Google Git
Sign in
llvm/llvm-project/e14b11b74dcafea1e2a71b9788b85b34ab4cf1e6/./llvm/test/CodeGen/NVPTX
tree: b80fc0f820fef5119d7f5107aa93321b50c69299
  1. access-non-generic.ll
  2. activemask.ll
  3. add-sub-128bit.ll
  4. addr-mode.ll
  5. address-folder.ll
  6. address-folder.mir
  7. addrspacecast-cse.ll
  8. addrspacecast-folding.ll
  9. addrspacecast-gvar.ll
  10. addrspacecast-ptx64.ll
  11. addrspacecast.ll
  12. aggr-param.ll
  13. aggregate-return.ll
  14. alias-errors.ll
  15. alias.ll
  16. and-or-setcc.ll
  17. annotations.ll
  18. anonymous-fn-param.ll
  19. APIntLoadStore.ll
  20. APIntParam.ll
  21. APIntSextParam.ll
  22. APIntZextParam.ll
  23. applypriority.ll
  24. arbitrary-fp-to-float.ll
  25. arg-lowering.ll
  26. arithmetic-fp-sm20.ll
  27. arithmetic-int.ll
  28. asm-printer-ptx-module-directives.ll
  29. async-copy.ll
  30. atomic-alignment.err.ll
  31. atomic-lower-local.ll
  32. atomicrmw-allow-ftz-atomics.ll
  33. atomicrmw-expand.err.ll
  34. atomicrmw-sm60.ll
  35. atomicrmw-sm70.ll
  36. atomicrmw-sm90.ll
  37. atomicrmw.py
  38. atomics-b128.ll
  39. atomics-sm60.ll
  40. atomics.ll
  41. b52037.ll
  42. barrier.ll
  43. bf16-instructions.ll
  44. bf16-neg-noftz.ll
  45. bf16-setp-noftz.ll
  46. bf16.ll
  47. bf16x2-instructions-approx.ll
  48. bf16x2-instructions.ll
  49. bfe.ll
  50. blocksareclusters-kernel-attr.ll
  51. bmsk.ll
  52. boolean-patterns.ll
  53. branch-fold.ll
  54. branch-fold.mir
  55. brkpt.ll
  56. bswap.ll
  57. bug17709.ll
  58. bug21465.ll
  59. bug22246.ll
  60. bug22322.ll
  61. bug26185-2.ll
  62. bug26185.ll
  63. bug41651.ll
  64. bug52623.ll
  65. bypass-div.ll
  66. byval-arg-vectorize.ll
  67. byval-const-global.ll
  68. call-with-alloca-buffer.ll
  69. call_bitcast_byval.ll
  70. callchain.ll
  71. calling-conv.ll
  72. calls-with-phi.ll
  73. chain-different-as.ll
  74. cluster-dim.ll
  75. clusterlaunchcontrol-multicast.ll
  76. clusterlaunchcontrol.ll
  77. cmpxchg-sm60.ll
  78. cmpxchg-sm70.ll
  79. cmpxchg-sm90.ll
  80. cmpxchg-unsupported-syncscope.err.ll
  81. cmpxchg.ll
  82. cmpxchg.py
  83. combine-mad.ll
  84. combine-min-max.ll
  85. combine-mul-wide-type.ll
  86. combine-wide.ll
  87. common-linkage.ll
  88. compare-int.ll
  89. compute-ptx-value-vts.ll
  90. constant-vectors.ll
  91. convergent-mir-call.ll
  92. convert-call-to-indirect.ll
  93. convert-fp-i128.ll
  94. convert-fp-i8.ll
  95. convert-fp.ll
  96. convert-int-sm20.ll
  97. convert-sm100.ll
  98. convert-sm100a.ll
  99. convert-sm103a.ll
  100. convert-sm80-sf.ll
  101. convert-sm80.ll
  102. convert-sm89.ll
  103. convert-sm90.ll
  104. convert_fp4x2_sm_100f.ll
  105. convert_fp4x2_to_bf16x2.ll
  106. convert_fp6x2_sm_100f.ll
  107. convert_fp6x2_to_bf16x2.ll
  108. convert_fp8x2_sm_100f.ll
  109. convert_fp8x2_to_bf16x2.ll
  110. convert_s2f6x2_sm_100a.ll
