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) {
117 ; CHECK: sbbl %eax, %eax
118 ; CHECK: andl $1, %eax
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) {
829 %res = call i32 @llvm.x86.sse2.ucomilt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
832 declare i32 @llvm.x86.sse2.ucomilt.sd(<2 x double>, <2 x double>) nounwind readnone
835 define i32 @test_x86_sse2_ucomineq_sd(<2 x double> %a0, <2 x double> %a1) {
839 %res = call i32 @llvm.x86.sse2.ucomineq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
842 declare i32 @llvm.x86.sse2.ucomineq.sd(<2 x double>, <2 x double>) nounwind readnone
845 define <2 x double> @test_x86_sse3_addsub_pd(<2 x double> %a0, <2 x double> %a1) {
847 %res = call <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
848 ret <2 x double> %res
850 declare <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double>, <2 x double>) nounwind readnone
853 define <4 x float> @test_x86_sse3_addsub_ps(<4 x float> %a0, <4 x float> %a1) {
855 %res = call <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
858 declare <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float>, <4 x float>) nounwind readnone
861 define <2 x double> @test_x86_sse3_hadd_pd(<2 x double> %a0, <2 x double> %a1) {
863 %res = call <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
864 ret <2 x double> %res
866 declare <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double>, <2 x double>) nounwind readnone
869 define <4 x float> @test_x86_sse3_hadd_ps(<4 x float> %a0, <4 x float> %a1) {
871 %res = call <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
874 declare <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float>, <4 x float>) nounwind readnone
877 define <2 x double> @test_x86_sse3_hsub_pd(<2 x double> %a0, <2 x double> %a1) {
879 %res = call <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
880 ret <2 x double> %res
882 declare <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double>, <2 x double>) nounwind readnone
885 define <4 x float> @test_x86_sse3_hsub_ps(<4 x float> %a0, <4 x float> %a1) {
887 %res = call <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
890 declare <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float>, <4 x float>) nounwind readnone
893 define <16 x i8> @test_x86_sse3_ldu_dq(i8* %a0) {
896 %res = call <16 x i8> @llvm.x86.sse3.ldu.dq(i8* %a0) ; <<16 x i8>> [#uses=1]
899 declare <16 x i8> @llvm.x86.sse3.ldu.dq(i8*) nounwind readonly
902 define <2 x double> @test_x86_sse41_blendpd(<2 x double> %a0, <2 x double> %a1) {
904 %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
905 ret <2 x double> %res
907 declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i32) nounwind readnone
910 define <4 x float> @test_x86_sse41_blendps(<4 x float> %a0, <4 x float> %a1) {
912 %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
915 declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i32) nounwind readnone
918 define <2 x double> @test_x86_sse41_blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2) {
920 %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]
921 ret <2 x double> %res
923 declare <2 x double> @llvm.x86.sse41.blendvpd(<2 x double>, <2 x double>, <2 x double>) nounwind readnone
926 define <4 x float> @test_x86_sse41_blendvps(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2) {
928 %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]
931 declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x float>) nounwind readnone
934 define <2 x double> @test_x86_sse41_dppd(<2 x double> %a0, <2 x double> %a1) {
936 %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
937 ret <2 x double> %res
939 declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i32) nounwind readnone
942 define <4 x float> @test_x86_sse41_dpps(<4 x float> %a0, <4 x float> %a1) {
944 %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
947 declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i32) nounwind readnone
950 define <4 x float> @test_x86_sse41_insertps(<4 x float> %a0, <4 x float> %a1) {
952 %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
955 declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone
958 define <2 x i64> @test_x86_sse41_movntdqa(i8* %a0) {
961 %res = call <2 x i64> @llvm.x86.sse41.movntdqa(i8* %a0) ; <<2 x i64>> [#uses=1]
964 declare <2 x i64> @llvm.x86.sse41.movntdqa(i8*) nounwind readonly
967 define <16 x i8> @test_x86_sse41_mpsadbw(<16 x i8> %a0, <16 x i8> %a1) {
969 %res = call <16 x i8> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i32 7) ; <<16 x i8>> [#uses=1]
972 declare <16 x i8> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i32) nounwind readnone
975 define <8 x i16> @test_x86_sse41_packusdw(<4 x i32> %a0, <4 x i32> %a1) {
977 %res = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a0, <4 x i32> %a1) ; <<8 x i16>> [#uses=1]
980 declare <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32>, <4 x i32>) nounwind readnone
983 define <16 x i8> @test_x86_sse41_pblendvb(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> %a2) {
985 %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]
988 declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone
991 define <8 x i16> @test_x86_sse41_pblendw(<8 x i16> %a0, <8 x i16> %a1) {
993 %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i32 7) ; <<8 x i16>> [#uses=1]
996 declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i32) nounwind readnone
999 define <2 x i64> @test_x86_sse41_pcmpeqq(<2 x i64> %a0, <2 x i64> %a1) {
1001 %res = call <2 x i64> @llvm.x86.sse41.pcmpeqq(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
1004 declare <2 x i64> @llvm.x86.sse41.pcmpeqq(<2 x i64>, <2 x i64>) nounwind readnone
1007 define <8 x i16> @test_x86_sse41_phminposuw(<8 x i16> %a0) {
1008 ; CHECK: vphminposuw
1009 %res = call <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
1012 declare <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16>) nounwind readnone
1015 define <16 x i8> @test_x86_sse41_pmaxsb(<16 x i8> %a0, <16 x i8> %a1) {
1017 %res = call <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1020 declare <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8>, <16 x i8>) nounwind readnone
1023 define <4 x i32> @test_x86_sse41_pmaxsd(<4 x i32> %a0, <4 x i32> %a1) {
1025 %res = call <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1028 declare <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32>, <4 x i32>) nounwind readnone
1031 define <4 x i32> @test_x86_sse41_pmaxud(<4 x i32> %a0, <4 x i32> %a1) {
1033 %res = call <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1036 declare <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32>, <4 x i32>) nounwind readnone
1039 define <8 x i16> @test_x86_sse41_pmaxuw(<8 x i16> %a0, <8 x i16> %a1) {
