll
  368. shift-opt.ll
  369. shift-parts.ll
  370. short-ptr.ll
  371. shuffle-vec-undef-init.ll
  372. simple-call.ll
  373. sm-version.ll
  374. speculative-execution-divergent-target.ll
  375. sqrt-approx.ll
  376. st-addrspace.ll
  377. st-generic.ll
  378. st-param-imm.ll
  379. st_bulk.ll
  380. stacksaverestore.ll
  381. store-retval.ll
  382. store-undef.ll
  383. surf-read-cuda.ll
  384. surf-read.ll
  385. surf-tex.py
  386. surf-write-cuda.ll
  387. surf-write.ll
  388. switch-loop-header.mir
  389. switch.ll
  390. symbol-naming.ll
  391. szext.ll
  392. tag-invariant-loads.ll
  393. TailDuplication-convergent.ll
  394. tanhf.ll
  395. tcgen05-alloc.ll
  396. tcgen05-commit.ll
  397. tcgen05-cp.ll
  398. tcgen05-fence.ll
  399. tcgen05-ld.ll
  400. tcgen05-mma-block-scale-invalid.ll
  401. tcgen05-mma-block-scale-ptx88-aa.ll
  402. tcgen05-mma-block-scale-ptx88.ll
  403. tcgen05-mma-block-scale.ll
  404. tcgen05-mma-disable-output-lane-i8.ll
  405. tcgen05-mma-disable-output-lane.ll
  406. tcgen05-mma-i8.ll
  407. tcgen05-mma-invalid.ll
  408. tcgen05-mma-scale-d-invalid.ll
  409. tcgen05-mma-scale-d.ll
  410. tcgen05-mma-tensor-formatted.ll
  411. tcgen05-mma-ws-i8.ll
  412. tcgen05-mma-ws.ll
  413. tcgen05-mma.ll
  414. tcgen05-shift.ll
  415. tcgen05-st.ll
  416. tensormap_replace.ll
  417. tensormap_replace_invalid.ll
  418. tensormap_replace_sm_100a.ll
  419. tensormap_replace_sm_103a.ll
  420. tex-read-cuda.ll
  421. tex-read.ll
  422. texsurf-queries.ll
  423. thread-fence.ll
  424. tid-range.ll
  425. trunc-setcc.ll
  426. trunc-tofp.ll
  427. unaligned-param-load-store.ll
  428. unfold-masked-merge-vector-variablemask.ll
  429. unreachable.ll
  430. unrecognized-sm1x.ll
  431. upgrade-nvvm-annotations.ll
  432. used-bytes-mask.ll
  433. vaargs.ll
  434. variadics-backend.ll
  435. variadics-lowering.ll
  436. vec-param-load.ll
  437. vec8.ll
  438. vector-args.ll
  439. vector-call.ll
  440. vector-compare.ll
  441. vector-global.ll
  442. vector-loads.ll
  443. vector-returns.ll
  444. vector-select.ll
  445. vector-stores.ll
  446. vectorize-misaligned.ll
  447. vote.ll
  448. weak-global.ll
  449. weak-linkage.ll
  450. wgmma-sm90a-fence.ll
  451. wmma-ptx60-sm70.py
  452. wmma-ptx61-sm70.py
  453. wmma-ptx63-sm72.py
  454. wmma-ptx63-sm75.py
  455. wmma-ptx64-sm70.py
  456. wmma-ptx65-sm75.py
  457. wmma-ptx71-sm80.py
  458. wmma-ptx78-sm90.py
  459. wmma-ptx86-sm100a.py
  460. wmma-ptx86-sm101a.py
  461. wmma-ptx86-sm120a.py
  462. wmma-ptx87-sm120a.py
  463. wmma-ptx88-sm100f.py
  464. wmma-ptx88-sm120a.py
  465. wmma-ptx88-sm120f.py
  466. wmma-ptx90-sm110f.py
  467. wmma.py
  468. zeroext-32bit.ll