Merging r261039:

[oota-llvm.git] / test / CodeGen / X86 / avx2-intrinsics-x86.ll

diff --git a/test/CodeGen/X86/avx2-intrinsics-x86.ll b/test/CodeGen/X86/avx2-intrinsics-x86.ll
index b7e2b7412ff6048d465914b81171ac0db21b15a9..606aca9dc02b63262ca2671d0036367abc2298e6 100644 (file)
--- a/test/CodeGen/X86/avx2-intrinsics-x86.ll
+++ b/test/CodeGen/X86/avx2-intrinsics-x86.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mcpu=core-avx2 -mattr=avx2 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mattr=avx2 | FileCheck %s
 
 define <16 x i16> @test_x86_avx2_packssdw(<8 x i32> %a0, <8 x i32> %a1) {
   ; CHECK: vpackssdw
@@ -641,30 +641,6 @@ define <4 x i64> @test_x86_avx2_pmul.dq(<8 x i32> %a0, <8 x i32> %a1) {
 declare <4 x i64> @llvm.x86.avx2.pmul.dq(<8 x i32>, <8 x i32>) nounwind readnone
 
 
-define <4 x double> @test_x86_avx2_vbroadcast_sd_pd_256(<2 x double> %a0) {
-  ; CHECK: vbroadcastsd
-  %res = call <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double> %a0) ; <<4 x double>> [#uses=1]
-  ret <4 x double> %res
-}
-declare <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double>) nounwind readonly
-
-
-define <4 x float> @test_x86_avx2_vbroadcast_ss_ps(<4 x float> %a0) {
-  ; CHECK: vbroadcastss
-  %res = call <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
-  ret <4 x float> %res
-}
-declare <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float>) nounwind readonly
-
-
-define <8 x float> @test_x86_avx2_vbroadcast_ss_ps_256(<4 x float> %a0) {
-  ; CHECK: vbroadcastss
-  %res = call <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float> %a0) ; <<8 x float>> [#uses=1]
-  ret <8 x float> %res
-}
-declare <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float>) nounwind readonly
-
-
 define <4 x i32> @test_x86_avx2_pblendd_128(<4 x i32> %a0, <4 x i32> %a1) {
   ; CHECK: vpblendd
   %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i8 7) ; <<4 x i32>> [#uses=1]
@@ -681,84 +657,26 @@ define <8 x i32> @test_x86_avx2_pblendd_256(<8 x i32> %a0, <8 x i32> %a1) {
 declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i8) nounwind readnone
 