1041 %res = call <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1044 declare <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16>, <8 x i16>) nounwind readnone
1047 define <16 x i8> @test_x86_sse41_pminsb(<16 x i8> %a0, <16 x i8> %a1) {
1049 %res = call <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1052 declare <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8>, <16 x i8>) nounwind readnone
1055 define <4 x i32> @test_x86_sse41_pminsd(<4 x i32> %a0, <4 x i32> %a1) {
1057 %res = call <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1060 declare <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32>, <4 x i32>) nounwind readnone
1063 define <4 x i32> @test_x86_sse41_pminud(<4 x i32> %a0, <4 x i32> %a1) {
1065 %res = call <4 x i32> @llvm.x86.sse41.pminud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1068 declare <4 x i32> @llvm.x86.sse41.pminud(<4 x i32>, <4 x i32>) nounwind readnone
1071 define <8 x i16> @test_x86_sse41_pminuw(<8 x i16> %a0, <8 x i16> %a1) {
1073 %res = call <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1076 declare <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16>, <8 x i16>) nounwind readnone
1079 define <4 x i32> @test_x86_sse41_pmovsxbd(<16 x i8> %a0) {
1081 %res = call <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
1084 declare <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8>) nounwind readnone
1087 define <2 x i64> @test_x86_sse41_pmovsxbq(<16 x i8> %a0) {
1089 %res = call <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
1092 declare <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8>) nounwind readnone
1095 define <8 x i16> @test_x86_sse41_pmovsxbw(<16 x i8> %a0) {
1097 %res = call <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
1100 declare <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8>) nounwind readnone
1103 define <2 x i64> @test_x86_sse41_pmovsxdq(<4 x i32> %a0) {
1105 %res = call <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
1108 declare <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32>) nounwind readnone
1111 define <4 x i32> @test_x86_sse41_pmovsxwd(<8 x i16> %a0) {
1113 %res = call <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
1116 declare <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16>) nounwind readnone
1119 define <2 x i64> @test_x86_sse41_pmovsxwq(<8 x i16> %a0) {
1121 %res = call <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
1124 declare <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16>) nounwind readnone
1127 define <4 x i32> @test_x86_sse41_pmovzxbd(<16 x i8> %a0) {
1129 %res = call <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
1132 declare <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8>) nounwind readnone
1135 define <2 x i64> @test_x86_sse41_pmovzxbq(<16 x i8> %a0) {
1137 %res = call <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
1140 declare <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8>) nounwind readnone
1143 define <8 x i16> @test_x86_sse41_pmovzxbw(<16 x i8> %a0) {
1145 %res = call <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
1148 declare <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8>) nounwind readnone
1151 define <2 x i64> @test_x86_sse41_pmovzxdq(<4 x i32> %a0) {
1153 %res = call <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
1156 declare <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32>) nounwind readnone
1159 define <4 x i32> @test_x86_sse41_pmovzxwd(<8 x i16> %a0) {
1161 %res = call <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
1164 declare <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16>) nounwind readnone
1167 define <2 x i64> @test_x86_sse41_pmovzxwq(<8 x i16> %a0) {
1169 %res = call <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
1172 declare <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16>) nounwind readnone
1175 define <2 x i64> @test_x86_sse41_pmuldq(<4 x i32> %a0, <4 x i32> %a1) {
1177 %res = call <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32> %a0, <4 x i32> %a1) ; <<2 x i64>> [#uses=1]
1180 declare <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32>, <4 x i32>) nounwind readnone
1183 define i32 @test_x86_sse41_ptestc(<4 x float> %a0, <4 x float> %a1) {
1186 %res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1189 declare i32 @llvm.x86.sse41.ptestc(<4 x float>, <4 x float>) nounwind readnone
1192 define i32 @test_x86_sse41_ptestnzc(<4 x float> %a0, <4 x float> %a1) {
1196 %res = call i32 @llvm.x86.sse41.ptestnzc(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1199 declare i32 @llvm.x86.sse41.ptestnzc(<4 x float>, <4 x float>) nounwind readnone
1202 define i32 @test_x86_sse41_ptestz(<4 x float> %a0, <4 x float> %a1) {
1206 %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1209 declare i32 @llvm.x86.sse41.ptestz(<4 x float>, <4 x float>) nounwind readnone
1212 define <2 x double> @test_x86_sse41_round_pd(<2 x double> %a0) {
1214 %res = call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %a0, i32 7) ; <<2 x double>> [#uses=1]
1215 ret <2 x double> %res
1217 declare <2 x double> @llvm.x86.sse41.round.pd(<2 x double>, i32) nounwind readnone
1220 define <4 x float> @test_x86_sse41_round_ps(<4 x float> %a0) {
1222 %res = call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %a0, i32 7) ; <<4 x float>> [#uses=1]
1223 ret <4 x float> %res
1225 declare <4 x float> @llvm.x86.sse41.round.ps(<4 x float>, i32) nounwind readnone
1228 define <2 x double> @test_x86_sse41_round_sd(<2 x double> %a0, <2 x double> %a1) {
1230 %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]
1231 ret <2 x double> %res
1233 declare <2 x double> @llvm.x86.sse41.round.sd(<2 x double>, <2 x double>, i32) nounwind readnone
1236 define <4 x float> @test_x86_sse41_round_ss(<4 x float> %a0, <4 x float> %a1) {
1238 %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]
1239 ret <4 x float> %res
1241 declare <4 x float> @llvm.x86.sse41.round.ss(<4 x float>, <4 x float>, i32) nounwind readnone
1244 define i32 @test_x86_sse42_pcmpestri128(<16 x i8> %a0, <16 x i8> %a2) {
1249 %res = call i32 @llvm.x86.sse42.pcmpestri128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1252 declare i32 @llvm.x86.sse42.pcmpestri128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1255 define i32 @test_x86_sse42_pcmpestria128(<16 x i8> %a0, <16 x i8> %a2) {
1260 %res = call i32 @llvm.x86.sse42.pcmpestria128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1263 declare i32 @llvm.x86.sse42.pcmpestria128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1266 define i32 @test_x86_sse42_pcmpestric128(<16 x i8> %a0, <16 x i8> %a2) {
1271 %res = call i32 @llvm.x86.sse42.pcmpestric128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1274 declare i32 @llvm.x86.sse42.pcmpestric128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1277 define i32 @test_x86_sse42_pcmpestrio128(<16 x i8> %a0, <16 x i8> %a2) {
