Google GitGoogle Git
Sign in
llvm/llvm-project/f1f5d9c88e9cba37ae033581be49d4ea202df24a/./llvm/test/CodeGen/NVPTX
tree: ce1f9e6a3828da3f8179fe16b1453f91023a3fd3
  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. arbitrary-fp-to-float.ll
  23. arg-lowering.ll
  24. arithmetic-fp-sm20.ll
  25. arithmetic-int.ll
  26. asm-printer-ptx-module-directives.ll
  27. async-copy.ll
  28. atomic-alignment.err.ll
  29. atomic-lower-local.ll
  30. atomicrmw-allow-ftz-atomics.ll
  31. atomicrmw-expand.err.ll
  32. atomicrmw-sm60.ll
  33. atomicrmw-sm70.ll
  34. atomicrmw-sm90.ll
  35. atomicrmw.py
  36. atomics-b128.ll
  37. atomics-sm60.ll
  38. atomics.ll
  39. b52037.ll
  40. barrier.ll
  41. bf16-instructions.ll
  42. bf16.ll
  43. bf16x2-instructions-approx.ll
  44. bf16x2-instructions.ll
  45. bfe.ll
  46. blocksareclusters-kernel-attr.ll
  47. bmsk.ll
  48. boolean-patterns.ll
  49. branch-fold.ll
  50. branch-fold.mir
  51. brkpt.ll
  52. bswap.ll
  53. bug17709.ll
  54. bug21465.ll
  55. bug22246.ll
  56. bug22322.ll
  57. bug26185-2.ll
  58. bug26185.ll
  59. bug41651.ll
  60. bug52623.ll
  61. bypass-div.ll
  62. byval-arg-vectorize.ll
  63. byval-const-global.ll
  64. call-with-alloca-buffer.ll
  65. call_bitcast_byval.ll
  66. callchain.ll
  67. calling-conv.ll
  68. calls-with-phi.ll
  69. chain-different-as.ll
  70. cluster-dim.ll
  71. clusterlaunchcontrol-multicast.ll
  72. clusterlaunchcontrol.ll
  73. cmpxchg-sm60.ll
  74. cmpxchg-sm70.ll
  75. cmpxchg-sm90.ll
  76. cmpxchg-unsupported-syncscope.err.ll
  77. cmpxchg.ll
  78. cmpxchg.py
  79. combine-mad.ll
  80. combine-min-max.ll
  81. combine-mul-wide-type.ll
  82. combine-wide.ll
  83. common-linkage.ll
  84. compare-int.ll
  85. compute-ptx-value-vts.ll
  86. constant-vectors.ll
  87. convergent-mir-call.ll
  88. convert-call-to-indirect.ll
  89. convert-fp-i8.ll
  90. convert-fp.ll
  91. convert-int-sm20.ll
  92. convert-sm100.ll
  93. convert-sm100a.ll
  94. convert-sm103a.ll
  95. convert-sm80-sf.ll
  96. convert-sm80.ll
  97. convert-sm89.ll
  98. convert-sm90.ll
  99. convert_fp4x2_sm_100f.ll
  100. convert_fp4x2_to_bf16x2.ll
  101. convert_fp6x2_sm_100f.ll
  102. convert_fp6x2_to_bf16x2.ll
  103. convert_fp8x2_sm_100f.ll
  104. convert_fp8x2_to_bf16x2.ll
  105. convert_s2f6x2_sm_100a.ll
  106. copysign.ll
  107. cp-async-bulk-ptx86.ll
  108. cp-async-bulk-s2g-sm100.ll
  109. cp-async-bulk-tensor-g2s-1cta.ll
  110. cp-async-bulk-tensor-g2s-2cta.ll
  111. cp-async-bulk-tensor-g2s-cta-sm100.ll
  112. cp-async-bulk-tensor-g2s-cta-sm100a.ll
  113. cp-async-bulk-tensor-g2s-cta-sm90.ll
  114. cp-async-bulk-tensor-g2s-gather4.ll
  115. cp-async-bulk-tensor-g2s-im2colw.ll
