1 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mcpu=corei7 -mattr=avx | FileCheck %s
3 define <2 x i64> @test_x86_aesni_aesdec(<2 x i64> %a0, <2 x i64> %a1) {
5 %res = call <2 x i64> @llvm.x86.aesni.aesdec(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
8 declare <2 x i64> @llvm.x86.aesni.aesdec(<2 x i64>, <2 x i64>) nounwind readnone
11 define <2 x i64> @test_x86_aesni_aesdeclast(<2 x i64> %a0, <2 x i64> %a1) {
13 %res = call <2 x i64> @llvm.x86.aesni.aesdeclast(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
16 declare <2 x i64> @llvm.x86.aesni.aesdeclast(<2 x i64>, <2 x i64>) nounwind readnone
19 define <2 x i64> @test_x86_aesni_aesenc(<2 x i64> %a0, <2 x i64> %a1) {
21 %res = call <2 x i64> @llvm.x86.aesni.aesenc(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
24 declare <2 x i64> @llvm.x86.aesni.aesenc(<2 x i64>, <2 x i64>) nounwind readnone
27 define <2 x i64> @test_x86_aesni_aesenclast(<2 x i64> %a0, <2 x i64> %a1) {
29 %res = call <2 x i64> @llvm.x86.aesni.aesenclast(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
32 declare <2 x i64> @llvm.x86.aesni.aesenclast(<2 x i64>, <2 x i64>) nounwind readnone
35 define <2 x i64> @test_x86_aesni_aesimc(<2 x i64> %a0) {
37 %res = call <2 x i64> @llvm.x86.aesni.aesimc(<2 x i64> %a0) ; <<2 x i64>> [#uses=1]
40 declare <2 x i64> @llvm.x86.aesni.aesimc(<2 x i64>) nounwind readnone
43 define <2 x i64> @test_x86_aesni_aeskeygenassist(<2 x i64> %a0) {
44 ; CHECK: vaeskeygenassist
45 %res = call <2 x i64> @llvm.x86.aesni.aeskeygenassist(<2 x i64> %a0, i8 7) ; <<2 x i64>> [#uses=1]
48 declare <2 x i64> @llvm.x86.aesni.aeskeygenassist(<2 x i64>, i8) nounwind readnone
51 define <2 x double> @test_x86_sse2_add_sd(<2 x double> %a0, <2 x double> %a1) {
53 %res = call <2 x double> @llvm.x86.sse2.add.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
56 declare <2 x double> @llvm.x86.sse2.add.sd(<2 x double>, <2 x double>) nounwind readnone
59 define <2 x double> @test_x86_sse2_cmp_pd(<2 x double> %a0, <2 x double> %a1) {
61 %res = call <2 x double> @llvm.x86.sse2.cmp.pd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
64 declare <2 x double> @llvm.x86.sse2.cmp.pd(<2 x double>, <2 x double>, i8) nounwind readnone
67 define <2 x double> @test_x86_sse2_cmp_sd(<2 x double> %a0, <2 x double> %a1) {
69 %res = call <2 x double> @llvm.x86.sse2.cmp.sd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
72 declare <2 x double> @llvm.x86.sse2.cmp.sd(<2 x double>, <2 x double>, i8) nounwind readnone
75 define i32 @test_x86_sse2_comieq_sd(<2 x double> %a0, <2 x double> %a1) {
79 %res = call i32 @llvm.x86.sse2.comieq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
82 declare i32 @llvm.x86.sse2.comieq.sd(<2 x double>, <2 x double>) nounwind readnone
85 define i32 @test_x86_sse2_comige_sd(<2 x double> %a0, <2 x double> %a1) {
89 %res = call i32 @llvm.x86.sse2.comige.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
92 declare i32 @llvm.x86.sse2.comige.sd(<2 x double>, <2 x double>) nounwind readnone
95 define i32 @test_x86_sse2_comigt_sd(<2 x double> %a0, <2 x double> %a1) {
99 %res = call i32 @llvm.x86.sse2.comigt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
102 declare i32 @llvm.x86.sse2.comigt.sd(<2 x double>, <2 x double>) nounwind readnone
105 define i32 @test_x86_sse2_comile_sd(<2 x double> %a0, <2 x double> %a1) {
109 %res = call i32 @llvm.x86.sse2.comile.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
112 declare i32 @llvm.x86.sse2.comile.sd(<2 x double>, <2 x double>) nounwind readnone
115 define i32 @test_x86_sse2_comilt_sd(<2 x double> %a0, <2 x double> %a1) {
119 %res = call i32 @llvm.x86.sse2.comilt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
122 declare i32 @llvm.x86.sse2.comilt.sd(<2 x double>, <2 x double>) nounwind readnone
125 define i32 @test_x86_sse2_comineq_sd(<2 x double> %a0, <2 x double> %a1) {
129 %res = call i32 @llvm.x86.sse2.comineq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
132 declare i32 @llvm.x86.sse2.comineq.sd(<2 x double>, <2 x double>) nounwind readnone
135 define <2 x double> @test_x86_sse2_cvtdq2pd(<4 x i32> %a0) {
137 %res = call <2 x double> @llvm.x86.sse2.cvtdq2pd(<4 x i32> %a0) ; <<2 x double>> [#uses=1]
138 ret <2 x double> %res
140 declare <2 x double> @llvm.x86.sse2.cvtdq2pd(<4 x i32>) nounwind readnone
143 define <4 x float> @test_x86_sse2_cvtdq2ps(<4 x i32> %a0) {
145 %res = call <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32> %a0) ; <<4 x float>> [#uses=1]
148 declare <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32>) nounwind readnone
151 define <4 x i32> @test_x86_sse2_cvtpd2dq(<2 x double> %a0) {
153 %res = call <4 x i32> @llvm.x86.sse2.cvtpd2dq(<2 x double> %a0) ; <<4 x i32>> [#uses=1]
156 declare <4 x i32> @llvm.x86.sse2.cvtpd2dq(<2 x double>) nounwind readnone
159 define <4 x float> @test_x86_sse2_cvtpd2ps(<2 x double> %a0) {
161 %res = call <4 x float> @llvm.x86.sse2.cvtpd2ps(<2 x double> %a0) ; <<4 x float>> [#uses=1]
164 declare <4 x float> @llvm.x86.sse2.cvtpd2ps(<2 x double>) nounwind readnone
167 define <4 x i32> @test_x86_sse2_cvtps2dq(<4 x float> %a0) {
169 %res = call <4 x i32> @llvm.x86.sse2.cvtps2dq(<4 x float> %a0) ; <<4 x i32>> [#uses=1]
172 declare <4 x i32> @llvm.x86.sse2.cvtps2dq(<4 x float>) nounwind readnone
175 define <2 x double> @test_x86_sse2_cvtps2pd(<4 x float> %a0) {
177 %res = call <2 x double> @llvm.x86.sse2.cvtps2pd(<4 x float> %a0) ; <<2 x double>> [#uses=1]
178 ret <2 x double> %res
180 declare <2 x double> @llvm.x86.sse2.cvtps2pd(<4 x float>) nounwind readnone
183 define i32 @test_x86_sse2_cvtsd2si(<2 x double> %a0) {
185 %res = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> %a0) ; <i32> [#uses=1]
188 declare i32 @llvm.x86.sse2.cvtsd2si(<2 x double>) nounwind readnone
191 define <4 x float> @test_x86_sse2_cvtsd2ss(<4 x float> %a0, <2 x double> %a1) {
193 %res = call <4 x float> @llvm.x86.sse2.cvtsd2ss(<4 x float> %a0, <2 x double> %a1) ; <<4 x float>> [#uses=1]
196 declare <4 x float> @llvm.x86.sse2.cvtsd2ss(<4 x float>, <2 x double>) nounwind readnone
199 define <2 x double> @test_x86_sse2_cvtsi2sd(<2 x double> %a0) {
202 %res = call <2 x double> @llvm.x86.sse2.cvtsi2sd(<2 x double> %a0, i32 7) ; <<2 x double>> [#uses=1]
203 ret <2 x double> %res
205 declare <2 x double> @llvm.x86.sse2.cvtsi2sd(<2 x double>, i32) nounwind readnone
208 define <2 x double> @test_x86_sse2_cvtss2sd(<2 x double> %a0, <4 x float> %a1) {
210 %res = call <2 x double> @llvm.x86.sse2.cvtss2sd(<2 x double> %a0, <4 x float> %a1) ; <<2 x double>> [#uses=1]
211 ret <2 x double> %res
213 declare <2 x double> @llvm.x86.sse2.cvtss2sd(<2 x double>, <4 x float>) nounwind readnone
216 define <4 x i32> @test_x86_sse2_cvttpd2dq(<2 x double> %a0) {
218 %res = call <4 x i32> @llvm.x86.sse2.cvttpd2dq(<2 x double> %a0) ; <<4 x i32>> [#uses=1]
221 declare <4 x i32> @llvm.x86.sse2.cvttpd2dq(<2 x double>) nounwind readnone
224 define <4 x i32> @test_x86_sse2_cvttps2dq(<4 x float> %a0) {
226 %res = call <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float> %a0) ; <<4 x i32>> [#uses=1]
229 declare <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float>) nounwind readnone
232 define i32 @test_x86_sse2_cvttsd2si(<2 x double> %a0) {
234 %res = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> %a0) ; <i32> [#uses=1]
237 declare i32 @llvm.x86.sse2.cvttsd2si(<2 x double>) nounwind readnone
240 define <2 x double> @test_x86_sse2_div_sd(<2 x double> %a0, <2 x double> %a1) {
242 %res = call <2 x double> @llvm.x86.sse2.div.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
243 ret <2 x double> %res
245 declare <2 x double> @llvm.x86.sse2.div.sd(<2 x double>, <2 x double>) nounwind readnone
248 define <16 x i8> @test_x86_sse2_loadu_dq(i8* %a0) {
251 %res = call <16 x i8> @llvm.x86.sse2.loadu.dq(i8* %a0) ; <<16 x i8>> [#uses=1]
254 declare <16 x i8> @llvm.x86.sse2.loadu.dq(i8*) nounwind readonly
257 define <2 x double> @test_x86_sse2_loadu_pd(i8* %a0) {
260 %res = call <2 x double> @llvm.x86.sse2.loadu.pd(i8* %a0) ; <<2 x double>> [#uses=1]
261 ret <2 x double> %res
263 declare <2 x double> @llvm.x86.sse2.loadu.pd(i8*) nounwind readonly
266 define void @test_x86_sse2_maskmov_dqu(<16 x i8> %a0, <16 x i8> %a1, i8* %a2) {
271 call void @llvm.x86.sse2.maskmov.dqu(<16 x i8> %a0, <16 x i8> %a1, i8* %a2)
274 declare void @llvm.x86.sse2.maskmov.dqu(<16 x i8>, <16 x i8>, i8*) nounwind
277 define <2 x double> @test_x86_sse2_max_pd(<2 x double> %a0, <2 x double> %a1) {
279 %res = call <2 x double> @llvm.x86.sse2.max.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
280 ret <2 x double> %res
282 declare <2 x double> @llvm.x86.sse2.max.pd(<2 x double>, <2 x double>) nounwind readnone
285 define <2 x double> @test_x86_sse2_max_sd(<2 x double> %a0, <2 x double> %a1) {
287 %res = call <2 x double> @llvm.x86.sse2.max.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
288 ret <2 x double> %res
290 declare <2 x double> @llvm.x86.sse2.max.sd(<2 x double>, <2 x double>) nounwind readnone
293 define <2 x double> @test_x86_sse2_min_pd(<2 x double> %a0, <2 x double> %a1) {
295 %res = call <2 x double> @llvm.x86.sse2.min.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
296 ret <2 x double> %res
298 declare <2 x double> @llvm.x86.sse2.min.pd(<2 x double>, <2 x double>) nounwind readnone
301 define <2 x double> @test_x86_sse2_min_sd(<2 x double> %a0, <2 x double> %a1) {
303 %res = call <2 x double> @llvm.x86.sse2.min.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
304 ret <2 x double> %res
306 declare <2 x double> @llvm.x86.sse2.min.sd(<2 x double>, <2 x double>) nounwind readnone
309 define i32 @test_x86_sse2_movmsk_pd(<2 x double> %a0) {
311 %res = call i32 @llvm.x86.sse2.movmsk.pd(<2 x double> %a0) ; <i32> [#uses=1]
314 declare i32 @llvm.x86.sse2.movmsk.pd(<2 x double>) nounwind readnone
317 define void @test_x86_sse2_movnt_dq(i8* %a0, <2 x i64> %a1) {
320 call void @llvm.x86.sse2.movnt.dq(i8* %a0, <2 x i64> %a1)
323 declare void @llvm.x86.sse2.movnt.dq(i8*, <2 x i64>) nounwind
326 define void @test_x86_sse2_movnt_pd(i8* %a0, <2 x double> %a1) {
329 call void @llvm.x86.sse2.movnt.pd(i8* %a0, <2 x double> %a1)