1282 %res = call i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1285 declare i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1288 define i32 @test_x86_sse42_pcmpestris128(<16 x i8> %a0, <16 x i8> %a2) {
1293 %res = call i32 @llvm.x86.sse42.pcmpestris128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1296 declare i32 @llvm.x86.sse42.pcmpestris128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1299 define i32 @test_x86_sse42_pcmpestriz128(<16 x i8> %a0, <16 x i8> %a2) {
1304 %res = call i32 @llvm.x86.sse42.pcmpestriz128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1307 declare i32 @llvm.x86.sse42.pcmpestriz128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1310 define <16 x i8> @test_x86_sse42_pcmpestrm128(<16 x i8> %a0, <16 x i8> %a2) {
1314 %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]
1317 declare <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1320 define <2 x i64> @test_x86_sse42_pcmpgtq(<2 x i64> %a0, <2 x i64> %a1) {
1322 %res = call <2 x i64> @llvm.x86.sse42.pcmpgtq(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
1325 declare <2 x i64> @llvm.x86.sse42.pcmpgtq(<2 x i64>, <2 x i64>) nounwind readnone
1328 define i32 @test_x86_sse42_pcmpistri128(<16 x i8> %a0, <16 x i8> %a1) {
1331 %res = call i32 @llvm.x86.sse42.pcmpistri128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1334 declare i32 @llvm.x86.sse42.pcmpistri128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1337 define i32 @test_x86_sse42_pcmpistria128(<16 x i8> %a0, <16 x i8> %a1) {
1340 %res = call i32 @llvm.x86.sse42.pcmpistria128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1343 declare i32 @llvm.x86.sse42.pcmpistria128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1346 define i32 @test_x86_sse42_pcmpistric128(<16 x i8> %a0, <16 x i8> %a1) {
1349 %res = call i32 @llvm.x86.sse42.pcmpistric128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1352 declare i32 @llvm.x86.sse42.pcmpistric128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1355 define i32 @test_x86_sse42_pcmpistrio128(<16 x i8> %a0, <16 x i8> %a1) {
1358 %res = call i32 @llvm.x86.sse42.pcmpistrio128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1361 declare i32 @llvm.x86.sse42.pcmpistrio128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1364 define i32 @test_x86_sse42_pcmpistris128(<16 x i8> %a0, <16 x i8> %a1) {
1367 %res = call i32 @llvm.x86.sse42.pcmpistris128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1370 declare i32 @llvm.x86.sse42.pcmpistris128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1373 define i32 @test_x86_sse42_pcmpistriz128(<16 x i8> %a0, <16 x i8> %a1) {
1376 %res = call i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1379 declare i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1382 define <16 x i8> @test_x86_sse42_pcmpistrm128(<16 x i8> %a0, <16 x i8> %a1) {
1384 %res = call <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <<16 x i8>> [#uses=1]
1387 declare <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1390 define <4 x float> @test_x86_sse_add_ss(<4 x float> %a0, <4 x float> %a1) {
1392 %res = call <4 x float> @llvm.x86.sse.add.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1393 ret <4 x float> %res
1395 declare <4 x float> @llvm.x86.sse.add.ss(<4 x float>, <4 x float>) nounwind readnone
1398 define <4 x float> @test_x86_sse_cmp_ps(<4 x float> %a0, <4 x float> %a1) {
1400 %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]
1401 ret <4 x float> %res
1403 declare <4 x float> @llvm.x86.sse.cmp.ps(<4 x float>, <4 x float>, i8) nounwind readnone
1406 define <4 x float> @test_x86_sse_cmp_ss(<4 x float> %a0, <4 x float> %a1) {
1408 %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]
1409 ret <4 x float> %res
1411 declare <4 x float> @llvm.x86.sse.cmp.ss(<4 x float>, <4 x float>, i8) nounwind readnone
1414 define i32 @test_x86_sse_comieq_ss(<4 x float> %a0, <4 x float> %a1) {
1418 %res = call i32 @llvm.x86.sse.comieq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1421 declare i32 @llvm.x86.sse.comieq.ss(<4 x float>, <4 x float>) nounwind readnone
1424 define i32 @test_x86_sse_comige_ss(<4 x float> %a0, <4 x float> %a1) {
1428 %res = call i32 @llvm.x86.sse.comige.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1431 declare i32 @llvm.x86.sse.comige.ss(<4 x float>, <4 x float>) nounwind readnone
1434 define i32 @test_x86_sse_comigt_ss(<4 x float> %a0, <4 x float> %a1) {
1438 %res = call i32 @llvm.x86.sse.comigt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1441 declare i32 @llvm.x86.sse.comigt.ss(<4 x float>, <4 x float>) nounwind readnone
1444 define i32 @test_x86_sse_comile_ss(<4 x float> %a0, <4 x float> %a1) {
1448 %res = call i32 @llvm.x86.sse.comile.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1451 declare i32 @llvm.x86.sse.comile.ss(<4 x float>, <4 x float>) nounwind readnone
1454 define i32 @test_x86_sse_comilt_ss(<4 x float> %a0, <4 x float> %a1) {
1457 %res = call i32 @llvm.x86.sse.comilt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1460 declare i32 @llvm.x86.sse.comilt.ss(<4 x float>, <4 x float>) nounwind readnone
1463 define i32 @test_x86_sse_comineq_ss(<4 x float> %a0, <4 x float> %a1) {
1467 %res = call i32 @llvm.x86.sse.comineq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1470 declare i32 @llvm.x86.sse.comineq.ss(<4 x float>, <4 x float>) nounwind readnone
1473 define <4 x float> @test_x86_sse_cvtsi2ss(<4 x float> %a0) {
1476 %res = call <4 x float> @llvm.x86.sse.cvtsi2ss(<4 x float> %a0, i32 7) ; <<4 x float>> [#uses=1]
1477 ret <4 x float> %res
1479 declare <4 x float> @llvm.x86.sse.cvtsi2ss(<4 x float>, i32) nounwind readnone
1482 define i32 @test_x86_sse_cvtss2si(<4 x float> %a0) {
1484 %res = call i32 @llvm.x86.sse.cvtss2si(<4 x float> %a0) ; <i32> [#uses=1]
1487 declare i32 @llvm.x86.sse.cvtss2si(<4 x float>) nounwind readnone
1490 define i32 @test_x86_sse_cvttss2si(<4 x float> %a0) {
1492 %res = call i32 @llvm.x86.sse.cvttss2si(<4 x float> %a0) ; <i32> [#uses=1]
1495 declare i32 @llvm.x86.sse.cvttss2si(<4 x float>) nounwind readnone
1498 define <4 x float> @test_x86_sse_div_ss(<4 x float> %a0, <4 x float> %a1) {
1500 %res = call <4 x float> @llvm.x86.sse.div.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1501 ret <4 x float> %res
1503 declare <4 x float> @llvm.x86.sse.div.ss(<4 x float>, <4 x float>) nounwind readnone
1506 define void @test_x86_sse_ldmxcsr(i8* %a0) {
1509 call void @llvm.x86.sse.ldmxcsr(i8* %a0)
1512 declare void @llvm.x86.sse.ldmxcsr(i8*) nounwind
1515 define <4 x float> @test_x86_sse_loadu_ps(i8* %a0) {
1518 %res = call <4 x float> @llvm.x86.sse.loadu.ps(i8* %a0) ; <<4 x float>> [#uses=1]
1519 ret <4 x float> %res
1521 declare <4 x float> @llvm.x86.sse.loadu.ps(i8*) nounwind readonly