  111. copysign.ll
  112. cp-async-bulk-ptx86.ll
  113. cp-async-bulk-s2g-sm100.ll
  114. cp-async-bulk-tensor-g2s-1cta.ll
  115. cp-async-bulk-tensor-g2s-2cta.ll
  116. cp-async-bulk-tensor-g2s-cta-sm100.ll
  117. cp-async-bulk-tensor-g2s-cta-sm100a.ll
  118. cp-async-bulk-tensor-g2s-cta-sm90.ll
  119. cp-async-bulk-tensor-g2s-gather4.ll
  120. cp-async-bulk-tensor-g2s-im2colw.ll
  121. cp-async-bulk-tensor-g2s-im2colw128.ll
  122. cp-async-bulk-tensor-g2s-invalid.ll
  123. cp-async-bulk-tensor-g2s.ll
  124. cp-async-bulk-tensor-prefetch-sm100a.ll
  125. cp-async-bulk-tensor-prefetch.ll
  126. cp-async-bulk-tensor-reduce.ll
  127. cp-async-bulk-tensor-s2g-scatter4.ll
  128. cp-async-bulk-tensor-s2g.ll
  129. cp-async-bulk.ll
  130. cse-mov-sym.ll
  131. ctlz.ll
  132. ctpop.ll
  133. cttz.ll
  134. dag-cse.ll
  135. dead-shfl.ll
  136. default-sm.ll
  137. demote-vars.ll
  138. disable-opt.ll
  139. discard.ll
  140. disjoint-or-addr.ll
  141. distributed-shared-cluster.ll
  142. div-ri.ll
  143. div.ll
  144. divrem-combine.ll
  145. dot-product.ll
  146. dynamic-stackalloc-regression.ll
  147. dynamic_stackalloc.ll
  148. elect.ll
  149. empty-type.ll
  150. envreg.ll
  151. extern-shared-valid-name.ll
  152. extloadv.ll
  153. extractelement.ll
  154. f16-abs.ll
  155. f16-add-sat.ll
  156. f16-ex2.ll
  157. f16-instructions.ll
  158. f16-mul-sat.ll
  159. f16-sub-sat.ll
  160. f16x2-instructions.ll
  161. f32-ex2.ll
  162. f32-lg2.ll
  163. f32x2-convert-i32x2.ll
  164. f32x2-instructions.ll
  165. fabs-intrinsics.ll
  166. fast-math.ll
  167. fcos-no-fast-math.ll
  168. fence-proxy-sm90-ptx86.ll
  169. fence-proxy-sm90.ll
  170. fence-proxy-tensormap-invalid.ll
  171. fence-proxy-tensormap.ll
  172. fence-proxy.ll
  173. fence.ll
  174. fence.py
  175. fexp2.ll
  176. filetype-null.ll
  177. flo.ll
  178. float-to-arbitrary-fp.ll
  179. flog2.ll
  180. fma-assoc.ll
  181. fma-disable.ll
  182. fma-oob.ll
  183. fma-relu-contract.ll
  184. fma-relu-fma-intrinsic.ll
  185. fma-relu-instruction-flag.ll
  186. fma.ll
  187. fmax3.ll
  188. fminimum-fmaximum.ll
  189. fns.ll
  190. fold-movs.ll
  191. forward-ld-param.ll
  192. fp-arith-sat.ll
  193. fp-contract-f32x2.ll
  194. fp-contract.ll
  195. fp-fold-sub.ll
  196. fp-literals.ll
  197. fp128-storage-type.ll
  198. frameindex-lifetime.ll
  199. frem.ll
  200. fsin-no-fast-math.ll
  201. function-align.ll
  202. funnel-shift-clamp.ll
  203. generic-to-nvvm-ir.ll
  204. generic-to-nvvm.ll
  205. global-addrspace.ll
  206. global-ctor-empty.ll
  207. global-incomplete-init.ll
  208. global-ordering.ll
  209. global-variable-big.ll
  210. global-visibility.ll
  211. globals_init.ll
  212. globals_lowering.ll
  213. griddepcontrol.ll
  214. gvar-init.ll
  215. gvn-scalar-pre-reg-pressure.ll
  216. half.ll
  217. i1-array-global.ll
  218. i1-ext-load.ll