332 declare void @llvm.x86.sse2.movnt.pd(i8*, <2 x double>) nounwind
335 define <2 x double> @test_x86_sse2_mul_sd(<2 x double> %a0, <2 x double> %a1) {
337 %res = call <2 x double> @llvm.x86.sse2.mul.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
338 ret <2 x double> %res
340 declare <2 x double> @llvm.x86.sse2.mul.sd(<2 x double>, <2 x double>) nounwind readnone
343 define <8 x i16> @test_x86_sse2_packssdw_128(<4 x i32> %a0, <4 x i32> %a1) {
345 %res = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a0, <4 x i32> %a1) ; <<8 x i16>> [#uses=1]
348 declare <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32>, <4 x i32>) nounwind readnone
351 define <16 x i8> @test_x86_sse2_packsswb_128(<8 x i16> %a0, <8 x i16> %a1) {
353 %res = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a0, <8 x i16> %a1) ; <<16 x i8>> [#uses=1]
356 declare <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16>, <8 x i16>) nounwind readnone
359 define <16 x i8> @test_x86_sse2_packuswb_128(<8 x i16> %a0, <8 x i16> %a1) {
361 %res = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a0, <8 x i16> %a1) ; <<16 x i8>> [#uses=1]
364 declare <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16>, <8 x i16>) nounwind readnone
367 define <16 x i8> @test_x86_sse2_padds_b(<16 x i8> %a0, <16 x i8> %a1) {
369 %res = call <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
372 declare <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8>, <16 x i8>) nounwind readnone
375 define <8 x i16> @test_x86_sse2_padds_w(<8 x i16> %a0, <8 x i16> %a1) {
377 %res = call <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
380 declare <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16>, <8 x i16>) nounwind readnone
383 define <16 x i8> @test_x86_sse2_paddus_b(<16 x i8> %a0, <16 x i8> %a1) {
385 %res = call <16 x i8> @llvm.x86.sse2.paddus.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
388 declare <16 x i8> @llvm.x86.sse2.paddus.b(<16 x i8>, <16 x i8>) nounwind readnone
391 define <8 x i16> @test_x86_sse2_paddus_w(<8 x i16> %a0, <8 x i16> %a1) {
393 %res = call <8 x i16> @llvm.x86.sse2.paddus.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
396 declare <8 x i16> @llvm.x86.sse2.paddus.w(<8 x i16>, <8 x i16>) nounwind readnone
399 define <16 x i8> @test_x86_sse2_pavg_b(<16 x i8> %a0, <16 x i8> %a1) {
401 %res = call <16 x i8> @llvm.x86.sse2.pavg.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
404 declare <16 x i8> @llvm.x86.sse2.pavg.b(<16 x i8>, <16 x i8>) nounwind readnone
407 define <8 x i16> @test_x86_sse2_pavg_w(<8 x i16> %a0, <8 x i16> %a1) {
409 %res = call <8 x i16> @llvm.x86.sse2.pavg.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
412 declare <8 x i16> @llvm.x86.sse2.pavg.w(<8 x i16>, <8 x i16>) nounwind readnone
415 define <16 x i8> @test_x86_sse2_pcmpeq_b(<16 x i8> %a0, <16 x i8> %a1) {
417 %res = call <16 x i8> @llvm.x86.sse2.pcmpeq.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
420 declare <16 x i8> @llvm.x86.sse2.pcmpeq.b(<16 x i8>, <16 x i8>) nounwind readnone
423 define <4 x i32> @test_x86_sse2_pcmpeq_d(<4 x i32> %a0, <4 x i32> %a1) {
425 %res = call <4 x i32> @llvm.x86.sse2.pcmpeq.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
428 declare <4 x i32> @llvm.x86.sse2.pcmpeq.d(<4 x i32>, <4 x i32>) nounwind readnone
431 define <8 x i16> @test_x86_sse2_pcmpeq_w(<8 x i16> %a0, <8 x i16> %a1) {
433 %res = call <8 x i16> @llvm.x86.sse2.pcmpeq.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
436 declare <8 x i16> @llvm.x86.sse2.pcmpeq.w(<8 x i16>, <8 x i16>) nounwind readnone
439 define <16 x i8> @test_x86_sse2_pcmpgt_b(<16 x i8> %a0, <16 x i8> %a1) {
441 %res = call <16 x i8> @llvm.x86.sse2.pcmpgt.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
444 declare <16 x i8> @llvm.x86.sse2.pcmpgt.b(<16 x i8>, <16 x i8>) nounwind readnone
447 define <4 x i32> @test_x86_sse2_pcmpgt_d(<4 x i32> %a0, <4 x i32> %a1) {
449 %res = call <4 x i32> @llvm.x86.sse2.pcmpgt.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
452 declare <4 x i32> @llvm.x86.sse2.pcmpgt.d(<4 x i32>, <4 x i32>) nounwind readnone
455 define <8 x i16> @test_x86_sse2_pcmpgt_w(<8 x i16> %a0, <8 x i16> %a1) {
457 %res = call <8 x i16> @llvm.x86.sse2.pcmpgt.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
460 declare <8 x i16> @llvm.x86.sse2.pcmpgt.w(<8 x i16>, <8 x i16>) nounwind readnone
463 define <4 x i32> @test_x86_sse2_pmadd_wd(<8 x i16> %a0, <8 x i16> %a1) {
465 %res = call <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16> %a0, <8 x i16> %a1) ; <<4 x i32>> [#uses=1]
468 declare <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16>, <8 x i16>) nounwind readnone
471 define <8 x i16> @test_x86_sse2_pmaxs_w(<8 x i16> %a0, <8 x i16> %a1) {
473 %res = call <8 x i16> @llvm.x86.sse2.pmaxs.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
476 declare <8 x i16> @llvm.x86.sse2.pmaxs.w(<8 x i16>, <8 x i16>) nounwind readnone
479 define <16 x i8> @test_x86_sse2_pmaxu_b(<16 x i8> %a0, <16 x i8> %a1) {
481 %res = call <16 x i8> @llvm.x86.sse2.pmaxu.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
484 declare <16 x i8> @llvm.x86.sse2.pmaxu.b(<16 x i8>, <16 x i8>) nounwind readnone
487 define <8 x i16> @test_x86_sse2_pmins_w(<8 x i16> %a0, <8 x i16> %a1) {
489 %res = call <8 x i16> @llvm.x86.sse2.pmins.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
492 declare <8 x i16> @llvm.x86.sse2.pmins.w(<8 x i16>, <8 x i16>) nounwind readnone
495 define <16 x i8> @test_x86_sse2_pminu_b(<16 x i8> %a0, <16 x i8> %a1) {
497 %res = call <16 x i8> @llvm.x86.sse2.pminu.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
500 declare <16 x i8> @llvm.x86.sse2.pminu.b(<16 x i8>, <16 x i8>) nounwind readnone
503 define i32 @test_x86_sse2_pmovmskb_128(<16 x i8> %a0) {
505 %res = call i32 @llvm.x86.sse2.pmovmskb.128(<16 x i8> %a0) ; <i32> [#uses=1]
508 declare i32 @llvm.x86.sse2.pmovmskb.128(<16 x i8>) nounwind readnone
511 define <8 x i16> @test_x86_sse2_pmulh_w(<8 x i16> %a0, <8 x i16> %a1) {
513 %res = call <8 x i16> @llvm.x86.sse2.pmulh.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
516 declare <8 x i16> @llvm.x86.sse2.pmulh.w(<8 x i16>, <8 x i16>) nounwind readnone
519 define <8 x i16> @test_x86_sse2_pmulhu_w(<8 x i16> %a0, <8 x i16> %a1) {
521 %res = call <8 x i16> @llvm.x86.sse2.pmulhu.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
524 declare <8 x i16> @llvm.x86.sse2.pmulhu.w(<8 x i16>, <8 x i16>) nounwind readnone
527 define <2 x i64> @test_x86_sse2_pmulu_dq(<4 x i32> %a0, <4 x i32> %a1) {
529 %res = call <2 x i64> @llvm.x86.sse2.pmulu.dq(<4 x i32> %a0, <4 x i32> %a1) ; <<2 x i64>> [#uses=1]
532 declare <2 x i64> @llvm.x86.sse2.pmulu.dq(<4 x i32>, <4 x i32>) nounwind readnone
535 define <2 x i64> @test_x86_sse2_psad_bw(<16 x i8> %a0, <16 x i8> %a1) {
537 %res = call <2 x i64> @llvm.x86.sse2.psad.bw(<16 x i8> %a0, <16 x i8> %a1) ; <<2 x i64>> [#uses=1]
540 declare <2 x i64> @llvm.x86.sse2.psad.bw(<16 x i8>, <16 x i8>) nounwind readnone
543 define <4 x i32> @test_x86_sse2_psll_d(<4 x i32> %a0, <4 x i32> %a1) {
545 %res = call <4 x i32> @llvm.x86.sse2.psll.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
548 declare <4 x i32> @llvm.x86.sse2.psll.d(<4 x i32>, <4 x i32>) nounwind readnone
551 define <2 x i64> @test_x86_sse2_psll_dq(<2 x i64> %a0) {
553 %res = call <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
556 declare <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64>, i32) nounwind readnone
559 define <2 x i64> @test_x86_sse2_psll_dq_bs(<2 x i64> %a0) {
561 %res = call <2 x i64> @llvm.x86.sse2.psll.dq.bs(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
564 declare <2 x i64> @llvm.x86.sse2.psll.dq.bs(<2 x i64>, i32) nounwind readnone
567 define <2 x i64> @test_x86_sse2_psll_q(<2 x i64> %a0, <2 x i64> %a1) {
569 %res = call <2 x i64> @llvm.x86.sse2.psll.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
572 declare <2 x i64> @llvm.x86.sse2.psll.q(<2 x i64>, <2 x i64>) nounwind readnone
575 define <8 x i16> @test_x86_sse2_psll_w(<8 x i16> %a0, <8 x i16> %a1) {
577 %res = call <8 x i16> @llvm.x86.sse2.psll.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
580 declare <8 x i16> @llvm.x86.sse2.psll.w(<8 x i16>, <8 x i16>) nounwind readnone
583 define <4 x i32> @test_x86_sse2_pslli_d(<4 x i32> %a0) {
585 %res = call <4 x i32> @llvm.x86.sse2.pslli.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
588 declare <4 x i32> @llvm.x86.sse2.pslli.d(<4 x i32>, i32) nounwind readnone
591 define <2 x i64> @test_x86_sse2_pslli_q(<2 x i64> %a0) {
593 %res = call <2 x i64> @llvm.x86.sse2.pslli.q(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
596 declare <2 x i64> @llvm.x86.sse2.pslli.q(<2 x i64>, i32) nounwind readnone
599 define <8 x i16> @test_x86_sse2_pslli_w(<8 x i16> %a0) {
601 %res = call <8 x i16> @llvm.x86.sse2.pslli.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
604 declare <8 x i16> @llvm.x86.sse2.pslli.w(<8 x i16>, i32) nounwind readnone
607 define <4 x i32> @test_x86_sse2_psra_d(<4 x i32> %a0, <4 x i32> %a1) {
609 %res = call <4 x i32> @llvm.x86.sse2.psra.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
612 declare <4 x i32> @llvm.x86.sse2.psra.d(<4 x i32>, <4 x i32>) nounwind readnone
615 define <8 x i16> @test_x86_sse2_psra_w(<8 x i16> %a0, <8 x i16> %a1) {
617 %res = call <8 x i16> @llvm.x86.sse2.psra.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
620 declare <8 x i16> @llvm.x86.sse2.psra.w(<8 x i16>, <8 x i16>) nounwind readnone
623 define <4 x i32> @test_x86_sse2_psrai_d(<4 x i32> %a0) {
625 %res = call <4 x i32> @llvm.x86.sse2.psrai.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
628 declare <4 x i32> @llvm.x86.sse2.psrai.d(<4 x i32>, i32) nounwind readnone
631 define <8 x i16> @test_x86_sse2_psrai_w(<8 x i16> %a0) {
633 %res = call <8 x i16> @llvm.x86.sse2.psrai.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
636 declare <8 x i16> @llvm.x86.sse2.psrai.w(<8 x i16>, i32) nounwind readnone
639 define <4 x i32> @test_x86_sse2_psrl_d(<4 x i32> %a0, <4 x i32> %a1) {
641 %res = call <4 x i32> @llvm.x86.sse2.psrl.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
644 declare <4 x i32> @llvm.x86.sse2.psrl.d(<4 x i32>, <4 x i32>) nounwind readnone