1524 define <4 x float> @test_x86_sse_max_ps(<4 x float> %a0, <4 x float> %a1) {
1526 %res = call <4 x float> @llvm.x86.sse.max.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1527 ret <4 x float> %res
1529 declare <4 x float> @llvm.x86.sse.max.ps(<4 x float>, <4 x float>) nounwind readnone
1532 define <4 x float> @test_x86_sse_max_ss(<4 x float> %a0, <4 x float> %a1) {
1534 %res = call <4 x float> @llvm.x86.sse.max.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1535 ret <4 x float> %res
1537 declare <4 x float> @llvm.x86.sse.max.ss(<4 x float>, <4 x float>) nounwind readnone
1540 define <4 x float> @test_x86_sse_min_ps(<4 x float> %a0, <4 x float> %a1) {
1542 %res = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1543 ret <4 x float> %res
1545 declare <4 x float> @llvm.x86.sse.min.ps(<4 x float>, <4 x float>) nounwind readnone
1548 define <4 x float> @test_x86_sse_min_ss(<4 x float> %a0, <4 x float> %a1) {
1550 %res = call <4 x float> @llvm.x86.sse.min.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1551 ret <4 x float> %res
1553 declare <4 x float> @llvm.x86.sse.min.ss(<4 x float>, <4 x float>) nounwind readnone
1556 define i32 @test_x86_sse_movmsk_ps(<4 x float> %a0) {
1558 %res = call i32 @llvm.x86.sse.movmsk.ps(<4 x float> %a0) ; <i32> [#uses=1]
1561 declare i32 @llvm.x86.sse.movmsk.ps(<4 x float>) nounwind readnone
1564 define void @test_x86_sse_movnt_ps(i8* %a0, <4 x float> %a1) {
1567 call void @llvm.x86.sse.movnt.ps(i8* %a0, <4 x float> %a1)
1570 declare void @llvm.x86.sse.movnt.ps(i8*, <4 x float>) nounwind
1573 define <4 x float> @test_x86_sse_mul_ss(<4 x float> %a0, <4 x float> %a1) {
1575 %res = call <4 x float> @llvm.x86.sse.mul.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1576 ret <4 x float> %res
1578 declare <4 x float> @llvm.x86.sse.mul.ss(<4 x float>, <4 x float>) nounwind readnone
1581 define <4 x float> @test_x86_sse_rcp_ps(<4 x float> %a0) {
1583 %res = call <4 x float> @llvm.x86.sse.rcp.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1584 ret <4 x float> %res
1586 declare <4 x float> @llvm.x86.sse.rcp.ps(<4 x float>) nounwind readnone
1589 define <4 x float> @test_x86_sse_rcp_ss(<4 x float> %a0) {
1591 %res = call <4 x float> @llvm.x86.sse.rcp.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1592 ret <4 x float> %res
1594 declare <4 x float> @llvm.x86.sse.rcp.ss(<4 x float>) nounwind readnone
1597 define <4 x float> @test_x86_sse_rsqrt_ps(<4 x float> %a0) {
1599 %res = call <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1600 ret <4 x float> %res
1602 declare <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float>) nounwind readnone
1605 define <4 x float> @test_x86_sse_rsqrt_ss(<4 x float> %a0) {
1607 %res = call <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1608 ret <4 x float> %res
1610 declare <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float>) nounwind readnone
1613 define <4 x float> @test_x86_sse_sqrt_ps(<4 x float> %a0) {
1615 %res = call <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1616 ret <4 x float> %res
1618 declare <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float>) nounwind readnone
1621 define <4 x float> @test_x86_sse_sqrt_ss(<4 x float> %a0) {
1623 %res = call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1624 ret <4 x float> %res
1626 declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>) nounwind readnone
1629 define void @test_x86_sse_stmxcsr(i8* %a0) {
1632 call void @llvm.x86.sse.stmxcsr(i8* %a0)
1635 declare void @llvm.x86.sse.stmxcsr(i8*) nounwind
1638 define void @test_x86_sse_storeu_ps(i8* %a0, <4 x float> %a1) {
1641 call void @llvm.x86.sse.storeu.ps(i8* %a0, <4 x float> %a1)
1644 declare void @llvm.x86.sse.storeu.ps(i8*, <4 x float>) nounwind
1647 define <4 x float> @test_x86_sse_sub_ss(<4 x float> %a0, <4 x float> %a1) {
1649 %res = call <4 x float> @llvm.x86.sse.sub.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1650 ret <4 x float> %res
1652 declare <4 x float> @llvm.x86.sse.sub.ss(<4 x float>, <4 x float>) nounwind readnone
1655 define i32 @test_x86_sse_ucomieq_ss(<4 x float> %a0, <4 x float> %a1) {
1659 %res = call i32 @llvm.x86.sse.ucomieq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1662 declare i32 @llvm.x86.sse.ucomieq.ss(<4 x float>, <4 x float>) nounwind readnone
1665 define i32 @test_x86_sse_ucomige_ss(<4 x float> %a0, <4 x float> %a1) {
1669 %res = call i32 @llvm.x86.sse.ucomige.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1672 declare i32 @llvm.x86.sse.ucomige.ss(<4 x float>, <4 x float>) nounwind readnone
1675 define i32 @test_x86_sse_ucomigt_ss(<4 x float> %a0, <4 x float> %a1) {
1679 %res = call i32 @llvm.x86.sse.ucomigt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1682 declare i32 @llvm.x86.sse.ucomigt.ss(<4 x float>, <4 x float>) nounwind readnone
1685 define i32 @test_x86_sse_ucomile_ss(<4 x float> %a0, <4 x float> %a1) {
1689 %res = call i32 @llvm.x86.sse.ucomile.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1692 declare i32 @llvm.x86.sse.ucomile.ss(<4 x float>, <4 x float>) nounwind readnone
1695 define i32 @test_x86_sse_ucomilt_ss(<4 x float> %a0, <4 x float> %a1) {
1698 %res = call i32 @llvm.x86.sse.ucomilt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1701 declare i32 @llvm.x86.sse.ucomilt.ss(<4 x float>, <4 x float>) nounwind readnone
1704 define i32 @test_x86_sse_ucomineq_ss(<4 x float> %a0, <4 x float> %a1) {
1708 %res = call i32 @llvm.x86.sse.ucomineq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1711 declare i32 @llvm.x86.sse.ucomineq.ss(<4 x float>, <4 x float>) nounwind readnone
1714 define <16 x i8> @test_x86_ssse3_pabs_b_128(<16 x i8> %a0) {
1716 %res = call <16 x i8> @llvm.x86.ssse3.pabs.b.128(<16 x i8> %a0) ; <<16 x i8>> [#uses=1]
1719 declare <16 x i8> @llvm.x86.ssse3.pabs.b.128(<16 x i8>) nounwind readnone
1722 define <4 x i32> @test_x86_ssse3_pabs_d_128(<4 x i32> %a0) {
1724 %res = call <4 x i32> @llvm.x86.ssse3.pabs.d.128(<4 x i32> %a0) ; <<4 x i32>> [#uses=1]
1727 declare <4 x i32> @llvm.x86.ssse3.pabs.d.128(<4 x i32>) nounwind readnone
1730 define <8 x i16> @test_x86_ssse3_pabs_w_128(<8 x i16> %a0) {
1732 %res = call <8 x i16> @llvm.x86.ssse3.pabs.w.128(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
1735 declare <8 x i16> @llvm.x86.ssse3.pabs.w.128(<8 x i16>) nounwind readnone
1738 define <4 x i32> @test_x86_ssse3_phadd_d_128(<4 x i32> %a0, <4 x i32> %a1) {
1740 %res = call <4 x i32> @llvm.x86.ssse3.phadd.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1743 declare <4 x i32> @llvm.x86.ssse3.phadd.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1746 define <4 x i32> @test_x86_ssse3_phadd_sw_128(<4 x i32> %a0, <4 x i32> %a1) {
1748 %res = call <4 x i32> @llvm.x86.ssse3.phadd.sw.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1751 declare <4 x i32> @llvm.x86.ssse3.phadd.sw.128(<4 x i32>, <4 x i32>) nounwind readnone