  219. i1-global.ll
  220. i1-icmp.ll
  221. i1-int-to-fp.ll
  222. i1-load-lower.ll
  223. i1-param.ll
  224. i1-select.ll
  225. i128-array.ll
  226. i128-global.ll
  227. i128-ld-st.ll
  228. i128-param.ll
  229. i128-retval.ll
  230. i128-struct.ll
  231. i128.ll
  232. i16x2-instructions.ll
  233. i32x2-instructions.ll
  234. i8-param.ll
  235. i8x2-instructions.ll
  236. i8x4-instructions.ll
  237. idioms.ll
  238. imad.ll
  239. indirect_byval.ll
  240. inline-asm-b128-test1.ll
  241. inline-asm-b128-test2.ll
  242. inline-asm-b128-test3.ll
  243. inline-asm-line-info-inlined-at.ll
  244. inline-asm-line-info-per-instruction.ll
  245. inline-asm-line-number-before.ll
  246. inline-asm.ll
  247. inlineasm-output-template.ll
  248. insert-vector-elt-bitcast-legalize.ll
  249. insert-vector-elt-shuffle-i8.ll
  250. insertelt-dynamic.ll
  251. intr-range.ll
  252. intrinsic-immarg-print-mismatched-signature.ll
  253. intrinsic-old.ll
  254. intrinsics-sm90-ptx81.ll
  255. intrinsics-sm90.ll
  256. intrinsics.ll
  257. isspacep.ll
  258. jump-table.ll
  259. kernel-param-align.ll
  260. ld-addrspace.ll
  261. ld-generic.ll
  262. ld-param-sink.ll
  263. ld-st-addrrspace.py
  264. ldg-invariant-256.ll
  265. ldg-invariant.ll
  266. ldparam-v4.ll
  267. ldu-i8.ll
  268. ldu-ldg.ll
  269. ldu-reg-plus-offset.ll
  270. lit.local.cfg
  271. load-sext-i1.ll
  272. load-store-256-addressing-invariant.ll
  273. load-store-256-addressing.ll
  274. load-store-atomic.err.ll
  275. load-store-scalars.ll
  276. load-store-sm-70.ll
  277. load-store-sm-90.ll
  278. load-store-vectors-256.ll
  279. load-store-vectors.ll
  280. load-with-non-coherent-cache.ll
  281. LoadStoreVectorizer.ll
  282. local-stack-frame.ll
  283. loop-vectorize.ll
  284. lower-aggr-copies-shared.ll
  285. lower-aggr-copies.ll
  286. lower-alloca.ll
  287. lower-args-alignment.ll
  288. lower-args-gridconstant.ll
  289. lower-args.ll
  290. lower-byval-args-dbg.ll
  291. lower-byval-args-idempotent.ll
  292. lower-byval-args-mem-attrs.ll
  293. lower-byval-args.ll
  294. lower-ctor-dtor.ll
  295. lower-kernel-ptr-arg.ll
  296. machine-cse-predicate-inversion-multiple-users.ll
  297. machine-cse-predicate-inversion-rollback.mir
  298. machine-cse-predicate-inversion-vector-float.ll
  299. machine-cse-predicate-inversion.ll
  300. machine-cse-predicate-no-inversion.ll
  301. machine-sink.ll
  302. machinelicm-no-preheader.mir
  303. MachineSink-call.ll
  304. MachineSink-convergent.ll
  305. managed.ll
  306. mark-kernel-ptrs-global.ll
  307. masked-load-3xhalf.ll
  308. masked-load-vectors.ll
  309. masked-store-variable-mask.ll
  310. masked-store-vectors-256.ll
  311. match.ll
  312. math-intrins-sm53-ptx42.ll
  313. math-intrins-sm80-ptx70-autoupgrade.ll
  314. math-intrins-sm80-ptx70-instcombine.ll
  315. math-intrins-sm80-ptx70.ll