647 define <2 x i64> @test_x86_sse2_psrl_dq(<2 x i64> %a0) {
649 %res = call <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
652 declare <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64>, i32) nounwind readnone
655 define <2 x i64> @test_x86_sse2_psrl_dq_bs(<2 x i64> %a0) {
657 %res = call <2 x i64> @llvm.x86.sse2.psrl.dq.bs(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
660 declare <2 x i64> @llvm.x86.sse2.psrl.dq.bs(<2 x i64>, i32) nounwind readnone
663 define <2 x i64> @test_x86_sse2_psrl_q(<2 x i64> %a0, <2 x i64> %a1) {
665 %res = call <2 x i64> @llvm.x86.sse2.psrl.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
668 declare <2 x i64> @llvm.x86.sse2.psrl.q(<2 x i64>, <2 x i64>) nounwind readnone
671 define <8 x i16> @test_x86_sse2_psrl_w(<8 x i16> %a0, <8 x i16> %a1) {
673 %res = call <8 x i16> @llvm.x86.sse2.psrl.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
676 declare <8 x i16> @llvm.x86.sse2.psrl.w(<8 x i16>, <8 x i16>) nounwind readnone
679 define <4 x i32> @test_x86_sse2_psrli_d(<4 x i32> %a0) {
681 %res = call <4 x i32> @llvm.x86.sse2.psrli.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
684 declare <4 x i32> @llvm.x86.sse2.psrli.d(<4 x i32>, i32) nounwind readnone
687 define <2 x i64> @test_x86_sse2_psrli_q(<2 x i64> %a0) {
689 %res = call <2 x i64> @llvm.x86.sse2.psrli.q(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
692 declare <2 x i64> @llvm.x86.sse2.psrli.q(<2 x i64>, i32) nounwind readnone
695 define <8 x i16> @test_x86_sse2_psrli_w(<8 x i16> %a0) {
697 %res = call <8 x i16> @llvm.x86.sse2.psrli.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
700 declare <8 x i16> @llvm.x86.sse2.psrli.w(<8 x i16>, i32) nounwind readnone
703 define <16 x i8> @test_x86_sse2_psubs_b(<16 x i8> %a0, <16 x i8> %a1) {
705 %res = call <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
708 declare <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8>, <16 x i8>) nounwind readnone
711 define <8 x i16> @test_x86_sse2_psubs_w(<8 x i16> %a0, <8 x i16> %a1) {
713 %res = call <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
716 declare <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16>, <8 x i16>) nounwind readnone
719 define <16 x i8> @test_x86_sse2_psubus_b(<16 x i8> %a0, <16 x i8> %a1) {
721 %res = call <16 x i8> @llvm.x86.sse2.psubus.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
724 declare <16 x i8> @llvm.x86.sse2.psubus.b(<16 x i8>, <16 x i8>) nounwind readnone
727 define <8 x i16> @test_x86_sse2_psubus_w(<8 x i16> %a0, <8 x i16> %a1) {
729 %res = call <8 x i16> @llvm.x86.sse2.psubus.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
732 declare <8 x i16> @llvm.x86.sse2.psubus.w(<8 x i16>, <8 x i16>) nounwind readnone
735 define <2 x double> @test_x86_sse2_sqrt_pd(<2 x double> %a0) {
737 %res = call <2 x double> @llvm.x86.sse2.sqrt.pd(<2 x double> %a0) ; <<2 x double>> [#uses=1]
738 ret <2 x double> %res
740 declare <2 x double> @llvm.x86.sse2.sqrt.pd(<2 x double>) nounwind readnone
743 define <2 x double> @test_x86_sse2_sqrt_sd(<2 x double> %a0) {
745 %res = call <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double> %a0) ; <<2 x double>> [#uses=1]
746 ret <2 x double> %res
748 declare <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double>) nounwind readnone
751 define void @test_x86_sse2_storel_dq(i8* %a0, <4 x i32> %a1) {
754 call void @llvm.x86.sse2.storel.dq(i8* %a0, <4 x i32> %a1)
757 declare void @llvm.x86.sse2.storel.dq(i8*, <4 x i32>) nounwind
760 define void @test_x86_sse2_storeu_dq(i8* %a0, <16 x i8> %a1) {
763 call void @llvm.x86.sse2.storeu.dq(i8* %a0, <16 x i8> %a1)
766 declare void @llvm.x86.sse2.storeu.dq(i8*, <16 x i8>) nounwind
769 define void @test_x86_sse2_storeu_pd(i8* %a0, <2 x double> %a1) {
772 call void @llvm.x86.sse2.storeu.pd(i8* %a0, <2 x double> %a1)
775 declare void @llvm.x86.sse2.storeu.pd(i8*, <2 x double>) nounwind
778 define <2 x double> @test_x86_sse2_sub_sd(<2 x double> %a0, <2 x double> %a1) {
780 %res = call <2 x double> @llvm.x86.sse2.sub.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
781 ret <2 x double> %res
783 declare <2 x double> @llvm.x86.sse2.sub.sd(<2 x double>, <2 x double>) nounwind readnone
786 define i32 @test_x86_sse2_ucomieq_sd(<2 x double> %a0, <2 x double> %a1) {
790 %res = call i32 @llvm.x86.sse2.ucomieq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
793 declare i32 @llvm.x86.sse2.ucomieq.sd(<2 x double>, <2 x double>) nounwind readnone
796 define i32 @test_x86_sse2_ucomige_sd(<2 x double> %a0, <2 x double> %a1) {
800 %res = call i32 @llvm.x86.sse2.ucomige.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
803 declare i32 @llvm.x86.sse2.ucomige.sd(<2 x double>, <2 x double>) nounwind readnone
806 define i32 @test_x86_sse2_ucomigt_sd(<2 x double> %a0, <2 x double> %a1) {
810 %res = call i32 @llvm.x86.sse2.ucomigt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
813 declare i32 @llvm.x86.sse2.ucomigt.sd(<2 x double>, <2 x double>) nounwind readnone
816 define i32 @test_x86_sse2_ucomile_sd(<2 x double> %a0, <2 x double> %a1) {
820 %res = call i32 @llvm.x86.sse2.ucomile.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
823 declare i32 @llvm.x86.sse2.ucomile.sd(<2 x double>, <2 x double>) nounwind readnone
826 define i32 @test_x86_sse2_ucomilt_sd(<2 x double> %a0, <2 x double> %a1) {
830 %res = call i32 @llvm.x86.sse2.ucomilt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
833 declare i32 @llvm.x86.sse2.ucomilt.sd(<2 x double>, <2 x double>) nounwind readnone
836 define i32 @test_x86_sse2_ucomineq_sd(<2 x double> %a0, <2 x double> %a1) {
840 %res = call i32 @llvm.x86.sse2.ucomineq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
843 declare i32 @llvm.x86.sse2.ucomineq.sd(<2 x double>, <2 x double>) nounwind readnone
846 define <2 x double> @test_x86_sse3_addsub_pd(<2 x double> %a0, <2 x double> %a1) {
848 %res = call <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
849 ret <2 x double> %res
851 declare <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double>, <2 x double>) nounwind readnone
854 define <4 x float> @test_x86_sse3_addsub_ps(<4 x float> %a0, <4 x float> %a1) {
856 %res = call <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
859 declare <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float>, <4 x float>) nounwind readnone
862 define <2 x double> @test_x86_sse3_hadd_pd(<2 x double> %a0, <2 x double> %a1) {
864 %res = call <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
865 ret <2 x double> %res
867 declare <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double>, <2 x double>) nounwind readnone
870 define <4 x float> @test_x86_sse3_hadd_ps(<4 x float> %a0, <4 x float> %a1) {
872 %res = call <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
875 declare <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float>, <4 x float>) nounwind readnone
878 define <2 x double> @test_x86_sse3_hsub_pd(<2 x double> %a0, <2 x double> %a1) {
880 %res = call <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
881 ret <2 x double> %res
883 declare <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double>, <2 x double>) nounwind readnone
886 define <4 x float> @test_x86_sse3_hsub_ps(<4 x float> %a0, <4 x float> %a1) {
888 %res = call <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
891 declare <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float>, <4 x float>) nounwind readnone
894 define <16 x i8> @test_x86_sse3_ldu_dq(i8* %a0) {
897 %res = call <16 x i8> @llvm.x86.sse3.ldu.dq(i8* %a0) ; <<16 x i8>> [#uses=1]
900 declare <16 x i8> @llvm.x86.sse3.ldu.dq(i8*) nounwind readonly
903 define <2 x double> @test_x86_sse41_blendpd(<2 x double> %a0, <2 x double> %a1) {
905 %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
906 ret <2 x double> %res
908 declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i32) nounwind readnone
911 define <4 x float> @test_x86_sse41_blendps(<4 x float> %a0, <4 x float> %a1) {
913 %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
916 declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i32) nounwind readnone
919 define <2 x double> @test_x86_sse41_blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2) {
921 %res = call <2 x double> @llvm.x86.sse41.blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2) ; <<2 x double>> [#uses=1]
922 ret <2 x double> %res
924 declare <2 x double> @llvm.x86.sse41.blendvpd(<2 x double>, <2 x double>, <2 x double>) nounwind readnone
927 define <4 x float> @test_x86_sse41_blendvps(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2) {
929 %res = call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2) ; <<4 x float>> [#uses=1]
932 declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x float>) nounwind readnone
935 define <2 x double> @test_x86_sse41_dppd(<2 x double> %a0, <2 x double> %a1) {
937 %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
938 ret <2 x double> %res
940 declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i32) nounwind readnone
943 define <4 x float> @test_x86_sse41_dpps(<4 x float> %a0, <4 x float> %a1) {
945 %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
948 declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i32) nounwind readnone
951 define <4 x float> @test_x86_sse41_insertps(<4 x float> %a0, <4 x float> %a1) {
953 %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
956 declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone
959 define <2 x i64> @test_x86_sse41_movntdqa(i8* %a0) {
962 %res = call <2 x i64> @llvm.x86.sse41.movntdqa(i8* %a0) ; <<2 x i64>> [#uses=1]
965 declare <2 x i64> @llvm.x86.sse41.movntdqa(i8*) nounwind readonly
968 define <16 x i8> @test_x86_sse41_mpsadbw(<16 x i8> %a0, <16 x i8> %a1) {
970 %res = call <16 x i8> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i32 7) ; <<16 x i8>> [#uses=1]
973 declare <16 x i8> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i32) nounwind readnone
976 define <8 x i16> @test_x86_sse41_packusdw(<4 x i32> %a0, <4 x i32> %a1) {
978 %res = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a0, <4 x i32> %a1) ; <<8 x i16>> [#uses=1]