  116. cp-async-bulk-tensor-g2s-im2colw128.ll
  117. cp-async-bulk-tensor-g2s-invalid.ll
  118. cp-async-bulk-tensor-g2s.ll
  119. cp-async-bulk-tensor-prefetch-sm100a.ll
  120. cp-async-bulk-tensor-prefetch.ll
  121. cp-async-bulk-tensor-reduce.ll
  122. cp-async-bulk-tensor-s2g-scatter4.ll
  123. cp-async-bulk-tensor-s2g.ll
  124. cp-async-bulk.ll
  125. cse-mov-sym.ll
  126. ctlz.ll
  127. ctpop.ll
  128. cttz.ll
  129. dag-cse.ll
  130. dead-shfl.ll
  131. default-sm.ll
  132. demote-vars.ll
  133. disable-opt.ll
  134. discard.ll
  135. disjoint-or-addr.ll
  136. distributed-shared-cluster.ll
  137. div-ri.ll
  138. div.ll
  139. divrem-combine.ll
  140. dot-product.ll
  141. dynamic-stackalloc-regression.ll
  142. dynamic_stackalloc.ll
  143. elect.ll
  144. empty-type.ll
  145. envreg.ll
  146. extern-shared-valid-name.ll
  147. extloadv.ll
  148. extractelement.ll
  149. f16-abs.ll
  150. f16-add-sat.ll
  151. f16-ex2.ll
  152. f16-instructions.ll
  153. f16-mul-sat.ll
  154. f16-sub-sat.ll
  155. f16x2-instructions.ll
  156. f32-ex2.ll
  157. f32-lg2.ll
  158. f32x2-convert-i32x2.ll
  159. f32x2-instructions.ll
  160. fabs-intrinsics.ll
  161. fast-math.ll
  162. fcos-no-fast-math.ll
  163. fence-proxy-sm90-ptx86.ll
  164. fence-proxy-sm90.ll
  165. fence-proxy-tensormap-invalid.ll
  166. fence-proxy-tensormap.ll
  167. fence-proxy.ll
  168. fence.ll
  169. fence.py
  170. fexp2.ll
  171. filetype-null.ll
  172. flo.ll
  173. float-to-arbitrary-fp.ll
  174. flog2.ll
  175. fma-assoc.ll
  176. fma-disable.ll
  177. fma-oob.ll
  178. fma-relu-contract.ll
  179. fma-relu-fma-intrinsic.ll
  180. fma-relu-instruction-flag.ll
  181. fma.ll
  182. fmax3.ll
  183. fminimum-fmaximum.ll
  184. fns.ll
  185. fold-movs.ll
  186. forward-ld-param.ll
  187. fp-arith-sat.ll
  188. fp-contract-f32x2.ll
  189. fp-contract.ll
  190. fp-fold-sub.ll
  191. fp-literals.ll
  192. fp128-storage-type.ll
  193. frameindex-lifetime.ll
  194. frem.ll
  195. fsin-no-fast-math.ll
  196. function-align.ll
  197. funnel-shift-clamp.ll
  198. generic-to-nvvm-ir.ll
  199. generic-to-nvvm.ll
  200. global-addrspace.ll
  201. global-ctor-empty.ll
  202. global-incomplete-init.ll
  203. global-ordering.ll
  204. global-variable-big.ll
  205. global-visibility.ll
  206. globals_init.ll
  207. globals_lowering.ll
  208. griddepcontrol.ll
  209. gvar-init.ll
  210. gvn-scalar-pre-reg-pressure.ll
  211. half.ll
  212. i1-array-global.ll
  213. i1-ext-load.ll
  214. i1-global.ll
  215. i1-icmp.ll
  216. i1-int-to-fp.ll
  217. i1-load-lower.ll
  218. i1-param.ll
  219. i1-select.ll
  220. i128-array.ll
  221. i128-global.ll
  222. i128-ld-st.ll
  223. i128-param.ll