1754 define <8 x i16> @test_x86_ssse3_phadd_w_128(<8 x i16> %a0, <8 x i16> %a1) {
1756 %res = call <8 x i16> @llvm.x86.ssse3.phadd.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1759 declare <8 x i16> @llvm.x86.ssse3.phadd.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1762 define <4 x i32> @test_x86_ssse3_phsub_d_128(<4 x i32> %a0, <4 x i32> %a1) {
1764 %res = call <4 x i32> @llvm.x86.ssse3.phsub.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1767 declare <4 x i32> @llvm.x86.ssse3.phsub.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1770 define <8 x i16> @test_x86_ssse3_phsub_sw_128(<8 x i16> %a0, <8 x i16> %a1) {
1772 %res = call <8 x i16> @llvm.x86.ssse3.phsub.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1775 declare <8 x i16> @llvm.x86.ssse3.phsub.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1778 define <8 x i16> @test_x86_ssse3_phsub_w_128(<8 x i16> %a0, <8 x i16> %a1) {
1780 %res = call <8 x i16> @llvm.x86.ssse3.phsub.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1783 declare <8 x i16> @llvm.x86.ssse3.phsub.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1786 define <8 x i16> @test_x86_ssse3_pmadd_ub_sw_128(<8 x i16> %a0, <8 x i16> %a1) {
1788 %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]
1791 declare <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1794 define <8 x i16> @test_x86_ssse3_pmul_hr_sw_128(<8 x i16> %a0, <8 x i16> %a1) {
1796 %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]
1799 declare <8 x i16> @llvm.x86.ssse3.pmul.hr.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1802 define <16 x i8> @test_x86_ssse3_pshuf_b_128(<16 x i8> %a0, <16 x i8> %a1) {
1804 %res = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1807 declare <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8>, <16 x i8>) nounwind readnone
1810 define <16 x i8> @test_x86_ssse3_psign_b_128(<16 x i8> %a0, <16 x i8> %a1) {
1812 %res = call <16 x i8> @llvm.x86.ssse3.psign.b.128(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1815 declare <16 x i8> @llvm.x86.ssse3.psign.b.128(<16 x i8>, <16 x i8>) nounwind readnone
1818 define <4 x i32> @test_x86_ssse3_psign_d_128(<4 x i32> %a0, <4 x i32> %a1) {
1820 %res = call <4 x i32> @llvm.x86.ssse3.psign.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1823 declare <4 x i32> @llvm.x86.ssse3.psign.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1826 define <8 x i16> @test_x86_ssse3_psign_w_128(<8 x i16> %a0, <8 x i16> %a1) {
1828 %res = call <8 x i16> @llvm.x86.ssse3.psign.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1831 declare <8 x i16> @llvm.x86.ssse3.psign.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1834 define <4 x double> @test_x86_avx_addsub_pd_256(<4 x double> %a0, <4 x double> %a1) {
1836 %res = call <4 x double> @llvm.x86.avx.addsub.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1837 ret <4 x double> %res
1839 declare <4 x double> @llvm.x86.avx.addsub.pd.256(<4 x double>, <4 x double>) nounwind readnone
1842 define <8 x float> @test_x86_avx_addsub_ps_256(<8 x float> %a0, <8 x float> %a1) {
1844 %res = call <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
1845 ret <8 x float> %res
1847 declare <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float>, <8 x float>) nounwind readnone
1850 define <4 x double> @test_x86_avx_blend_pd_256(<4 x double> %a0, <4 x double> %a1) {
1852 %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]
1853 ret <4 x double> %res
1855 declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i32) nounwind readnone
1858 define <8 x float> @test_x86_avx_blend_ps_256(<8 x float> %a0, <8 x float> %a1) {
1860 %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]
1861 ret <8 x float> %res
1863 declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
1866 define <4 x double> @test_x86_avx_blendv_pd_256(<4 x double> %a0, <4 x double> %a1, <4 x double> %a2) {
1868 %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]
1869 ret <4 x double> %res
1871 declare <4 x double> @llvm.x86.avx.blendv.pd.256(<4 x double>, <4 x double>, <4 x double>) nounwind readnone
1874 define <8 x float> @test_x86_avx_blendv_ps_256(<8 x float> %a0, <8 x float> %a1, <8 x float> %a2) {
1876 %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]
1877 ret <8 x float> %res
1879 declare <8 x float> @llvm.x86.avx.blendv.ps.256(<8 x float>, <8 x float>, <8 x float>) nounwind readnone
1882 define <4 x double> @test_x86_avx_cmp_pd_256(<4 x double> %a0, <4 x double> %a1) {
1884 %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]
1885 ret <4 x double> %res
1887 declare <4 x double> @llvm.x86.avx.cmp.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone
1890 define <8 x float> @test_x86_avx_cmp_ps_256(<8 x float> %a0, <8 x float> %a1) {
1892 %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]
1893 ret <8 x float> %res
1895 declare <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
1898 define <4 x float> @test_x86_avx_cvt_pd2_ps_256(<4 x double> %a0) {
1900 %res = call <4 x float> @llvm.x86.avx.cvt.pd2.ps.256(<4 x double> %a0) ; <<4 x float>> [#uses=1]
1901 ret <4 x float> %res
1903 declare <4 x float> @llvm.x86.avx.cvt.pd2.ps.256(<4 x double>) nounwind readnone
1906 define <4 x i32> @test_x86_avx_cvt_pd2dq_256(<4 x double> %a0) {
1908 %res = call <4 x i32> @llvm.x86.avx.cvt.pd2dq.256(<4 x double> %a0) ; <<4 x i32>> [#uses=1]
1911 declare <4 x i32> @llvm.x86.avx.cvt.pd2dq.256(<4 x double>) nounwind readnone
1914 define <4 x double> @test_x86_avx_cvt_ps2_pd_256(<4 x float> %a0) {
1916 %res = call <4 x double> @llvm.x86.avx.cvt.ps2.pd.256(<4 x float> %a0) ; <<4 x double>> [#uses=1]
1917 ret <4 x double> %res
1919 declare <4 x double> @llvm.x86.avx.cvt.ps2.pd.256(<4 x float>) nounwind readnone
1922 define <8 x i32> @test_x86_avx_cvt_ps2dq_256(<8 x float> %a0) {
1924 %res = call <8 x i32> @llvm.x86.avx.cvt.ps2dq.256(<8 x float> %a0) ; <<8 x i32>> [#uses=1]
1927 declare <8 x i32> @llvm.x86.avx.cvt.ps2dq.256(<8 x float>) nounwind readnone
1930 define <4 x double> @test_x86_avx_cvtdq2_pd_256(<4 x i32> %a0) {
1932 %res = call <4 x double> @llvm.x86.avx.cvtdq2.pd.256(<4 x i32> %a0) ; <<4 x double>> [#uses=1]
1933 ret <4 x double> %res
1935 declare <4 x double> @llvm.x86.avx.cvtdq2.pd.256(<4 x i32>) nounwind readnone
1938 define <8 x float> @test_x86_avx_cvtdq2_ps_256(<8 x i32> %a0) {
1940 %res = call <8 x float> @llvm.x86.avx.cvtdq2.ps.256(<8 x i32> %a0) ; <<8 x float>> [#uses=1]
1941 ret <8 x float> %res
1943 declare <8 x float> @llvm.x86.avx.cvtdq2.ps.256(<8 x i32>) nounwind readnone
1946 define <4 x i32> @test_x86_avx_cvtt_pd2dq_256(<4 x double> %a0) {
1947 ; CHECK: vcvttpd2dqy
1948 %res = call <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double> %a0) ; <<4 x i32>> [#uses=1]
1951 declare <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double>) nounwind readnone