981 declare <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32>, <4 x i32>) nounwind readnone
984 define <16 x i8> @test_x86_sse41_pblendvb(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> %a2) {
986 %res = call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> %a2) ; <<16 x i8>> [#uses=1]
989 declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone
992 define <8 x i16> @test_x86_sse41_pblendw(<8 x i16> %a0, <8 x i16> %a1) {
994 %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i32 7) ; <<8 x i16>> [#uses=1]
997 declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i32) nounwind readnone
1000 define <2 x i64> @test_x86_sse41_pcmpeqq(<2 x i64> %a0, <2 x i64> %a1) {
1002 %res = call <2 x i64> @llvm.x86.sse41.pcmpeqq(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
1005 declare <2 x i64> @llvm.x86.sse41.pcmpeqq(<2 x i64>, <2 x i64>) nounwind readnone
1008 define <8 x i16> @test_x86_sse41_phminposuw(<8 x i16> %a0) {
1009 ; CHECK: vphminposuw
1010 %res = call <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
1013 declare <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16>) nounwind readnone
1016 define <16 x i8> @test_x86_sse41_pmaxsb(<16 x i8> %a0, <16 x i8> %a1) {
1018 %res = call <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1021 declare <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8>, <16 x i8>) nounwind readnone
1024 define <4 x i32> @test_x86_sse41_pmaxsd(<4 x i32> %a0, <4 x i32> %a1) {
1026 %res = call <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1029 declare <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32>, <4 x i32>) nounwind readnone
1032 define <4 x i32> @test_x86_sse41_pmaxud(<4 x i32> %a0, <4 x i32> %a1) {
1034 %res = call <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1037 declare <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32>, <4 x i32>) nounwind readnone
1040 define <8 x i16> @test_x86_sse41_pmaxuw(<8 x i16> %a0, <8 x i16> %a1) {
1042 %res = call <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1045 declare <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16>, <8 x i16>) nounwind readnone
1048 define <16 x i8> @test_x86_sse41_pminsb(<16 x i8> %a0, <16 x i8> %a1) {
1050 %res = call <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1053 declare <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8>, <16 x i8>) nounwind readnone
1056 define <4 x i32> @test_x86_sse41_pminsd(<4 x i32> %a0, <4 x i32> %a1) {
1058 %res = call <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1061 declare <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32>, <4 x i32>) nounwind readnone
1064 define <4 x i32> @test_x86_sse41_pminud(<4 x i32> %a0, <4 x i32> %a1) {
1066 %res = call <4 x i32> @llvm.x86.sse41.pminud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1069 declare <4 x i32> @llvm.x86.sse41.pminud(<4 x i32>, <4 x i32>) nounwind readnone
1072 define <8 x i16> @test_x86_sse41_pminuw(<8 x i16> %a0, <8 x i16> %a1) {
1074 %res = call <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1077 declare <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16>, <8 x i16>) nounwind readnone
1080 define <4 x i32> @test_x86_sse41_pmovsxbd(<16 x i8> %a0) {
1082 %res = call <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
1085 declare <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8>) nounwind readnone
1088 define <2 x i64> @test_x86_sse41_pmovsxbq(<16 x i8> %a0) {
1090 %res = call <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
1093 declare <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8>) nounwind readnone
1096 define <8 x i16> @test_x86_sse41_pmovsxbw(<16 x i8> %a0) {
1098 %res = call <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
1101 declare <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8>) nounwind readnone
1104 define <2 x i64> @test_x86_sse41_pmovsxdq(<4 x i32> %a0) {
1106 %res = call <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
1109 declare <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32>) nounwind readnone
1112 define <4 x i32> @test_x86_sse41_pmovsxwd(<8 x i16> %a0) {
1114 %res = call <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
1117 declare <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16>) nounwind readnone
1120 define <2 x i64> @test_x86_sse41_pmovsxwq(<8 x i16> %a0) {
1122 %res = call <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
1125 declare <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16>) nounwind readnone
1128 define <4 x i32> @test_x86_sse41_pmovzxbd(<16 x i8> %a0) {
1130 %res = call <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
1133 declare <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8>) nounwind readnone
1136 define <2 x i64> @test_x86_sse41_pmovzxbq(<16 x i8> %a0) {
1138 %res = call <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
1141 declare <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8>) nounwind readnone
1144 define <8 x i16> @test_x86_sse41_pmovzxbw(<16 x i8> %a0) {
1146 %res = call <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
1149 declare <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8>) nounwind readnone
1152 define <2 x i64> @test_x86_sse41_pmovzxdq(<4 x i32> %a0) {
1154 %res = call <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
1157 declare <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32>) nounwind readnone
1160 define <4 x i32> @test_x86_sse41_pmovzxwd(<8 x i16> %a0) {
1162 %res = call <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
1165 declare <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16>) nounwind readnone
1168 define <2 x i64> @test_x86_sse41_pmovzxwq(<8 x i16> %a0) {
1170 %res = call <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
1173 declare <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16>) nounwind readnone
1176 define <2 x i64> @test_x86_sse41_pmuldq(<4 x i32> %a0, <4 x i32> %a1) {
1178 %res = call <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32> %a0, <4 x i32> %a1) ; <<2 x i64>> [#uses=1]
1181 declare <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32>, <4 x i32>) nounwind readnone
1184 define i32 @test_x86_sse41_ptestc(<4 x float> %a0, <4 x float> %a1) {
1188 %res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1191 declare i32 @llvm.x86.sse41.ptestc(<4 x float>, <4 x float>) nounwind readnone
1194 define i32 @test_x86_sse41_ptestnzc(<4 x float> %a0, <4 x float> %a1) {
1198 %res = call i32 @llvm.x86.sse41.ptestnzc(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1201 declare i32 @llvm.x86.sse41.ptestnzc(<4 x float>, <4 x float>) nounwind readnone
1204 define i32 @test_x86_sse41_ptestz(<4 x float> %a0, <4 x float> %a1) {
1208 %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1211 declare i32 @llvm.x86.sse41.ptestz(<4 x float>, <4 x float>) nounwind readnone
1214 define <2 x double> @test_x86_sse41_round_pd(<2 x double> %a0) {
1216 %res = call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %a0, i32 7) ; <<2 x double>> [#uses=1]
1217 ret <2 x double> %res
1219 declare <2 x double> @llvm.x86.sse41.round.pd(<2 x double>, i32) nounwind readnone
1222 define <4 x float> @test_x86_sse41_round_ps(<4 x float> %a0) {
1224 %res = call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %a0, i32 7) ; <<4 x float>> [#uses=1]
1225 ret <4 x float> %res
1227 declare <4 x float> @llvm.x86.sse41.round.ps(<4 x float>, i32) nounwind readnone
1230 define <2 x double> @test_x86_sse41_round_sd(<2 x double> %a0, <2 x double> %a1) {
1232 %res = call <2 x double> @llvm.x86.sse41.round.sd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
1233 ret <2 x double> %res
1235 declare <2 x double> @llvm.x86.sse41.round.sd(<2 x double>, <2 x double>, i32) nounwind readnone
1238 define <4 x float> @test_x86_sse41_round_ss(<4 x float> %a0, <4 x float> %a1) {
1240 %res = call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
1241 ret <4 x float> %res
1243 declare <4 x float> @llvm.x86.sse41.round.ss(<4 x float>, <4 x float>, i32) nounwind readnone
1246 define i32 @test_x86_sse42_pcmpestri128(<16 x i8> %a0, <16 x i8> %a2) {
1251 %res = call i32 @llvm.x86.sse42.pcmpestri128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1254 declare i32 @llvm.x86.sse42.pcmpestri128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1257 define i32 @test_x86_sse42_pcmpestria128(<16 x i8> %a0, <16 x i8> %a2) {
1262 %res = call i32 @llvm.x86.sse42.pcmpestria128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1265 declare i32 @llvm.x86.sse42.pcmpestria128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1268 define i32 @test_x86_sse42_pcmpestric128(<16 x i8> %a0, <16 x i8> %a2) {
1273 %res = call i32 @llvm.x86.sse42.pcmpestric128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1276 declare i32 @llvm.x86.sse42.pcmpestric128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1279 define i32 @test_x86_sse42_pcmpestrio128(<16 x i8> %a0, <16 x i8> %a2) {
1284 %res = call i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1287 declare i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1290 define i32 @test_x86_sse42_pcmpestris128(<16 x i8> %a0, <16 x i8> %a2) {
1295 %res = call i32 @llvm.x86.sse42.pcmpestris128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1298 declare i32 @llvm.x86.sse42.pcmpestris128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1301 define i32 @test_x86_sse42_pcmpestriz128(<16 x i8> %a0, <16 x i8> %a2) {
1306 %res = call i32 @llvm.x86.sse42.pcmpestriz128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1309 declare i32 @llvm.x86.sse42.pcmpestriz128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1312 define <16 x i8> @test_x86_sse42_pcmpestrm128(<16 x i8> %a0, <16 x i8> %a2) {
1316 %res = call <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <<16 x i8>> [#uses=1]
1319 declare <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1322 define <2 x i64> @test_x86_sse42_pcmpgtq(<2 x i64> %a0, <2 x i64> %a1) {
1324 %res = call <2 x i64> @llvm.x86.sse42.pcmpgtq(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
1327 declare <2 x i64> @llvm.x86.sse42.pcmpgtq(<2 x i64>, <2 x i64>) nounwind readnone