  224. i128-retval.ll
  225. i128-struct.ll
  226. i128.ll
  227. i16x2-instructions.ll
  228. i32x2-instructions.ll
  229. i8-param.ll
  230. i8x2-instructions.ll
  231. i8x4-instructions.ll
  232. idioms.ll
  233. imad.ll
  234. indirect_byval.ll
  235. inline-asm-b128-test1.ll
  236. inline-asm-b128-test2.ll
  237. inline-asm-b128-test3.ll
  238. inline-asm-line-info-inlined-at.ll
  239. inline-asm-line-info-per-instruction.ll
  240. inline-asm-line-number-before.ll
  241. inline-asm.ll
  242. inlineasm-output-template.ll
  243. insert-vector-elt-bitcast-legalize.ll
  244. insertelt-dynamic.ll
  245. intr-range.ll
  246. intrinsic-old.ll
  247. intrinsics-sm90-ptx81.ll
  248. intrinsics-sm90.ll
  249. intrinsics.ll
  250. isspacep.ll
  251. jump-table.ll
  252. kernel-param-align.ll
  253. ld-addrspace.ll
  254. ld-generic.ll
  255. ld-param-sink.ll
  256. ld-st-addrrspace.py
  257. ldg-invariant-256.ll
  258. ldg-invariant.ll
  259. ldparam-v4.ll
  260. ldu-i8.ll
  261. ldu-ldg.ll
  262. ldu-reg-plus-offset.ll
  263. lit.local.cfg
  264. load-sext-i1.ll
  265. load-store-256-addressing-invariant.ll
  266. load-store-256-addressing.ll
  267. load-store-atomic.err.ll
  268. load-store-scalars.ll
  269. load-store-sm-70.ll
  270. load-store-sm-90.ll
  271. load-store-vectors-256.ll
  272. load-store-vectors.ll
  273. load-with-non-coherent-cache.ll
  274. LoadStoreVectorizer.ll
  275. local-stack-frame.ll
  276. loop-vectorize.ll
  277. lower-aggr-copies-shared.ll
  278. lower-aggr-copies.ll
  279. lower-alloca.ll
  280. lower-args-alignment.ll
  281. lower-args-gridconstant.ll
  282. lower-args.ll
  283. lower-byval-args-dbg.ll
  284. lower-byval-args-idempotent.ll
  285. lower-byval-args.ll
  286. lower-ctor-dtor.ll
  287. lower-kernel-ptr-arg.ll
  288. machine-cse-predicate-inversion-multiple-users.ll
  289. machine-cse-predicate-inversion-rollback.mir
  290. machine-cse-predicate-inversion-vector-float.ll
  291. machine-cse-predicate-inversion.ll
  292. machine-cse-predicate-no-inversion.ll
  293. machine-sink.ll
  294. machinelicm-no-preheader.mir
  295. MachineSink-call.ll
  296. MachineSink-convergent.ll
  297. managed.ll
  298. mark-kernel-ptrs-global.ll
  299. masked-load-3xhalf.ll
  300. masked-load-vectors.ll
  301. masked-store-variable-mask.ll
  302. masked-store-vectors-256.ll
  303. match.ll
  304. math-intrins-sm53-ptx42.ll
  305. math-intrins-sm80-ptx70-autoupgrade.ll
  306. math-intrins-sm80-ptx70-instcombine.ll
  307. math-intrins-sm80-ptx70.ll
  308. math-intrins-sm86-ptx72-autoupgrade.ll
  309. math-intrins-sm86-ptx72.ll
  310. math-intrins.ll
  311. max-align.ll
  312. maxclusterrank.ll
  313. mbarrier.ll