 
-define <16 x i8> @test_x86_avx2_pbroadcastb_128(<16 x i8> %a0) {
-  ; CHECK: vpbroadcastb
-  %res = call <16 x i8> @llvm.x86.avx2.pbroadcastb.128(<16 x i8> %a0) ; <<16 x i8>> [#uses=1]
-  ret <16 x i8> %res
-}
-declare <16 x i8> @llvm.x86.avx2.pbroadcastb.128(<16 x i8>) nounwind readonly
-
-
-define <32 x i8> @test_x86_avx2_pbroadcastb_256(<16 x i8> %a0) {
-  ; CHECK: vpbroadcastb
-  %res = call <32 x i8> @llvm.x86.avx2.pbroadcastb.256(<16 x i8> %a0) ; <<32 x i8>> [#uses=1]
-  ret <32 x i8> %res
-}
-declare <32 x i8> @llvm.x86.avx2.pbroadcastb.256(<16 x i8>) nounwind readonly
-
-
-define <8 x i16> @test_x86_avx2_pbroadcastw_128(<8 x i16> %a0) {
-  ; CHECK: vpbroadcastw
-  %res = call <8 x i16> @llvm.x86.avx2.pbroadcastw.128(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
-  ret <8 x i16> %res
-}
-declare <8 x i16> @llvm.x86.avx2.pbroadcastw.128(<8 x i16>) nounwind readonly
-
-
-define <16 x i16> @test_x86_avx2_pbroadcastw_256(<8 x i16> %a0) {
-  ; CHECK: vpbroadcastw
-  %res = call <16 x i16> @llvm.x86.avx2.pbroadcastw.256(<8 x i16> %a0) ; <<16 x i16>> [#uses=1]
-  ret <16 x i16> %res
-}
-declare <16 x i16> @llvm.x86.avx2.pbroadcastw.256(<8 x i16>) nounwind readonly
-
-
-define <4 x i32> @test_x86_avx2_pbroadcastd_128(<4 x i32> %a0) {
-  ; CHECK: vbroadcastss
-  %res = call <4 x i32> @llvm.x86.avx2.pbroadcastd.128(<4 x i32> %a0) ; <<4 x i32>> [#uses=1]
-  ret <4 x i32> %res
-}
-declare <4 x i32> @llvm.x86.avx2.pbroadcastd.128(<4 x i32>) nounwind readonly
-
-
-define <8 x i32> @test_x86_avx2_pbroadcastd_256(<4 x i32> %a0) {
-  ; CHECK: vbroadcastss {{[^,]+}}, %ymm{{[0-9]+}}
-  %res = call <8 x i32> @llvm.x86.avx2.pbroadcastd.256(<4 x i32> %a0) ; <<8 x i32>> [#uses=1]
-  ret <8 x i32> %res
-}
-declare <8 x i32> @llvm.x86.avx2.pbroadcastd.256(<4 x i32>) nounwind readonly
-
-
-define <2 x i64> @test_x86_avx2_pbroadcastq_128(<2 x i64> %a0) {
-  ; CHECK: vpbroadcastq
-  %res = call <2 x i64> @llvm.x86.avx2.pbroadcastq.128(<2 x i64> %a0) ; <<2 x i64>> [#uses=1]
-  ret <2 x i64> %res
-}
-declare <2 x i64> @llvm.x86.avx2.pbroadcastq.128(<2 x i64>) nounwind readonly
-
-
-define <4 x i64> @test_x86_avx2_pbroadcastq_256(<2 x i64> %a0) {
-  ; CHECK: vbroadcastsd {{[^,]+}}, %ymm{{[0-9]+}}
-  %res = call <4 x i64> @llvm.x86.avx2.pbroadcastq.256(<2 x i64> %a0) ; <<4 x i64>> [#uses=1]
-  ret <4 x i64> %res
-}
-declare <4 x i64> @llvm.x86.avx2.pbroadcastq.256(<2 x i64>) nounwind readonly
-
-
 define <8 x i32> @test_x86_avx2_permd(<8 x i32> %a0, <8 x i32> %a1) {
-  ; CHECK: vpermd
+  ; Check that the arguments are swapped between the intrinsic definition
+  ; and its lowering. Indeed, the offsets are the first source in
+  ; the instruction.
+  ; CHECK: vpermd %ymm0, %ymm1, %ymm0
   %res = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
   ret <8 x i32> %res
 }
 declare <8 x i32> @llvm.x86.avx2.permd(<8 x i32>, <8 x i32>) nounwind readonly
 
 
-define <8 x float> @test_x86_avx2_permps(<8 x float> %a0, <8 x float> %a1) {
-  ; CHECK: vpermps
-  %res = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
+define <8 x float> @test_x86_avx2_permps(<8 x float> %a0, <8 x i32> %a1) {
+  ; Check that the arguments are swapped between the intrinsic definition
+  ; and its lowering. Indeed, the offsets are the first source in
+  ; the instruction.
+  ; CHECK: vpermps %ymm0, %ymm1, %ymm0
+  %res = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> %a1) ; <<8 x float>> [#uses=1]
   ret <8 x float> %res
 }
-declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x float>) nounwind readonly
+declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x i32>) nounwind readonly
 
 
 define <4 x i64> @test_x86_avx2_vperm2i128(<4 x i64> %a0, <4 x i64> %a1) {
@@ -769,22 +687,6 @@ define <4 x i64> @test_x86_avx2_vperm2i128(<4 x i64> %a0, <4 x i64> %a1) {
 declare <4 x i64> @llvm.x86.avx2.vperm2i128(<4 x i64>, <4 x i64>, i8) nounwind readonly
 
 
-define <2 x i64> @test_x86_avx2_vextracti128(<4 x i64> %a0) {
-  ; CHECK: vextracti128
-  %res = call <2 x i64> @llvm.x86.avx2.vextracti128(<4 x i64> %a0, i8 7) ; <<2 x i64>> [#uses=1]
-  ret <2 x i64> %res
-}
-declare <2 x i64> @llvm.x86.avx2.vextracti128(<4 x i64>, i8) nounwind readnone
-
-
-define <4 x i64> @test_x86_avx2_vinserti128(<4 x i64> %a0, <2 x i64> %a1) {
-  ; CHECK: vinserti128
-  %res = call <4 x i64> @llvm.x86.avx2.vinserti128(<4 x i64> %a0, <2 x i64> %a1, i8 7) ; <<4 x i64>> [#uses=1]
-  ret <4 x i64> %res
-}
-declare <4 x i64> @llvm.x86.avx2.vinserti128(<4 x i64>, <2 x i64>, i8) nounwind readnone
-
-
 define <2 x i64> @test_x86_avx2_maskload_q(i8* %a0, <2 x i64> %a1) {
   ; CHECK: vpmaskmovq
   %res = call <2 x i64> @llvm.x86.avx2.maskload.q(i8* %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]