1330 define i32 @test_x86_sse42_pcmpistri128(<16 x i8> %a0, <16 x i8> %a1) {
1333 %res = call i32 @llvm.x86.sse42.pcmpistri128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1336 declare i32 @llvm.x86.sse42.pcmpistri128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1339 define i32 @test_x86_sse42_pcmpistria128(<16 x i8> %a0, <16 x i8> %a1) {
1342 %res = call i32 @llvm.x86.sse42.pcmpistria128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1345 declare i32 @llvm.x86.sse42.pcmpistria128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1348 define i32 @test_x86_sse42_pcmpistric128(<16 x i8> %a0, <16 x i8> %a1) {
1351 %res = call i32 @llvm.x86.sse42.pcmpistric128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1354 declare i32 @llvm.x86.sse42.pcmpistric128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1357 define i32 @test_x86_sse42_pcmpistrio128(<16 x i8> %a0, <16 x i8> %a1) {
1360 %res = call i32 @llvm.x86.sse42.pcmpistrio128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1363 declare i32 @llvm.x86.sse42.pcmpistrio128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1366 define i32 @test_x86_sse42_pcmpistris128(<16 x i8> %a0, <16 x i8> %a1) {
1369 %res = call i32 @llvm.x86.sse42.pcmpistris128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1372 declare i32 @llvm.x86.sse42.pcmpistris128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1375 define i32 @test_x86_sse42_pcmpistriz128(<16 x i8> %a0, <16 x i8> %a1) {
1378 %res = call i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1381 declare i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1384 define <16 x i8> @test_x86_sse42_pcmpistrm128(<16 x i8> %a0, <16 x i8> %a1) {
1386 %res = call <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <<16 x i8>> [#uses=1]
1389 declare <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1392 define <4 x float> @test_x86_sse_add_ss(<4 x float> %a0, <4 x float> %a1) {
1394 %res = call <4 x float> @llvm.x86.sse.add.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1395 ret <4 x float> %res
1397 declare <4 x float> @llvm.x86.sse.add.ss(<4 x float>, <4 x float>) nounwind readnone
1400 define <4 x float> @test_x86_sse_cmp_ps(<4 x float> %a0, <4 x float> %a1) {
1402 %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
1403 ret <4 x float> %res
1405 declare <4 x float> @llvm.x86.sse.cmp.ps(<4 x float>, <4 x float>, i8) nounwind readnone
1408 define <4 x float> @test_x86_sse_cmp_ss(<4 x float> %a0, <4 x float> %a1) {
1410 %res = call <4 x float> @llvm.x86.sse.cmp.ss(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
1411 ret <4 x float> %res
1413 declare <4 x float> @llvm.x86.sse.cmp.ss(<4 x float>, <4 x float>, i8) nounwind readnone
1416 define i32 @test_x86_sse_comieq_ss(<4 x float> %a0, <4 x float> %a1) {
1420 %res = call i32 @llvm.x86.sse.comieq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1423 declare i32 @llvm.x86.sse.comieq.ss(<4 x float>, <4 x float>) nounwind readnone
1426 define i32 @test_x86_sse_comige_ss(<4 x float> %a0, <4 x float> %a1) {
1430 %res = call i32 @llvm.x86.sse.comige.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1433 declare i32 @llvm.x86.sse.comige.ss(<4 x float>, <4 x float>) nounwind readnone
1436 define i32 @test_x86_sse_comigt_ss(<4 x float> %a0, <4 x float> %a1) {
1440 %res = call i32 @llvm.x86.sse.comigt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1443 declare i32 @llvm.x86.sse.comigt.ss(<4 x float>, <4 x float>) nounwind readnone
1446 define i32 @test_x86_sse_comile_ss(<4 x float> %a0, <4 x float> %a1) {
1450 %res = call i32 @llvm.x86.sse.comile.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1453 declare i32 @llvm.x86.sse.comile.ss(<4 x float>, <4 x float>) nounwind readnone
1456 define i32 @test_x86_sse_comilt_ss(<4 x float> %a0, <4 x float> %a1) {
1460 %res = call i32 @llvm.x86.sse.comilt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1463 declare i32 @llvm.x86.sse.comilt.ss(<4 x float>, <4 x float>) nounwind readnone
1466 define i32 @test_x86_sse_comineq_ss(<4 x float> %a0, <4 x float> %a1) {
1470 %res = call i32 @llvm.x86.sse.comineq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1473 declare i32 @llvm.x86.sse.comineq.ss(<4 x float>, <4 x float>) nounwind readnone
1476 define <4 x float> @test_x86_sse_cvtsi2ss(<4 x float> %a0) {
1479 %res = call <4 x float> @llvm.x86.sse.cvtsi2ss(<4 x float> %a0, i32 7) ; <<4 x float>> [#uses=1]
1480 ret <4 x float> %res
1482 declare <4 x float> @llvm.x86.sse.cvtsi2ss(<4 x float>, i32) nounwind readnone
1485 define i32 @test_x86_sse_cvtss2si(<4 x float> %a0) {
1487 %res = call i32 @llvm.x86.sse.cvtss2si(<4 x float> %a0) ; <i32> [#uses=1]
1490 declare i32 @llvm.x86.sse.cvtss2si(<4 x float>) nounwind readnone
1493 define i32 @test_x86_sse_cvttss2si(<4 x float> %a0) {
1495 %res = call i32 @llvm.x86.sse.cvttss2si(<4 x float> %a0) ; <i32> [#uses=1]
1498 declare i32 @llvm.x86.sse.cvttss2si(<4 x float>) nounwind readnone
1501 define <4 x float> @test_x86_sse_div_ss(<4 x float> %a0, <4 x float> %a1) {
1503 %res = call <4 x float> @llvm.x86.sse.div.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1504 ret <4 x float> %res
1506 declare <4 x float> @llvm.x86.sse.div.ss(<4 x float>, <4 x float>) nounwind readnone
1509 define void @test_x86_sse_ldmxcsr(i8* %a0) {
1512 call void @llvm.x86.sse.ldmxcsr(i8* %a0)
1515 declare void @llvm.x86.sse.ldmxcsr(i8*) nounwind
1518 define <4 x float> @test_x86_sse_loadu_ps(i8* %a0) {
1521 %res = call <4 x float> @llvm.x86.sse.loadu.ps(i8* %a0) ; <<4 x float>> [#uses=1]
1522 ret <4 x float> %res
1524 declare <4 x float> @llvm.x86.sse.loadu.ps(i8*) nounwind readonly
1527 define <4 x float> @test_x86_sse_max_ps(<4 x float> %a0, <4 x float> %a1) {
1529 %res = call <4 x float> @llvm.x86.sse.max.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1530 ret <4 x float> %res
1532 declare <4 x float> @llvm.x86.sse.max.ps(<4 x float>, <4 x float>) nounwind readnone
1535 define <4 x float> @test_x86_sse_max_ss(<4 x float> %a0, <4 x float> %a1) {
1537 %res = call <4 x float> @llvm.x86.sse.max.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1538 ret <4 x float> %res
1540 declare <4 x float> @llvm.x86.sse.max.ss(<4 x float>, <4 x float>) nounwind readnone
1543 define <4 x float> @test_x86_sse_min_ps(<4 x float> %a0, <4 x float> %a1) {
1545 %res = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1546 ret <4 x float> %res
1548 declare <4 x float> @llvm.x86.sse.min.ps(<4 x float>, <4 x float>) nounwind readnone
1551 define <4 x float> @test_x86_sse_min_ss(<4 x float> %a0, <4 x float> %a1) {
1553 %res = call <4 x float> @llvm.x86.sse.min.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1554 ret <4 x float> %res
1556 declare <4 x float> @llvm.x86.sse.min.ss(<4 x float>, <4 x float>) nounwind readnone
1559 define i32 @test_x86_sse_movmsk_ps(<4 x float> %a0) {
1561 %res = call i32 @llvm.x86.sse.movmsk.ps(<4 x float> %a0) ; <i32> [#uses=1]
1564 declare i32 @llvm.x86.sse.movmsk.ps(<4 x float>) nounwind readnone
1567 define void @test_x86_sse_movnt_ps(i8* %a0, <4 x float> %a1) {
1570 call void @llvm.x86.sse.movnt.ps(i8* %a0, <4 x float> %a1)
1573 declare void @llvm.x86.sse.movnt.ps(i8*, <4 x float>) nounwind
1576 define <4 x float> @test_x86_sse_mul_ss(<4 x float> %a0, <4 x float> %a1) {
1578 %res = call <4 x float> @llvm.x86.sse.mul.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1579 ret <4 x float> %res
1581 declare <4 x float> @llvm.x86.sse.mul.ss(<4 x float>, <4 x float>) nounwind readnone
1584 define <4 x float> @test_x86_sse_rcp_ps(<4 x float> %a0) {
1586 %res = call <4 x float> @llvm.x86.sse.rcp.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1587 ret <4 x float> %res
1589 declare <4 x float> @llvm.x86.sse.rcp.ps(<4 x float>) nounwind readnone
1592 define <4 x float> @test_x86_sse_rcp_ss(<4 x float> %a0) {
1594 %res = call <4 x float> @llvm.x86.sse.rcp.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1595 ret <4 x float> %res
1597 declare <4 x float> @llvm.x86.sse.rcp.ss(<4 x float>) nounwind readnone
1600 define <4 x float> @test_x86_sse_rsqrt_ps(<4 x float> %a0) {
1602 %res = call <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1603 ret <4 x float> %res
1605 declare <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float>) nounwind readnone
1608 define <4 x float> @test_x86_sse_rsqrt_ss(<4 x float> %a0) {
1610 %res = call <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1611 ret <4 x float> %res
1613 declare <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float>) nounwind readnone
1616 define <4 x float> @test_x86_sse_sqrt_ps(<4 x float> %a0) {
1618 %res = call <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1619 ret <4 x float> %res
1621 declare <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float>) nounwind readnone
1624 define <4 x float> @test_x86_sse_sqrt_ss(<4 x float> %a0) {
1626 %res = call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1627 ret <4 x float> %res
1629 declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>) nounwind readnone
1632 define void @test_x86_sse_stmxcsr(i8* %a0) {
1635 call void @llvm.x86.sse.stmxcsr(i8* %a0)
1638 declare void @llvm.x86.sse.stmxcsr(i8*) nounwind
1641 define void @test_x86_sse_storeu_ps(i8* %a0, <4 x float> %a1) {
1644 call void @llvm.x86.sse.storeu.ps(i8* %a0, <4 x float> %a1)
1647 declare void @llvm.x86.sse.storeu.ps(i8*, <4 x float>) nounwind
1650 define <4 x float> @test_x86_sse_sub_ss(<4 x float> %a0, <4 x float> %a1) {
1652 %res = call <4 x float> @llvm.x86.sse.sub.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1653 ret <4 x float> %res
1655 declare <4 x float> @llvm.x86.sse.sub.ss(<4 x float>, <4 x float>) nounwind readnone
1658 define i32 @test_x86_sse_ucomieq_ss(<4 x float> %a0, <4 x float> %a1) {
1662 %res = call i32 @llvm.x86.sse.ucomieq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1665 declare i32 @llvm.x86.sse.ucomieq.ss(<4 x float>, <4 x float>) nounwind readnone
1668 define i32 @test_x86_sse_ucomige_ss(<4 x float> %a0, <4 x float> %a1) {
1672 %res = call i32 @llvm.x86.sse.ucomige.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1675 declare i32 @llvm.x86.sse.ucomige.ss(<4 x float>, <4 x float>) nounwind readnone