1954 define <8 x i32> @test_x86_avx_cvtt_ps2dq_256(<8 x float> %a0) {
1956 %res = call <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float> %a0) ; <<8 x i32>> [#uses=1]
1959 declare <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float>) nounwind readnone
1962 define <8 x float> @test_x86_avx_dp_ps_256(<8 x float> %a0, <8 x float> %a1) {
1964 %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]
1965 ret <8 x float> %res
1967 declare <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
1970 define <4 x double> @test_x86_avx_hadd_pd_256(<4 x double> %a0, <4 x double> %a1) {
1972 %res = call <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1973 ret <4 x double> %res
1975 declare <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double>, <4 x double>) nounwind readnone
1978 define <8 x float> @test_x86_avx_hadd_ps_256(<8 x float> %a0, <8 x float> %a1) {
1980 %res = call <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
1981 ret <8 x float> %res
1983 declare <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float>, <8 x float>) nounwind readnone
1986 define <4 x double> @test_x86_avx_hsub_pd_256(<4 x double> %a0, <4 x double> %a1) {
1988 %res = call <4 x double> @llvm.x86.avx.hsub.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1989 ret <4 x double> %res
1991 declare <4 x double> @llvm.x86.avx.hsub.pd.256(<4 x double>, <4 x double>) nounwind readnone
1994 define <8 x float> @test_x86_avx_hsub_ps_256(<8 x float> %a0, <8 x float> %a1) {
1996 %res = call <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
1997 ret <8 x float> %res
1999 declare <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float>, <8 x float>) nounwind readnone
2002 define <32 x i8> @test_x86_avx_ldu_dq_256(i8* %a0) {
2004 %res = call <32 x i8> @llvm.x86.avx.ldu.dq.256(i8* %a0) ; <<32 x i8>> [#uses=1]
2007 declare <32 x i8> @llvm.x86.avx.ldu.dq.256(i8*) nounwind readonly
2010 define <32 x i8> @test_x86_avx_loadu_dq_256(i8* %a0) {
2012 %res = call <32 x i8> @llvm.x86.avx.loadu.dq.256(i8* %a0) ; <<32 x i8>> [#uses=1]
2015 declare <32 x i8> @llvm.x86.avx.loadu.dq.256(i8*) nounwind readonly
2018 define <4 x double> @test_x86_avx_loadu_pd_256(i8* %a0) {
2020 %res = call <4 x double> @llvm.x86.avx.loadu.pd.256(i8* %a0) ; <<4 x double>> [#uses=1]
2021 ret <4 x double> %res
2023 declare <4 x double> @llvm.x86.avx.loadu.pd.256(i8*) nounwind readonly
2026 define <8 x float> @test_x86_avx_loadu_ps_256(i8* %a0) {
2028 %res = call <8 x float> @llvm.x86.avx.loadu.ps.256(i8* %a0) ; <<8 x float>> [#uses=1]
2029 ret <8 x float> %res
2031 declare <8 x float> @llvm.x86.avx.loadu.ps.256(i8*) nounwind readonly
2034 define <2 x double> @test_x86_avx_maskload_pd(i8* %a0, <2 x double> %a1) {
2036 %res = call <2 x double> @llvm.x86.avx.maskload.pd(i8* %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
2037 ret <2 x double> %res
2039 declare <2 x double> @llvm.x86.avx.maskload.pd(i8*, <2 x double>) nounwind readonly
2042 define <4 x double> @test_x86_avx_maskload_pd_256(i8* %a0, <4 x double> %a1) {
2044 %res = call <4 x double> @llvm.x86.avx.maskload.pd.256(i8* %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2045 ret <4 x double> %res
2047 declare <4 x double> @llvm.x86.avx.maskload.pd.256(i8*, <4 x double>) nounwind readonly
2050 define <4 x float> @test_x86_avx_maskload_ps(i8* %a0, <4 x float> %a1) {
2052 %res = call <4 x float> @llvm.x86.avx.maskload.ps(i8* %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
2053 ret <4 x float> %res
2055 declare <4 x float> @llvm.x86.avx.maskload.ps(i8*, <4 x float>) nounwind readonly
2058 define <8 x float> @test_x86_avx_maskload_ps_256(i8* %a0, <8 x float> %a1) {
2060 %res = call <8 x float> @llvm.x86.avx.maskload.ps.256(i8* %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2061 ret <8 x float> %res
2063 declare <8 x float> @llvm.x86.avx.maskload.ps.256(i8*, <8 x float>) nounwind readonly
2066 define void @test_x86_avx_maskstore_pd(i8* %a0, <2 x double> %a1, <2 x double> %a2) {
2068 call void @llvm.x86.avx.maskstore.pd(i8* %a0, <2 x double> %a1, <2 x double> %a2)
2071 declare void @llvm.x86.avx.maskstore.pd(i8*, <2 x double>, <2 x double>) nounwind
2074 define void @test_x86_avx_maskstore_pd_256(i8* %a0, <4 x double> %a1, <4 x double> %a2) {
2076 call void @llvm.x86.avx.maskstore.pd.256(i8* %a0, <4 x double> %a1, <4 x double> %a2)
2079 declare void @llvm.x86.avx.maskstore.pd.256(i8*, <4 x double>, <4 x double>) nounwind
2082 define void @test_x86_avx_maskstore_ps(i8* %a0, <4 x float> %a1, <4 x float> %a2) {
2084 call void @llvm.x86.avx.maskstore.ps(i8* %a0, <4 x float> %a1, <4 x float> %a2)
2087 declare void @llvm.x86.avx.maskstore.ps(i8*, <4 x float>, <4 x float>) nounwind
2090 define void @test_x86_avx_maskstore_ps_256(i8* %a0, <8 x float> %a1, <8 x float> %a2) {
2092 call void @llvm.x86.avx.maskstore.ps.256(i8* %a0, <8 x float> %a1, <8 x float> %a2)
2095 declare void @llvm.x86.avx.maskstore.ps.256(i8*, <8 x float>, <8 x float>) nounwind
2098 define <4 x double> @test_x86_avx_max_pd_256(<4 x double> %a0, <4 x double> %a1) {
2100 %res = call <4 x double> @llvm.x86.avx.max.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2101 ret <4 x double> %res
2103 declare <4 x double> @llvm.x86.avx.max.pd.256(<4 x double>, <4 x double>) nounwind readnone
2106 define <8 x float> @test_x86_avx_max_ps_256(<8 x float> %a0, <8 x float> %a1) {
2108 %res = call <8 x float> @llvm.x86.avx.max.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2109 ret <8 x float> %res
2111 declare <8 x float> @llvm.x86.avx.max.ps.256(<8 x float>, <8 x float>) nounwind readnone
2114 define <4 x double> @test_x86_avx_min_pd_256(<4 x double> %a0, <4 x double> %a1) {
2116 %res = call <4 x double> @llvm.x86.avx.min.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2117 ret <4 x double> %res
2119 declare <4 x double> @llvm.x86.avx.min.pd.256(<4 x double>, <4 x double>) nounwind readnone
2122 define <8 x float> @test_x86_avx_min_ps_256(<8 x float> %a0, <8 x float> %a1) {
2124 %res = call <8 x float> @llvm.x86.avx.min.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2125 ret <8 x float> %res
2127 declare <8 x float> @llvm.x86.avx.min.ps.256(<8 x float>, <8 x float>) nounwind readnone
2130 define i32 @test_x86_avx_movmsk_pd_256(<4 x double> %a0) {
2132 %res = call i32 @llvm.x86.avx.movmsk.pd.256(<4 x double> %a0) ; <i32> [#uses=1]
2135 declare i32 @llvm.x86.avx.movmsk.pd.256(<4 x double>) nounwind readnone
2138 define i32 @test_x86_avx_movmsk_ps_256(<8 x float> %a0) {
2140 %res = call i32 @llvm.x86.avx.movmsk.ps.256(<8 x float> %a0) ; <i32> [#uses=1]
2143 declare i32 @llvm.x86.avx.movmsk.ps.256(<8 x float>) nounwind readnone
2146 define void @test_x86_avx_movnt_dq_256(i8* %a0, <4 x i64> %a1) {
2148 call void @llvm.x86.avx.movnt.dq.256(i8* %a0, <4 x i64> %a1)