  314. mbarrier_arr.ll
  315. mbarrier_arr_relaxed.ll
  316. mbarrier_tx.ll
  317. mbarrier_wait_sm80_ptx70.ll
  318. mbarrier_wait_sm80_ptx71.ll
  319. mbarrier_wait_sm90_ptx78.ll
  320. mbarrier_wait_sm90_ptx80.ll
  321. mbarrier_wait_sm90_ptx86.ll
  322. minmax-negative.ll
  323. misaligned-vector-ldst.ll
  324. misched_func_call.ll
  325. mixed-precision-fp.ll
  326. mma-no-sink-after-laneid-check.ll
  327. module-inline-asm.ll
  328. movmatrix.ll
  329. mulhi-intrins.ll
  330. mulwide.ll
  331. naked-fn-with-frame-pointer.ll
  332. nanosleep.ll
  333. no-extra-parens.ll
  334. no-f32x2.ll
  335. no-stack-protector-libcall-error.ll
  336. noduplicate-syncthreads.ll
  337. nofunc.ll
  338. noreturn.ll
  339. nounroll.ll
  340. nvcl-param-align.ll
  341. nvptx-aa-inline-asm.ll
  342. nvptx-aa.ll
  343. nvptx-fold-fma.ll
  344. nvptx-prec-divf32-flag.ll
  345. NVPTXAA_before_BasicAA.ll
  346. nvvm-abs.ll
  347. nvvm-annotations-D120129.ll
  348. nvvm-reflect-arch-O0.ll
  349. nvvm-reflect-arch.ll
  350. nvvm-reflect-module-flag.ll
  351. nvvm-reflect-ocl.ll
  352. nvvm-reflect-opaque.ll
  353. nvvm-reflect-options.ll
  354. nvvm-reflect.ll
  355. op-fence.ll
  356. packed-aggr.ll
  357. param-add.ll
  358. param-align.ll
  359. param-load-store.ll
  360. param-overalign.ll
  361. param-space-subqualifiers.ll
  362. param-vectorize-device.ll
  363. param-vectorize-kernel.ll
  364. pass-name.ll
  365. pm-event.ll
  366. pow2_mask_cmp.ll
  367. pr126337.ll
  368. pr13291-i1-store.ll
  369. pr16278.ll
  370. pr17529.ll
  371. prefetch-inferas-test.ll
  372. prefetch.ll
  373. prmt-const-folding.ll
  374. prmt.ll
  375. proxy-reg-erasure-ptx.ll
  376. proxy-reg-erasure.mir
  377. ptx-version-validation.ll
  378. rcp-opt.ll
  379. read-global-variable-constant.ll
  380. reduction-intrinsics.ll
  381. redux-sync-f32.ll
  382. redux-sync.ll
  383. refl1.ll
  384. reg-copy.ll
  385. reg-types.ll
  386. reqnctapercluster-const-fold.ll
  387. reqntid-const-fold.ll
  388. reserved-smem-offset.ll
  389. ret-align-mismatch.ll
  390. rotate-add.ll
  391. rotate.ll
  392. rotate_64.ll
  393. rsqrt-opt.ll
  394. rsqrt.ll
  395. sad-intrins.ll
  396. scalar-to-vector.ll
  397. scalarize-non-coalescable-v2f32.ll
  398. sched1.ll
  399. sched2.ll
  400. set-byval-param-align.ll
  401. setmaxnreg-sm100a.ll
  402. setmaxnreg.ll
  403. sext-in-reg.ll
  404. sext-params.ll
  405. sext-setcc.ll
  406. shfl-p.ll
  407. shfl-sync-p.ll
  408. shfl-sync.ll
  409. shfl.ll
  410. shift-opt.ll
  411. shift-parts.ll
  412. short-ptr.ll
  413. shuffle-vec-undef-init.ll
  414. simple-call.ll
  415. sm-version.ll
  416. speculative-execution-divergent-target.ll
  417. sqrt-approx.ll