1678 define i32 @test_x86_sse_ucomigt_ss(<4 x float> %a0, <4 x float> %a1) {
1682 %res = call i32 @llvm.x86.sse.ucomigt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1685 declare i32 @llvm.x86.sse.ucomigt.ss(<4 x float>, <4 x float>) nounwind readnone
1688 define i32 @test_x86_sse_ucomile_ss(<4 x float> %a0, <4 x float> %a1) {
1692 %res = call i32 @llvm.x86.sse.ucomile.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1695 declare i32 @llvm.x86.sse.ucomile.ss(<4 x float>, <4 x float>) nounwind readnone
1698 define i32 @test_x86_sse_ucomilt_ss(<4 x float> %a0, <4 x float> %a1) {
1702 %res = call i32 @llvm.x86.sse.ucomilt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1705 declare i32 @llvm.x86.sse.ucomilt.ss(<4 x float>, <4 x float>) nounwind readnone
1708 define i32 @test_x86_sse_ucomineq_ss(<4 x float> %a0, <4 x float> %a1) {
1712 %res = call i32 @llvm.x86.sse.ucomineq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1715 declare i32 @llvm.x86.sse.ucomineq.ss(<4 x float>, <4 x float>) nounwind readnone
1718 define <16 x i8> @test_x86_ssse3_pabs_b_128(<16 x i8> %a0) {
1720 %res = call <16 x i8> @llvm.x86.ssse3.pabs.b.128(<16 x i8> %a0) ; <<16 x i8>> [#uses=1]
1723 declare <16 x i8> @llvm.x86.ssse3.pabs.b.128(<16 x i8>) nounwind readnone
1726 define <4 x i32> @test_x86_ssse3_pabs_d_128(<4 x i32> %a0) {
1728 %res = call <4 x i32> @llvm.x86.ssse3.pabs.d.128(<4 x i32> %a0) ; <<4 x i32>> [#uses=1]
1731 declare <4 x i32> @llvm.x86.ssse3.pabs.d.128(<4 x i32>) nounwind readnone
1734 define <8 x i16> @test_x86_ssse3_pabs_w_128(<8 x i16> %a0) {
1736 %res = call <8 x i16> @llvm.x86.ssse3.pabs.w.128(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
1739 declare <8 x i16> @llvm.x86.ssse3.pabs.w.128(<8 x i16>) nounwind readnone
1742 define <4 x i32> @test_x86_ssse3_phadd_d_128(<4 x i32> %a0, <4 x i32> %a1) {
1744 %res = call <4 x i32> @llvm.x86.ssse3.phadd.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1747 declare <4 x i32> @llvm.x86.ssse3.phadd.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1750 define <4 x i32> @test_x86_ssse3_phadd_sw_128(<4 x i32> %a0, <4 x i32> %a1) {
1752 %res = call <4 x i32> @llvm.x86.ssse3.phadd.sw.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1755 declare <4 x i32> @llvm.x86.ssse3.phadd.sw.128(<4 x i32>, <4 x i32>) nounwind readnone
1758 define <8 x i16> @test_x86_ssse3_phadd_w_128(<8 x i16> %a0, <8 x i16> %a1) {
1760 %res = call <8 x i16> @llvm.x86.ssse3.phadd.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1763 declare <8 x i16> @llvm.x86.ssse3.phadd.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1766 define <4 x i32> @test_x86_ssse3_phsub_d_128(<4 x i32> %a0, <4 x i32> %a1) {
1768 %res = call <4 x i32> @llvm.x86.ssse3.phsub.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1771 declare <4 x i32> @llvm.x86.ssse3.phsub.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1774 define <8 x i16> @test_x86_ssse3_phsub_sw_128(<8 x i16> %a0, <8 x i16> %a1) {
1776 %res = call <8 x i16> @llvm.x86.ssse3.phsub.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1779 declare <8 x i16> @llvm.x86.ssse3.phsub.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1782 define <8 x i16> @test_x86_ssse3_phsub_w_128(<8 x i16> %a0, <8 x i16> %a1) {
1784 %res = call <8 x i16> @llvm.x86.ssse3.phsub.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1787 declare <8 x i16> @llvm.x86.ssse3.phsub.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1790 define <8 x i16> @test_x86_ssse3_pmadd_ub_sw_128(<8 x i16> %a0, <8 x i16> %a1) {
1792 %res = call <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1795 declare <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1798 define <8 x i16> @test_x86_ssse3_pmul_hr_sw_128(<8 x i16> %a0, <8 x i16> %a1) {
1800 %res = call <8 x i16> @llvm.x86.ssse3.pmul.hr.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1803 declare <8 x i16> @llvm.x86.ssse3.pmul.hr.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1806 define <16 x i8> @test_x86_ssse3_pshuf_b_128(<16 x i8> %a0, <16 x i8> %a1) {
1808 %res = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1811 declare <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8>, <16 x i8>) nounwind readnone
1814 define <16 x i8> @test_x86_ssse3_psign_b_128(<16 x i8> %a0, <16 x i8> %a1) {
1816 %res = call <16 x i8> @llvm.x86.ssse3.psign.b.128(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1819 declare <16 x i8> @llvm.x86.ssse3.psign.b.128(<16 x i8>, <16 x i8>) nounwind readnone
1822 define <4 x i32> @test_x86_ssse3_psign_d_128(<4 x i32> %a0, <4 x i32> %a1) {
1824 %res = call <4 x i32> @llvm.x86.ssse3.psign.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1827 declare <4 x i32> @llvm.x86.ssse3.psign.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1830 define <8 x i16> @test_x86_ssse3_psign_w_128(<8 x i16> %a0, <8 x i16> %a1) {
1832 %res = call <8 x i16> @llvm.x86.ssse3.psign.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1835 declare <8 x i16> @llvm.x86.ssse3.psign.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1838 define <4 x double> @test_x86_avx_addsub_pd_256(<4 x double> %a0, <4 x double> %a1) {
1840 %res = call <4 x double> @llvm.x86.avx.addsub.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1841 ret <4 x double> %res
1843 declare <4 x double> @llvm.x86.avx.addsub.pd.256(<4 x double>, <4 x double>) nounwind readnone
1846 define <8 x float> @test_x86_avx_addsub_ps_256(<8 x float> %a0, <8 x float> %a1) {
1848 %res = call <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
1849 ret <8 x float> %res
1851 declare <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float>, <8 x float>) nounwind readnone
1854 define <4 x double> @test_x86_avx_blend_pd_256(<4 x double> %a0, <4 x double> %a1) {
1856 %res = call <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double> %a0, <4 x double> %a1, i32 7) ; <<4 x double>> [#uses=1]
1857 ret <4 x double> %res
1859 declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i32) nounwind readnone
1862 define <8 x float> @test_x86_avx_blend_ps_256(<8 x float> %a0, <8 x float> %a1) {
1864 %res = call <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
1865 ret <8 x float> %res
1867 declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
1870 define <4 x double> @test_x86_avx_blendv_pd_256(<4 x double> %a0, <4 x double> %a1, <4 x double> %a2) {
1872 %res = call <4 x double> @llvm.x86.avx.blendv.pd.256(<4 x double> %a0, <4 x double> %a1, <4 x double> %a2) ; <<4 x double>> [#uses=1]
1873 ret <4 x double> %res
1875 declare <4 x double> @llvm.x86.avx.blendv.pd.256(<4 x double>, <4 x double>, <4 x double>) nounwind readnone
1878 define <8 x float> @test_x86_avx_blendv_ps_256(<8 x float> %a0, <8 x float> %a1, <8 x float> %a2) {
1880 %res = call <8 x float> @llvm.x86.avx.blendv.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float> %a2) ; <<8 x float>> [#uses=1]
1881 ret <8 x float> %res
1883 declare <8 x float> @llvm.x86.avx.blendv.ps.256(<8 x float>, <8 x float>, <8 x float>) nounwind readnone
1886 define <4 x double> @test_x86_avx_cmp_pd_256(<4 x double> %a0, <4 x double> %a1) {
1888 %res = call <4 x double> @llvm.x86.avx.cmp.pd.256(<4 x double> %a0, <4 x double> %a1, i8 7) ; <<4 x double>> [#uses=1]
1889 ret <4 x double> %res
1891 declare <4 x double> @llvm.x86.avx.cmp.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone
1894 define <8 x float> @test_x86_avx_cmp_ps_256(<8 x float> %a0, <8 x float> %a1) {
1896 %res = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a1, i8 7) ; <<8 x float>> [#uses=1]
1897 ret <8 x float> %res
1899 declare <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
1902 define <4 x float> @test_x86_avx_cvt_pd2_ps_256(<4 x double> %a0) {
1904 %res = call <4 x float> @llvm.x86.avx.cvt.pd2.ps.256(<4 x double> %a0) ; <<4 x float>> [#uses=1]
1905 ret <4 x float> %res
1907 declare <4 x float> @llvm.x86.avx.cvt.pd2.ps.256(<4 x double>) nounwind readnone
1910 define <4 x i32> @test_x86_avx_cvt_pd2dq_256(<4 x double> %a0) {
1912 %res = call <4 x i32> @llvm.x86.avx.cvt.pd2dq.256(<4 x double> %a0) ; <<4 x i32>> [#uses=1]
1915 declare <4 x i32> @llvm.x86.avx.cvt.pd2dq.256(<4 x double>) nounwind readnone
1918 define <4 x double> @test_x86_avx_cvt_ps2_pd_256(<4 x float> %a0) {
1920 %res = call <4 x double> @llvm.x86.avx.cvt.ps2.pd.256(<4 x float> %a0) ; <<4 x double>> [#uses=1]
1921 ret <4 x double> %res
1923 declare <4 x double> @llvm.x86.avx.cvt.ps2.pd.256(<4 x float>) nounwind readnone
1926 define <8 x i32> @test_x86_avx_cvt_ps2dq_256(<8 x float> %a0) {
1928 %res = call <8 x i32> @llvm.x86.avx.cvt.ps2dq.256(<8 x float> %a0) ; <<8 x i32>> [#uses=1]
1931 declare <8 x i32> @llvm.x86.avx.cvt.ps2dq.256(<8 x float>) nounwind readnone
1934 define <4 x double> @test_x86_avx_cvtdq2_pd_256(<4 x i32> %a0) {
1936 %res = call <4 x double> @llvm.x86.avx.cvtdq2.pd.256(<4 x i32> %a0) ; <<4 x double>> [#uses=1]
1937 ret <4 x double> %res
1939 declare <4 x double> @llvm.x86.avx.cvtdq2.pd.256(<4 x i32>) nounwind readnone
1942 define <8 x float> @test_x86_avx_cvtdq2_ps_256(<8 x i32> %a0) {
1944 %res = call <8 x float> @llvm.x86.avx.cvtdq2.ps.256(<8 x i32> %a0) ; <<8 x float>> [#uses=1]
1945 ret <8 x float> %res
1947 declare <8 x float> @llvm.x86.avx.cvtdq2.ps.256(<8 x i32>) nounwind readnone
1950 define <4 x i32> @test_x86_avx_cvtt_pd2dq_256(<4 x double> %a0) {
1951 ; CHECK: vcvttpd2dqy
1952 %res = call <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double> %a0) ; <<4 x i32>> [#uses=1]
1955 declare <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double>) nounwind readnone
1958 define <8 x i32> @test_x86_avx_cvtt_ps2dq_256(<8 x float> %a0) {
1960 %res = call <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float> %a0) ; <<8 x i32>> [#uses=1]
1963 declare <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float>) nounwind readnone
1966 define <8 x float> @test_x86_avx_dp_ps_256(<8 x float> %a0, <8 x float> %a1) {
1968 %res = call <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
1969 ret <8 x float> %res
1971 declare <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