2151 declare void @llvm.x86.avx.movnt.dq.256(i8*, <4 x i64>) nounwind
2154 define void @test_x86_avx_movnt_pd_256(i8* %a0, <4 x double> %a1) {
2156 call void @llvm.x86.avx.movnt.pd.256(i8* %a0, <4 x double> %a1)
2159 declare void @llvm.x86.avx.movnt.pd.256(i8*, <4 x double>) nounwind
2162 define void @test_x86_avx_movnt_ps_256(i8* %a0, <8 x float> %a1) {
2164 call void @llvm.x86.avx.movnt.ps.256(i8* %a0, <8 x float> %a1)
2167 declare void @llvm.x86.avx.movnt.ps.256(i8*, <8 x float>) nounwind
2170 define i32 @test_x86_avx_ptestc_256(<4 x i64> %a0, <4 x i64> %a1) {
2173 %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2176 declare i32 @llvm.x86.avx.ptestc.256(<4 x i64>, <4 x i64>) nounwind readnone
2179 define i32 @test_x86_avx_ptestnzc_256(<4 x i64> %a0, <4 x i64> %a1) {
2183 %res = call i32 @llvm.x86.avx.ptestnzc.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2186 declare i32 @llvm.x86.avx.ptestnzc.256(<4 x i64>, <4 x i64>) nounwind readnone
2189 define i32 @test_x86_avx_ptestz_256(<4 x i64> %a0, <4 x i64> %a1) {
2193 %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2196 declare i32 @llvm.x86.avx.ptestz.256(<4 x i64>, <4 x i64>) nounwind readnone
2199 define <8 x float> @test_x86_avx_rcp_ps_256(<8 x float> %a0) {
2201 %res = call <8 x float> @llvm.x86.avx.rcp.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2202 ret <8 x float> %res
2204 declare <8 x float> @llvm.x86.avx.rcp.ps.256(<8 x float>) nounwind readnone
2207 define <4 x double> @test_x86_avx_round_pd_256(<4 x double> %a0) {
2209 %res = call <4 x double> @llvm.x86.avx.round.pd.256(<4 x double> %a0, i32 7) ; <<4 x double>> [#uses=1]
2210 ret <4 x double> %res
2212 declare <4 x double> @llvm.x86.avx.round.pd.256(<4 x double>, i32) nounwind readnone
2215 define <8 x float> @test_x86_avx_round_ps_256(<8 x float> %a0) {
2217 %res = call <8 x float> @llvm.x86.avx.round.ps.256(<8 x float> %a0, i32 7) ; <<8 x float>> [#uses=1]
2218 ret <8 x float> %res
2220 declare <8 x float> @llvm.x86.avx.round.ps.256(<8 x float>, i32) nounwind readnone
2223 define <8 x float> @test_x86_avx_rsqrt_ps_256(<8 x float> %a0) {
2225 %res = call <8 x float> @llvm.x86.avx.rsqrt.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2226 ret <8 x float> %res
2228 declare <8 x float> @llvm.x86.avx.rsqrt.ps.256(<8 x float>) nounwind readnone
2231 define <4 x double> @test_x86_avx_sqrt_pd_256(<4 x double> %a0) {
2233 %res = call <4 x double> @llvm.x86.avx.sqrt.pd.256(<4 x double> %a0) ; <<4 x double>> [#uses=1]
2234 ret <4 x double> %res
2236 declare <4 x double> @llvm.x86.avx.sqrt.pd.256(<4 x double>) nounwind readnone
2239 define <8 x float> @test_x86_avx_sqrt_ps_256(<8 x float> %a0) {
2241 %res = call <8 x float> @llvm.x86.avx.sqrt.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2242 ret <8 x float> %res
2244 declare <8 x float> @llvm.x86.avx.sqrt.ps.256(<8 x float>) nounwind readnone
2247 define void @test_x86_avx_storeu_dq_256(i8* %a0, <32 x i8> %a1) {
2249 call void @llvm.x86.avx.storeu.dq.256(i8* %a0, <32 x i8> %a1)
2252 declare void @llvm.x86.avx.storeu.dq.256(i8*, <32 x i8>) nounwind
2255 define void @test_x86_avx_storeu_pd_256(i8* %a0, <4 x double> %a1) {
2257 call void @llvm.x86.avx.storeu.pd.256(i8* %a0, <4 x double> %a1)
2260 declare void @llvm.x86.avx.storeu.pd.256(i8*, <4 x double>) nounwind
2263 define void @test_x86_avx_storeu_ps_256(i8* %a0, <8 x float> %a1) {
2265 call void @llvm.x86.avx.storeu.ps.256(i8* %a0, <8 x float> %a1)
2268 declare void @llvm.x86.avx.storeu.ps.256(i8*, <8 x float>) nounwind
2271 define <4 x double> @test_x86_avx_vbroadcast_sd_256(i8* %a0) {
2272 ; CHECK: vbroadcastsd
2273 %res = call <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8* %a0) ; <<4 x double>> [#uses=1]
2274 ret <4 x double> %res
2276 declare <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8*) nounwind readonly
2279 define <4 x double> @test_x86_avx_vbroadcastf128_pd_256(i8* %a0) {
2280 ; CHECK: vbroadcastf128
2281 %res = call <4 x double> @llvm.x86.avx.vbroadcastf128.pd.256(i8* %a0) ; <<4 x double>> [#uses=1]
2282 ret <4 x double> %res
2284 declare <4 x double> @llvm.x86.avx.vbroadcastf128.pd.256(i8*) nounwind readonly
2287 define <8 x float> @test_x86_avx_vbroadcastf128_ps_256(i8* %a0) {
2288 ; CHECK: vbroadcastf128
2289 %res = call <8 x float> @llvm.x86.avx.vbroadcastf128.ps.256(i8* %a0) ; <<8 x float>> [#uses=1]
2290 ret <8 x float> %res
2292 declare <8 x float> @llvm.x86.avx.vbroadcastf128.ps.256(i8*) nounwind readonly
2295 define <4 x float> @test_x86_avx_vbroadcastss(i8* %a0) {
2296 ; CHECK: vbroadcastss
2297 %res = call <4 x float> @llvm.x86.avx.vbroadcastss(i8* %a0) ; <<4 x float>> [#uses=1]
2298 ret <4 x float> %res
2300 declare <4 x float> @llvm.x86.avx.vbroadcastss(i8*) nounwind readonly
2303 define <8 x float> @test_x86_avx_vbroadcastss_256(i8* %a0) {
2304 ; CHECK: vbroadcastss
2305 %res = call <8 x float> @llvm.x86.avx.vbroadcastss.256(i8* %a0) ; <<8 x float>> [#uses=1]
2306 ret <8 x float> %res
2308 declare <8 x float> @llvm.x86.avx.vbroadcastss.256(i8*) nounwind readonly
2311 define <2 x double> @test_x86_avx_vextractf128_pd_256(<4 x double> %a0) {
2312 ; CHECK: vextractf128
2313 %res = call <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double> %a0, i8 7) ; <<2 x double>> [#uses=1]
2314 ret <2 x double> %res
2316 declare <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double>, i8) nounwind readnone
2319 define <4 x float> @test_x86_avx_vextractf128_ps_256(<8 x float> %a0) {
2320 ; CHECK: vextractf128
2321 %res = call <4 x float> @llvm.x86.avx.vextractf128.ps.256(<8 x float> %a0, i8 7) ; <<4 x float>> [#uses=1]
2322 ret <4 x float> %res
2324 declare <4 x float> @llvm.x86.avx.vextractf128.ps.256(<8 x float>, i8) nounwind readnone
2327 define <4 x i32> @test_x86_avx_vextractf128_si_256(<8 x i32> %a0) {
2328 ; CHECK: vextractf128
2329 %res = call <4 x i32> @llvm.x86.avx.vextractf128.si.256(<8 x i32> %a0, i8 7) ; <<4 x i32>> [#uses=1]
2332 declare <4 x i32> @llvm.x86.avx.vextractf128.si.256(<8 x i32>, i8) nounwind readnone
2335 define <4 x double> @test_x86_avx_vinsertf128_pd_256(<4 x double> %a0, <2 x double> %a1) {
2336 ; CHECK: vinsertf128
2337 %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]
2338 ret <4 x double> %res
2340 declare <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double>, <2 x double>, i8) nounwind readnone
2343 define <8 x float> @test_x86_avx_vinsertf128_ps_256(<8 x float> %a0, <4 x float> %a1) {
2344 ; CHECK: vinsertf128
2345 %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]
2346 ret <8 x float> %res
2348 declare <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float>, <4 x float>, i8) nounwind readnone
2351 define <8 x i32> @test_x86_avx_vinsertf128_si_256(<8 x i32> %a0, <4 x i32> %a1) {
2352 ; CHECK: vinsertf128
2353 %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]