  316. math-intrins-sm86-ptx72-autoupgrade.ll
  317. math-intrins-sm86-ptx72.ll
  318. math-intrins.ll
  319. max-align.ll
  320. maxclusterrank.ll
  321. mbarrier.ll
  322. mbarrier_arr.ll
  323. mbarrier_arr_relaxed.ll
  324. mbarrier_tx.ll
  325. mbarrier_wait_sm80_ptx70.ll
  326. mbarrier_wait_sm80_ptx71.ll
  327. mbarrier_wait_sm90_ptx78.ll
  328. mbarrier_wait_sm90_ptx80.ll
  329. mbarrier_wait_sm90_ptx86.ll
  330. minmax-negative.ll
  331. misaligned-vector-ldst.ll
  332. misched_func_call.ll
  333. mixed-precision-fp.ll
  334. mma-no-sink-after-laneid-check.ll
  335. module-inline-asm.ll
  336. movmatrix.ll
  337. mulhi-intrins.ll
  338. mulwide.ll
  339. naked-fn-with-frame-pointer.ll
  340. nanosleep.ll
  341. no-extra-parens.ll
  342. no-f32x2.ll
  343. no-stack-protector-libcall-error.ll
  344. noduplicate-syncthreads.ll
  345. nofunc.ll
  346. noreturn.ll
  347. nounroll.ll
  348. nvcl-param-align.ll
  349. nvptx-aa-inline-asm.ll
  350. nvptx-aa.ll
  351. nvptx-fold-fma.ll
  352. nvptx-prec-divf32-flag.ll
  353. NVPTXAA_before_BasicAA.ll
  354. nvvm-abs.ll
  355. nvvm-annotations-D120129.ll
  356. nvvm-reflect-arch-O0.ll
  357. nvvm-reflect-arch.ll
  358. nvvm-reflect-module-flag.ll
  359. nvvm-reflect-ocl.ll
  360. nvvm-reflect-opaque.ll
  361. nvvm-reflect-options.ll
  362. nvvm-reflect.ll
  363. op-fence.ll
  364. packed-aggr.ll
  365. param-add.ll
  366. param-align.ll
  367. param-load-store.ll
  368. param-overalign.ll
  369. param-space-subqualifiers.ll
  370. param-vectorize-device.ll
  371. param-vectorize-kernel.ll
  372. pass-name.ll
  373. pm-event.ll
  374. pow2_mask_cmp.ll
  375. pr126337.ll
  376. pr13291-i1-store.ll
  377. pr16278.ll
  378. pr17529.ll
  379. prefetch-inferas-test.ll
  380. prefetch.ll
  381. prmt-const-folding.ll
  382. prmt.ll
  383. promote-param-align.ll
  384. proxy-reg-erasure-kill-flag.mir
  385. proxy-reg-erasure-ptx.ll
  386. proxy-reg-erasure.mir
  387. ptx-version-validation.ll
  388. rcp-opt.ll
  389. read-global-variable-constant.ll
  390. reduction-intrinsics.ll
  391. redux-sync-f32.ll
  392. redux-sync.ll
  393. refl1.ll
  394. reg-copy.ll
  395. reg-types.ll
  396. reqnctapercluster-const-fold.ll
  397. reqntid-const-fold.ll
  398. reserved-smem-offset.ll
  399. ret-align-mismatch.ll
  400. rotate-add.ll
  401. rotate.ll
  402. rotate_64.ll
  403. rsqrt-opt.ll
  404. rsqrt.ll
  405. sad-intrins.ll
  406. scalar-to-vector.ll
  407. scalarize-non-coalescable-v2f32.ll
  408. sched1.ll
  409. sched2.ll
  410. setmaxnreg-sm100a.ll
  411. setmaxnreg.ll
  412. sext-in-reg.ll
  413. sext-params.ll
  414. sext-setcc.ll
  415. shfl-p.ll
  416. shfl-sync-p.ll
  417. shfl-sync.ll
  418. shfl.ll
  419. shift-opt.ll
  420. shift-parts.ll
  421. short-ptr.ll
  422. shuffle-vec-undef-init.ll
  423. simple-call.ll
  424. sm-version.ll