1974 define <4 x double> @test_x86_avx_hadd_pd_256(<4 x double> %a0, <4 x double> %a1) {
1976 %res = call <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1977 ret <4 x double> %res
1979 declare <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double>, <4 x double>) nounwind readnone
1982 define <8 x float> @test_x86_avx_hadd_ps_256(<8 x float> %a0, <8 x float> %a1) {
1984 %res = call <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
1985 ret <8 x float> %res
1987 declare <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float>, <8 x float>) nounwind readnone
1990 define <4 x double> @test_x86_avx_hsub_pd_256(<4 x double> %a0, <4 x double> %a1) {
1992 %res = call <4 x double> @llvm.x86.avx.hsub.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1993 ret <4 x double> %res
1995 declare <4 x double> @llvm.x86.avx.hsub.pd.256(<4 x double>, <4 x double>) nounwind readnone
1998 define <8 x float> @test_x86_avx_hsub_ps_256(<8 x float> %a0, <8 x float> %a1) {
2000 %res = call <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2001 ret <8 x float> %res
2003 declare <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float>, <8 x float>) nounwind readnone
2006 define <32 x i8> @test_x86_avx_ldu_dq_256(i8* %a0) {
2008 %res = call <32 x i8> @llvm.x86.avx.ldu.dq.256(i8* %a0) ; <<32 x i8>> [#uses=1]
2011 declare <32 x i8> @llvm.x86.avx.ldu.dq.256(i8*) nounwind readonly
2014 define <32 x i8> @test_x86_avx_loadu_dq_256(i8* %a0) {
2016 %res = call <32 x i8> @llvm.x86.avx.loadu.dq.256(i8* %a0) ; <<32 x i8>> [#uses=1]
2019 declare <32 x i8> @llvm.x86.avx.loadu.dq.256(i8*) nounwind readonly
2022 define <4 x double> @test_x86_avx_loadu_pd_256(i8* %a0) {
2024 %res = call <4 x double> @llvm.x86.avx.loadu.pd.256(i8* %a0) ; <<4 x double>> [#uses=1]
2025 ret <4 x double> %res
2027 declare <4 x double> @llvm.x86.avx.loadu.pd.256(i8*) nounwind readonly
2030 define <8 x float> @test_x86_avx_loadu_ps_256(i8* %a0) {
2032 %res = call <8 x float> @llvm.x86.avx.loadu.ps.256(i8* %a0) ; <<8 x float>> [#uses=1]
2033 ret <8 x float> %res
2035 declare <8 x float> @llvm.x86.avx.loadu.ps.256(i8*) nounwind readonly
2038 define <2 x double> @test_x86_avx_maskload_pd(i8* %a0, <2 x double> %a1) {
2040 %res = call <2 x double> @llvm.x86.avx.maskload.pd(i8* %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
2041 ret <2 x double> %res
2043 declare <2 x double> @llvm.x86.avx.maskload.pd(i8*, <2 x double>) nounwind readonly
2046 define <4 x double> @test_x86_avx_maskload_pd_256(i8* %a0, <4 x double> %a1) {
2048 %res = call <4 x double> @llvm.x86.avx.maskload.pd.256(i8* %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2049 ret <4 x double> %res
2051 declare <4 x double> @llvm.x86.avx.maskload.pd.256(i8*, <4 x double>) nounwind readonly
2054 define <4 x float> @test_x86_avx_maskload_ps(i8* %a0, <4 x float> %a1) {
2056 %res = call <4 x float> @llvm.x86.avx.maskload.ps(i8* %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
2057 ret <4 x float> %res
2059 declare <4 x float> @llvm.x86.avx.maskload.ps(i8*, <4 x float>) nounwind readonly
2062 define <8 x float> @test_x86_avx_maskload_ps_256(i8* %a0, <8 x float> %a1) {
2064 %res = call <8 x float> @llvm.x86.avx.maskload.ps.256(i8* %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2065 ret <8 x float> %res
2067 declare <8 x float> @llvm.x86.avx.maskload.ps.256(i8*, <8 x float>) nounwind readonly
2070 define void @test_x86_avx_maskstore_pd(i8* %a0, <2 x double> %a1, <2 x double> %a2) {
2072 call void @llvm.x86.avx.maskstore.pd(i8* %a0, <2 x double> %a1, <2 x double> %a2)
2075 declare void @llvm.x86.avx.maskstore.pd(i8*, <2 x double>, <2 x double>) nounwind
2078 define void @test_x86_avx_maskstore_pd_256(i8* %a0, <4 x double> %a1, <4 x double> %a2) {
2080 call void @llvm.x86.avx.maskstore.pd.256(i8* %a0, <4 x double> %a1, <4 x double> %a2)
2083 declare void @llvm.x86.avx.maskstore.pd.256(i8*, <4 x double>, <4 x double>) nounwind
2086 define void @test_x86_avx_maskstore_ps(i8* %a0, <4 x float> %a1, <4 x float> %a2) {
2088 call void @llvm.x86.avx.maskstore.ps(i8* %a0, <4 x float> %a1, <4 x float> %a2)
2091 declare void @llvm.x86.avx.maskstore.ps(i8*, <4 x float>, <4 x float>) nounwind
2094 define void @test_x86_avx_maskstore_ps_256(i8* %a0, <8 x float> %a1, <8 x float> %a2) {
2096 call void @llvm.x86.avx.maskstore.ps.256(i8* %a0, <8 x float> %a1, <8 x float> %a2)
2099 declare void @llvm.x86.avx.maskstore.ps.256(i8*, <8 x float>, <8 x float>) nounwind
2102 define <4 x double> @test_x86_avx_max_pd_256(<4 x double> %a0, <4 x double> %a1) {
2104 %res = call <4 x double> @llvm.x86.avx.max.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2105 ret <4 x double> %res
2107 declare <4 x double> @llvm.x86.avx.max.pd.256(<4 x double>, <4 x double>) nounwind readnone
2110 define <8 x float> @test_x86_avx_max_ps_256(<8 x float> %a0, <8 x float> %a1) {
2112 %res = call <8 x float> @llvm.x86.avx.max.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2113 ret <8 x float> %res
2115 declare <8 x float> @llvm.x86.avx.max.ps.256(<8 x float>, <8 x float>) nounwind readnone
2118 define <4 x double> @test_x86_avx_min_pd_256(<4 x double> %a0, <4 x double> %a1) {
2120 %res = call <4 x double> @llvm.x86.avx.min.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2121 ret <4 x double> %res
2123 declare <4 x double> @llvm.x86.avx.min.pd.256(<4 x double>, <4 x double>) nounwind readnone
2126 define <8 x float> @test_x86_avx_min_ps_256(<8 x float> %a0, <8 x float> %a1) {
2128 %res = call <8 x float> @llvm.x86.avx.min.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2129 ret <8 x float> %res
2131 declare <8 x float> @llvm.x86.avx.min.ps.256(<8 x float>, <8 x float>) nounwind readnone
2134 define i32 @test_x86_avx_movmsk_pd_256(<4 x double> %a0) {
2136 %res = call i32 @llvm.x86.avx.movmsk.pd.256(<4 x double> %a0) ; <i32> [#uses=1]
2139 declare i32 @llvm.x86.avx.movmsk.pd.256(<4 x double>) nounwind readnone
2142 define i32 @test_x86_avx_movmsk_ps_256(<8 x float> %a0) {
2144 %res = call i32 @llvm.x86.avx.movmsk.ps.256(<8 x float> %a0) ; <i32> [#uses=1]
2147 declare i32 @llvm.x86.avx.movmsk.ps.256(<8 x float>) nounwind readnone
2150 define void @test_x86_avx_movnt_dq_256(i8* %a0, <4 x i64> %a1) {
2152 call void @llvm.x86.avx.movnt.dq.256(i8* %a0, <4 x i64> %a1)
2155 declare void @llvm.x86.avx.movnt.dq.256(i8*, <4 x i64>) nounwind
2158 define void @test_x86_avx_movnt_pd_256(i8* %a0, <4 x double> %a1) {
2160 call void @llvm.x86.avx.movnt.pd.256(i8* %a0, <4 x double> %a1)
2163 declare void @llvm.x86.avx.movnt.pd.256(i8*, <4 x double>) nounwind
2166 define void @test_x86_avx_movnt_ps_256(i8* %a0, <8 x float> %a1) {
2168 call void @llvm.x86.avx.movnt.ps.256(i8* %a0, <8 x float> %a1)
2171 declare void @llvm.x86.avx.movnt.ps.256(i8*, <8 x float>) nounwind
2174 define i32 @test_x86_avx_ptestc_256(<4 x i64> %a0, <4 x i64> %a1) {
2178 %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2181 declare i32 @llvm.x86.avx.ptestc.256(<4 x i64>, <4 x i64>) nounwind readnone
2184 define i32 @test_x86_avx_ptestnzc_256(<4 x i64> %a0, <4 x i64> %a1) {
2188 %res = call i32 @llvm.x86.avx.ptestnzc.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2191 declare i32 @llvm.x86.avx.ptestnzc.256(<4 x i64>, <4 x i64>) nounwind readnone
2194 define i32 @test_x86_avx_ptestz_256(<4 x i64> %a0, <4 x i64> %a1) {
2198 %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2201 declare i32 @llvm.x86.avx.ptestz.256(<4 x i64>, <4 x i64>) nounwind readnone
2204 define <8 x float> @test_x86_avx_rcp_ps_256(<8 x float> %a0) {
2206 %res = call <8 x float> @llvm.x86.avx.rcp.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2207 ret <8 x float> %res
2209 declare <8 x float> @llvm.x86.avx.rcp.ps.256(<8 x float>) nounwind readnone
2212 define <4 x double> @test_x86_avx_round_pd_256(<4 x double> %a0) {
2214 %res = call <4 x double> @llvm.x86.avx.round.pd.256(<4 x double> %a0, i32 7) ; <<4 x double>> [#uses=1]
2215 ret <4 x double> %res
2217 declare <4 x double> @llvm.x86.avx.round.pd.256(<4 x double>, i32) nounwind readnone
2220 define <8 x float> @test_x86_avx_round_ps_256(<8 x float> %a0) {
2222 %res = call <8 x float> @llvm.x86.avx.round.ps.256(<8 x float> %a0, i32 7) ; <<8 x float>> [#uses=1]
2223 ret <8 x float> %res
2225 declare <8 x float> @llvm.x86.avx.round.ps.256(<8 x float>, i32) nounwind readnone
2228 define <8 x float> @test_x86_avx_rsqrt_ps_256(<8 x float> %a0) {
2230 %res = call <8 x float> @llvm.x86.avx.rsqrt.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2231 ret <8 x float> %res
2233 declare <8 x float> @llvm.x86.avx.rsqrt.ps.256(<8 x float>) nounwind readnone
2236 define <4 x double> @test_x86_avx_sqrt_pd_256(<4 x double> %a0) {
2238 %res = call <4 x double> @llvm.x86.avx.sqrt.pd.256(<4 x double> %a0) ; <<4 x double>> [#uses=1]
2239 ret <4 x double> %res
2241 declare <4 x double> @llvm.x86.avx.sqrt.pd.256(<4 x double>) nounwind readnone
2244 define <8 x float> @test_x86_avx_sqrt_ps_256(<8 x float> %a0) {
2246 %res = call <8 x float> @llvm.x86.avx.sqrt.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2247 ret <8 x float> %res
2249 declare <8 x float> @llvm.x86.avx.sqrt.ps.256(<8 x float>) nounwind readnone
2252 define void @test_x86_avx_storeu_dq_256(i8* %a0, <32 x i8> %a1) {
2254 call void @llvm.x86.avx.storeu.dq.256(i8* %a0, <32 x i8> %a1)
2257 declare void @llvm.x86.avx.storeu.dq.256(i8*, <32 x i8>) nounwind
2260 define void @test_x86_avx_storeu_pd_256(i8* %a0, <4 x double> %a1) {
2262 call void @llvm.x86.avx.storeu.pd.256(i8* %a0, <4 x double> %a1)
2265 declare void @llvm.x86.avx.storeu.pd.256(i8*, <4 x double>) nounwind
2268 define void @test_x86_avx_storeu_ps_256(i8* %a0, <8 x float> %a1) {
2270 call void @llvm.x86.avx.storeu.ps.256(i8* %a0, <8 x float> %a1)
2273 declare void @llvm.x86.avx.storeu.ps.256(i8*, <8 x float>) nounwind
2276 define <4 x double> @test_x86_avx_vbroadcast_sd_256(i8* %a0) {
2277 ; CHECK: vbroadcastsd
2278 %res = call <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8* %a0) ; <<4 x double>> [#uses=1]
2279 ret <4 x double> %res
2281 declare <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8*) nounwind readonly
2284 define <4 x double> @test_x86_avx_vbroadcastf128_pd_256(i8* %a0) {