2356 declare <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32>, <4 x i32>, i8) nounwind readnone
2359 define <4 x double> @test_x86_avx_vperm2f128_pd_256(<4 x double> %a0, <4 x double> %a1) {
2361 %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]
2362 ret <4 x double> %res
2364 declare <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone
2367 define <8 x float> @test_x86_avx_vperm2f128_ps_256(<8 x float> %a0, <8 x float> %a1) {
2369 %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]
2370 ret <8 x float> %res
2372 declare <8 x float> @llvm.x86.avx.vperm2f128.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
2375 define <8 x i32> @test_x86_avx_vperm2f128_si_256(<8 x i32> %a0, <8 x i32> %a1) {
2377 %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]
2380 declare <8 x i32> @llvm.x86.avx.vperm2f128.si.256(<8 x i32>, <8 x i32>, i8) nounwind readnone
2383 define <2 x double> @test_x86_avx_vpermil_pd(<2 x double> %a0) {
2385 %res = call <2 x double> @llvm.x86.avx.vpermil.pd(<2 x double> %a0, i8 7) ; <<2 x double>> [#uses=1]
2386 ret <2 x double> %res
2388 declare <2 x double> @llvm.x86.avx.vpermil.pd(<2 x double>, i8) nounwind readnone
2391 define <4 x double> @test_x86_avx_vpermil_pd_256(<4 x double> %a0) {
2393 %res = call <4 x double> @llvm.x86.avx.vpermil.pd.256(<4 x double> %a0, i8 7) ; <<4 x double>> [#uses=1]
2394 ret <4 x double> %res
2396 declare <4 x double> @llvm.x86.avx.vpermil.pd.256(<4 x double>, i8) nounwind readnone
2399 define <4 x float> @test_x86_avx_vpermil_ps(<4 x float> %a0) {
2401 %res = call <4 x float> @llvm.x86.avx.vpermil.ps(<4 x float> %a0, i8 7) ; <<4 x float>> [#uses=1]
2402 ret <4 x float> %res
2404 declare <4 x float> @llvm.x86.avx.vpermil.ps(<4 x float>, i8) nounwind readnone
2407 define <8 x float> @test_x86_avx_vpermil_ps_256(<8 x float> %a0) {
2409 %res = call <8 x float> @llvm.x86.avx.vpermil.ps.256(<8 x float> %a0, i8 7) ; <<8 x float>> [#uses=1]
2410 ret <8 x float> %res
2412 declare <8 x float> @llvm.x86.avx.vpermil.ps.256(<8 x float>, i8) nounwind readnone
2415 define <2 x double> @test_x86_avx_vpermilvar_pd(<2 x double> %a0, <2 x i64> %a1) {
2417 %res = call <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double> %a0, <2 x i64> %a1) ; <<2 x double>> [#uses=1]
2418 ret <2 x double> %res
2420 declare <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double>, <2 x i64>) nounwind readnone
2423 define <4 x double> @test_x86_avx_vpermilvar_pd_256(<4 x double> %a0, <4 x i64> %a1) {
2425 %res = call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %a0, <4 x i64> %a1) ; <<4 x double>> [#uses=1]
2426 ret <4 x double> %res
2428 declare <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double>, <4 x i64>) nounwind readnone
2431 define <4 x float> @test_x86_avx_vpermilvar_ps(<4 x float> %a0, <4 x i32> %a1) {
2433 %res = call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> %a1) ; <<4 x float>> [#uses=1]
2434 ret <4 x float> %res
2436 declare <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float>, <4 x i32>) nounwind readnone
2439 define <8 x float> @test_x86_avx_vpermilvar_ps_256(<8 x float> %a0, <8 x i32> %a1) {
2441 %res = call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float> %a0, <8 x i32> %a1) ; <<8 x float>> [#uses=1]
2442 ret <8 x float> %res
2444 declare <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float>, <8 x i32>) nounwind readnone
2447 define i32 @test_x86_avx_vtestc_pd(<2 x double> %a0, <2 x double> %a1) {
2450 %res = call i32 @llvm.x86.avx.vtestc.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2453 declare i32 @llvm.x86.avx.vtestc.pd(<2 x double>, <2 x double>) nounwind readnone
2456 define i32 @test_x86_avx_vtestc_pd_256(<4 x double> %a0, <4 x double> %a1) {
2459 %res = call i32 @llvm.x86.avx.vtestc.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2462 declare i32 @llvm.x86.avx.vtestc.pd.256(<4 x double>, <4 x double>) nounwind readnone
2465 define i32 @test_x86_avx_vtestc_ps(<4 x float> %a0, <4 x float> %a1) {
2468 %res = call i32 @llvm.x86.avx.vtestc.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2471 declare i32 @llvm.x86.avx.vtestc.ps(<4 x float>, <4 x float>) nounwind readnone
2474 define i32 @test_x86_avx_vtestc_ps_256(<8 x float> %a0, <8 x float> %a1) {
2477 %res = call i32 @llvm.x86.avx.vtestc.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2480 declare i32 @llvm.x86.avx.vtestc.ps.256(<8 x float>, <8 x float>) nounwind readnone
2483 define i32 @test_x86_avx_vtestnzc_pd(<2 x double> %a0, <2 x double> %a1) {
2487 %res = call i32 @llvm.x86.avx.vtestnzc.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2490 declare i32 @llvm.x86.avx.vtestnzc.pd(<2 x double>, <2 x double>) nounwind readnone
2493 define i32 @test_x86_avx_vtestnzc_pd_256(<4 x double> %a0, <4 x double> %a1) {
2497 %res = call i32 @llvm.x86.avx.vtestnzc.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2500 declare i32 @llvm.x86.avx.vtestnzc.pd.256(<4 x double>, <4 x double>) nounwind readnone
2503 define i32 @test_x86_avx_vtestnzc_ps(<4 x float> %a0, <4 x float> %a1) {
2507 %res = call i32 @llvm.x86.avx.vtestnzc.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2510 declare i32 @llvm.x86.avx.vtestnzc.ps(<4 x float>, <4 x float>) nounwind readnone
2513 define i32 @test_x86_avx_vtestnzc_ps_256(<8 x float> %a0, <8 x float> %a1) {
2517 %res = call i32 @llvm.x86.avx.vtestnzc.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2520 declare i32 @llvm.x86.avx.vtestnzc.ps.256(<8 x float>, <8 x float>) nounwind readnone
2523 define i32 @test_x86_avx_vtestz_pd(<2 x double> %a0, <2 x double> %a1) {
2527 %res = call i32 @llvm.x86.avx.vtestz.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2530 declare i32 @llvm.x86.avx.vtestz.pd(<2 x double>, <2 x double>) nounwind readnone
2533 define i32 @test_x86_avx_vtestz_pd_256(<4 x double> %a0, <4 x double> %a1) {
2537 %res = call i32 @llvm.x86.avx.vtestz.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2540 declare i32 @llvm.x86.avx.vtestz.pd.256(<4 x double>, <4 x double>) nounwind readnone
2543 define i32 @test_x86_avx_vtestz_ps(<4 x float> %a0, <4 x float> %a1) {
2547 %res = call i32 @llvm.x86.avx.vtestz.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2550 declare i32 @llvm.x86.avx.vtestz.ps(<4 x float>, <4 x float>) nounwind readnone
2553 define i32 @test_x86_avx_vtestz_ps_256(<8 x float> %a0, <8 x float> %a1) {
2557 %res = call i32 @llvm.x86.avx.vtestz.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2560 declare i32 @llvm.x86.avx.vtestz.ps.256(<8 x float>, <8 x float>) nounwind readnone
2563 define void @test_x86_avx_vzeroall() {
2565 call void @llvm.x86.avx.vzeroall()
2568 declare void @llvm.x86.avx.vzeroall() nounwind
2571 define void @test_x86_avx_vzeroupper() {
2573 call void @llvm.x86.avx.vzeroupper()
2576 declare void @llvm.x86.avx.vzeroupper() nounwind