  425. speculative-execution-divergent-target.ll
  426. sqrt-approx.ll
  427. srl-bitcast-bv.ll
  428. st-addrspace.ll
  429. st-generic.ll
  430. st-param-imm.ll
  431. st_async_mbarrier.ll
  432. st_async_mbarrier_b128.ll
  433. st_async_release.ll
  434. st_async_release_multimem.ll
  435. st_bulk.ll
  436. stackaddress.ll
  437. stacksaverestore.ll
  438. store-retval.ll
  439. store-undef.ll
  440. sub-byte-constant-vector-convert.ll
  441. sub-byte-constant-vectors-i4-i2.ll
  442. surf-read-cuda.ll
  443. surf-read.ll
  444. surf-tex.py
  445. surf-write-cuda.ll
  446. surf-write.ll
  447. switch-loop-header.mir
  448. switch.ll
  449. symbol-naming.ll
  450. szext.ll
  451. tag-invariant-loads.ll
  452. TailDuplication-convergent.ll
  453. tanhf.ll
  454. tcgen05-alloc.ll
  455. tcgen05-commit.ll
  456. tcgen05-cp.ll
  457. tcgen05-fence.ll
  458. tcgen05-ld-red.ll
  459. tcgen05-ld.ll
  460. tcgen05-mma-block-scale-invalid.ll
  461. tcgen05-mma-block-scale-ptx88-aa.ll
  462. tcgen05-mma-block-scale-ptx88.ll
  463. tcgen05-mma-block-scale.ll
  464. tcgen05-mma-disable-output-lane-i8.ll
  465. tcgen05-mma-disable-output-lane.ll
  466. tcgen05-mma-i8.ll
  467. tcgen05-mma-invalid.ll
  468. tcgen05-mma-scale-d-invalid.ll
  469. tcgen05-mma-scale-d.ll
  470. tcgen05-mma-tensor-formatted.ll
  471. tcgen05-mma-ws-i8.ll
  472. tcgen05-mma-ws.ll
  473. tcgen05-mma.ll
  474. tcgen05-shift.ll
  475. tcgen05-st.ll
  476. tensormap_replace.ll
  477. tensormap_replace_invalid.ll
  478. tensormap_replace_sm_100a.ll
  479. tensormap_replace_sm_103a.ll
  480. tex-read-cuda.ll
  481. tex-read.ll
  482. texsurf-queries.ll
  483. thread-fence.ll
  484. tid-range.ll
  485. trunc-setcc.ll
  486. trunc-tofp.ll
  487. unaligned-param-load-store.ll
  488. unfold-masked-merge-vector-variablemask.ll
  489. unknown-intrinsic.ll
  490. unreachable.ll
  491. unrecognized-sm1x.ll
  492. upgrade-nvvm-annotations.ll
  493. used-bytes-mask.ll
  494. vaargs.ll
  495. variadics-backend.ll
  496. variadics-lowering.ll
  497. vec-param-load.ll
  498. vec8.ll
  499. vector-args.ll
  500. vector-call.ll
  501. vector-compare.ll
  502. vector-global.ll
  503. vector-loads.ll
  504. vector-returns.ll
  505. vector-select.ll
  506. vector-stores.ll
  507. vectorize-misaligned.ll
  508. vote.ll
  509. weak-global.ll
  510. weak-linkage.ll
  511. wgmma-sm90a-fence.ll
  512. wmma-ptx60-sm70.py
  513. wmma-ptx61-sm70.py
  514. wmma-ptx63-sm72.py
  515. wmma-ptx63-sm75.py
  516. wmma-ptx64-sm70.py
  517. wmma-ptx65-sm75.py
  518. wmma-ptx71-sm80.py
  519. wmma-ptx78-sm90.py
  520. wmma-ptx86-sm100a.py
  521. wmma-ptx86-sm101a.py
  522. wmma-ptx87-sm120a.py
  523. wmma-ptx88-sm100f.py
  524. wmma-ptx88-sm120a.py
  525. wmma-ptx88-sm120f.py
  526. wmma-ptx90-sm110f.py
  527. wmma-ptx91-sm120a.py
  528. wmma-ptx91-sm120f.py
  529. wmma.py
  530. zeroext-32bit.ll