2285 ; CHECK: vbroadcastf128
2286 %res = call <4 x double> @llvm.x86.avx.vbroadcastf128.pd.256(i8* %a0) ; <<4 x double>> [#uses=1]
2287 ret <4 x double> %res
2289 declare <4 x double> @llvm.x86.avx.vbroadcastf128.pd.256(i8*) nounwind readonly
2292 define <8 x float> @test_x86_avx_vbroadcastf128_ps_256(i8* %a0) {
2293 ; CHECK: vbroadcastf128
2294 %res = call <8 x float> @llvm.x86.avx.vbroadcastf128.ps.256(i8* %a0) ; <<8 x float>> [#uses=1]
2295 ret <8 x float> %res
2297 declare <8 x float> @llvm.x86.avx.vbroadcastf128.ps.256(i8*) nounwind readonly
2300 define <4 x float> @test_x86_avx_vbroadcastss(i8* %a0) {
2301 ; CHECK: vbroadcastss
2302 %res = call <4 x float> @llvm.x86.avx.vbroadcastss(i8* %a0) ; <<4 x float>> [#uses=1]
2303 ret <4 x float> %res
2305 declare <4 x float> @llvm.x86.avx.vbroadcastss(i8*) nounwind readonly
2308 define <8 x float> @test_x86_avx_vbroadcastss_256(i8* %a0) {
2309 ; CHECK: vbroadcastss
2310 %res = call <8 x float> @llvm.x86.avx.vbroadcastss.256(i8* %a0) ; <<8 x float>> [#uses=1]
2311 ret <8 x float> %res
2313 declare <8 x float> @llvm.x86.avx.vbroadcastss.256(i8*) nounwind readonly
2316 define <2 x double> @test_x86_avx_vextractf128_pd_256(<4 x double> %a0) {
2317 ; CHECK: vextractf128
2318 %res = call <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double> %a0, i8 7) ; <<2 x double>> [#uses=1]
2319 ret <2 x double> %res
2321 declare <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double>, i8) nounwind readnone
2324 define <4 x float> @test_x86_avx_vextractf128_ps_256(<8 x float> %a0) {
2325 ; CHECK: vextractf128
2326 %res = call <4 x float> @llvm.x86.avx.vextractf128.ps.256(<8 x float> %a0, i8 7) ; <<4 x float>> [#uses=1]
2327 ret <4 x float> %res
2329 declare <4 x float> @llvm.x86.avx.vextractf128.ps.256(<8 x float>, i8) nounwind readnone
2332 define <4 x i32> @test_x86_avx_vextractf128_si_256(<8 x i32> %a0) {
2333 ; CHECK: vextractf128
2334 %res = call <4 x i32> @llvm.x86.avx.vextractf128.si.256(<8 x i32> %a0, i8 7) ; <<4 x i32>> [#uses=1]
2337 declare <4 x i32> @llvm.x86.avx.vextractf128.si.256(<8 x i32>, i8) nounwind readnone
2340 define <4 x double> @test_x86_avx_vinsertf128_pd_256(<4 x double> %a0, <2 x double> %a1) {
2341 ; CHECK: vinsertf128
2342 %res = call <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double> %a0, <2 x double> %a1, i8 7) ; <<4 x double>> [#uses=1]
2343 ret <4 x double> %res
2345 declare <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double>, <2 x double>, i8) nounwind readnone
2348 define <8 x float> @test_x86_avx_vinsertf128_ps_256(<8 x float> %a0, <4 x float> %a1) {
2349 ; CHECK: vinsertf128
2350 %res = call <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float> %a0, <4 x float> %a1, i8 7) ; <<8 x float>> [#uses=1]
2351 ret <8 x float> %res
2353 declare <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float>, <4 x float>, i8) nounwind readnone
2356 define <8 x i32> @test_x86_avx_vinsertf128_si_256(<8 x i32> %a0, <4 x i32> %a1) {
2357 ; CHECK: vinsertf128
2358 %res = call <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32> %a0, <4 x i32> %a1, i8 7) ; <<8 x i32>> [#uses=1]
2361 declare <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32>, <4 x i32>, i8) nounwind readnone
2364 define <4 x double> @test_x86_avx_vperm2f128_pd_256(<4 x double> %a0, <4 x double> %a1) {
2366 %res = call <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double> %a0, <4 x double> %a1, i8 7) ; <<4 x double>> [#uses=1]
2367 ret <4 x double> %res
2369 declare <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone
2372 define <8 x float> @test_x86_avx_vperm2f128_ps_256(<8 x float> %a0, <8 x float> %a1) {
2374 %res = call <8 x float> @llvm.x86.avx.vperm2f128.ps.256(<8 x float> %a0, <8 x float> %a1, i8 7) ; <<8 x float>> [#uses=1]
2375 ret <8 x float> %res
2377 declare <8 x float> @llvm.x86.avx.vperm2f128.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
2380 define <8 x i32> @test_x86_avx_vperm2f128_si_256(<8 x i32> %a0, <8 x i32> %a1) {
2382 %res = call <8 x i32> @llvm.x86.avx.vperm2f128.si.256(<8 x i32> %a0, <8 x i32> %a1, i8 7) ; <<8 x i32>> [#uses=1]
2385 declare <8 x i32> @llvm.x86.avx.vperm2f128.si.256(<8 x i32>, <8 x i32>, i8) nounwind readnone
2388 define <2 x double> @test_x86_avx_vpermil_pd(<2 x double> %a0) {
2390 %res = call <2 x double> @llvm.x86.avx.vpermil.pd(<2 x double> %a0, i8 7) ; <<2 x double>> [#uses=1]
2391 ret <2 x double> %res
2393 declare <2 x double> @llvm.x86.avx.vpermil.pd(<2 x double>, i8) nounwind readnone
2396 define <4 x double> @test_x86_avx_vpermil_pd_256(<4 x double> %a0) {
2398 %res = call <4 x double> @llvm.x86.avx.vpermil.pd.256(<4 x double> %a0, i8 7) ; <<4 x double>> [#uses=1]
2399 ret <4 x double> %res
2401 declare <4 x double> @llvm.x86.avx.vpermil.pd.256(<4 x double>, i8) nounwind readnone
2404 define <4 x float> @test_x86_avx_vpermil_ps(<4 x float> %a0) {
2406 %res = call <4 x float> @llvm.x86.avx.vpermil.ps(<4 x float> %a0, i8 7) ; <<4 x float>> [#uses=1]
2407 ret <4 x float> %res
2409 declare <4 x float> @llvm.x86.avx.vpermil.ps(<4 x float>, i8) nounwind readnone
2412 define <8 x float> @test_x86_avx_vpermil_ps_256(<8 x float> %a0) {
2414 %res = call <8 x float> @llvm.x86.avx.vpermil.ps.256(<8 x float> %a0, i8 7) ; <<8 x float>> [#uses=1]
2415 ret <8 x float> %res
2417 declare <8 x float> @llvm.x86.avx.vpermil.ps.256(<8 x float>, i8) nounwind readnone
2420 define <2 x double> @test_x86_avx_vpermilvar_pd(<2 x double> %a0, <2 x i64> %a1) {
2422 %res = call <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double> %a0, <2 x i64> %a1) ; <<2 x double>> [#uses=1]
2423 ret <2 x double> %res
2425 declare <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double>, <2 x i64>) nounwind readnone
2428 define <4 x double> @test_x86_avx_vpermilvar_pd_256(<4 x double> %a0, <4 x i64> %a1) {
2430 %res = call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %a0, <4 x i64> %a1) ; <<4 x double>> [#uses=1]
2431 ret <4 x double> %res
2433 declare <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double>, <4 x i64>) nounwind readnone
2436 define <4 x float> @test_x86_avx_vpermilvar_ps(<4 x float> %a0, <4 x i32> %a1) {
2438 %res = call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> %a1) ; <<4 x float>> [#uses=1]
2439 ret <4 x float> %res
2441 declare <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float>, <4 x i32>) nounwind readnone
2444 define <8 x float> @test_x86_avx_vpermilvar_ps_256(<8 x float> %a0, <8 x i32> %a1) {
2446 %res = call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float> %a0, <8 x i32> %a1) ; <<8 x float>> [#uses=1]
2447 ret <8 x float> %res
2449 declare <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float>, <8 x i32>) nounwind readnone
2452 define i32 @test_x86_avx_vtestc_pd(<2 x double> %a0, <2 x double> %a1) {
2456 %res = call i32 @llvm.x86.avx.vtestc.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2459 declare i32 @llvm.x86.avx.vtestc.pd(<2 x double>, <2 x double>) nounwind readnone
2462 define i32 @test_x86_avx_vtestc_pd_256(<4 x double> %a0, <4 x double> %a1) {
2466 %res = call i32 @llvm.x86.avx.vtestc.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2469 declare i32 @llvm.x86.avx.vtestc.pd.256(<4 x double>, <4 x double>) nounwind readnone
2472 define i32 @test_x86_avx_vtestc_ps(<4 x float> %a0, <4 x float> %a1) {
2476 %res = call i32 @llvm.x86.avx.vtestc.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2479 declare i32 @llvm.x86.avx.vtestc.ps(<4 x float>, <4 x float>) nounwind readnone
2482 define i32 @test_x86_avx_vtestc_ps_256(<8 x float> %a0, <8 x float> %a1) {
2486 %res = call i32 @llvm.x86.avx.vtestc.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2489 declare i32 @llvm.x86.avx.vtestc.ps.256(<8 x float>, <8 x float>) nounwind readnone
2492 define i32 @test_x86_avx_vtestnzc_pd(<2 x double> %a0, <2 x double> %a1) {
2496 %res = call i32 @llvm.x86.avx.vtestnzc.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2499 declare i32 @llvm.x86.avx.vtestnzc.pd(<2 x double>, <2 x double>) nounwind readnone
2502 define i32 @test_x86_avx_vtestnzc_pd_256(<4 x double> %a0, <4 x double> %a1) {
2506 %res = call i32 @llvm.x86.avx.vtestnzc.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2509 declare i32 @llvm.x86.avx.vtestnzc.pd.256(<4 x double>, <4 x double>) nounwind readnone
2512 define i32 @test_x86_avx_vtestnzc_ps(<4 x float> %a0, <4 x float> %a1) {
2516 %res = call i32 @llvm.x86.avx.vtestnzc.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2519 declare i32 @llvm.x86.avx.vtestnzc.ps(<4 x float>, <4 x float>) nounwind readnone
2522 define i32 @test_x86_avx_vtestnzc_ps_256(<8 x float> %a0, <8 x float> %a1) {
2526 %res = call i32 @llvm.x86.avx.vtestnzc.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2529 declare i32 @llvm.x86.avx.vtestnzc.ps.256(<8 x float>, <8 x float>) nounwind readnone
2532 define i32 @test_x86_avx_vtestz_pd(<2 x double> %a0, <2 x double> %a1) {
2536 %res = call i32 @llvm.x86.avx.vtestz.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2539 declare i32 @llvm.x86.avx.vtestz.pd(<2 x double>, <2 x double>) nounwind readnone
2542 define i32 @test_x86_avx_vtestz_pd_256(<4 x double> %a0, <4 x double> %a1) {
2546 %res = call i32 @llvm.x86.avx.vtestz.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2549 declare i32 @llvm.x86.avx.vtestz.pd.256(<4 x double>, <4 x double>) nounwind readnone
2552 define i32 @test_x86_avx_vtestz_ps(<4 x float> %a0, <4 x float> %a1) {
2556 %res = call i32 @llvm.x86.avx.vtestz.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2559 declare i32 @llvm.x86.avx.vtestz.ps(<4 x float>, <4 x float>) nounwind readnone
2562 define i32 @test_x86_avx_vtestz_ps_256(<8 x float> %a0, <8 x float> %a1) {
2566 %res = call i32 @llvm.x86.avx.vtestz.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2569 declare i32 @llvm.x86.avx.vtestz.ps.256(<8 x float>, <8 x float>) nounwind readnone
2572 define void @test_x86_avx_vzeroall() {
2574 call void @llvm.x86.avx.vzeroall()
2577 declare void @llvm.x86.avx.vzeroall() nounwind
2580 define void @test_x86_avx_vzeroupper() {
2582 call void @llvm.x86.avx.vzeroupper()
2585 declare void @llvm.x86.avx.vzeroupper() nounwind