  418. srl-bitcast-bv.ll
  419. st-addrspace.ll
  420. st-generic.ll
  421. st-param-imm.ll
  422. st_bulk.ll
  423. stackaddress.ll
  424. stacksaverestore.ll
  425. store-retval.ll
  426. store-undef.ll
  427. sub-byte-constant-vector-convert.ll
  428. sub-byte-constant-vectors-i4-i2.ll
  429. surf-read-cuda.ll
  430. surf-read.ll
  431. surf-tex.py
  432. surf-write-cuda.ll
  433. surf-write.ll
  434. switch-loop-header.mir
  435. switch.ll
  436. symbol-naming.ll
  437. szext.ll
  438. tag-invariant-loads.ll
  439. TailDuplication-convergent.ll
  440. tanhf.ll
  441. tcgen05-alloc.ll
  442. tcgen05-commit.ll
  443. tcgen05-cp.ll
  444. tcgen05-fence.ll
  445. tcgen05-ld-red.ll
  446. tcgen05-ld.ll
  447. tcgen05-mma-block-scale-invalid.ll
  448. tcgen05-mma-block-scale-ptx88-aa.ll
  449. tcgen05-mma-block-scale-ptx88.ll
  450. tcgen05-mma-block-scale.ll
  451. tcgen05-mma-disable-output-lane-i8.ll
  452. tcgen05-mma-disable-output-lane.ll
  453. tcgen05-mma-i8.ll
  454. tcgen05-mma-invalid.ll
  455. tcgen05-mma-scale-d-invalid.ll
  456. tcgen05-mma-scale-d.ll
  457. tcgen05-mma-tensor-formatted.ll
  458. tcgen05-mma-ws-i8.ll
  459. tcgen05-mma-ws.ll
  460. tcgen05-mma.ll
  461. tcgen05-shift.ll
  462. tcgen05-st.ll
  463. tensormap_replace.ll
  464. tensormap_replace_invalid.ll
  465. tensormap_replace_sm_100a.ll
  466. tensormap_replace_sm_103a.ll
  467. tex-read-cuda.ll
  468. tex-read.ll
  469. texsurf-queries.ll
  470. thread-fence.ll
  471. tid-range.ll
  472. trunc-setcc.ll
  473. trunc-tofp.ll
  474. unaligned-param-load-store.ll
  475. unfold-masked-merge-vector-variablemask.ll
  476. unknown-intrinsic.ll
  477. unreachable.ll
  478. unrecognized-sm1x.ll
  479. upgrade-nvvm-annotations.ll
  480. used-bytes-mask.ll
  481. vaargs.ll
  482. variadics-backend.ll
  483. variadics-lowering.ll
  484. vec-param-load.ll
  485. vec8.ll
  486. vector-args.ll
  487. vector-call.ll
  488. vector-compare.ll
  489. vector-global.ll
  490. vector-loads.ll
  491. vector-returns.ll
  492. vector-select.ll
  493. vector-stores.ll
  494. vectorize-misaligned.ll
  495. vote.ll
  496. weak-global.ll
  497. weak-linkage.ll
  498. wgmma-sm90a-fence.ll
  499. wmma-ptx60-sm70.py
  500. wmma-ptx61-sm70.py
  501. wmma-ptx63-sm72.py
  502. wmma-ptx63-sm75.py
  503. wmma-ptx64-sm70.py
  504. wmma-ptx65-sm75.py
  505. wmma-ptx71-sm80.py
  506. wmma-ptx78-sm90.py
  507. wmma-ptx86-sm100a.py
  508. wmma-ptx86-sm101a.py
  509. wmma-ptx87-sm120a.py
  510. wmma-ptx88-sm100f.py
  511. wmma-ptx88-sm120a.py
  512. wmma-ptx88-sm120f.py
  513. wmma-ptx90-sm110f.py
  514. wmma-ptx91-sm120a.py
  515. wmma-ptx91-sm120f.py
  516. wmma.py
  517. zeroext-32bit.ll