Revert "Decouple dllexport/dllimport from linkage"

[oota-llvm.git] / test / CodeGen / X86 / avx-intel-ocl.ll

diff --git a/test/CodeGen/X86/avx-intel-ocl.ll b/test/CodeGen/X86/avx-intel-ocl.ll
index 4b7835b1902eb9e74b367e669d94780c8e81d178..7337815a39aced1a62ebbf5c240ea508e63494b3 100644 (file)
--- a/test/CodeGen/X86/avx-intel-ocl.ll
+++ b/test/CodeGen/X86/avx-intel-ocl.ll
@@ -32,7 +32,7 @@ declare i32 @func_int(i32, i32)
 define <16 x float> @testf16_inp(<16 x float> %a, <16 x float> %b) nounwind {
   %y = alloca <16 x float>, align 16
   %x = fadd <16 x float> %a, %b
-  %1 = call intel_ocl_bicc <16 x float> @func_float16_ptr(<16 x float> %x, <16 x float>* %y) 
+  %1 = call intel_ocl_bicc <16 x float> @func_float16_ptr(<16 x float> %x, <16 x float>* %y)
   %2 = load <16 x float>* %y, align 16
   %3 = fadd <16 x float> %2, %1
   ret <16 x float> %3
@@ -43,21 +43,21 @@ define <16 x float> @testf16_inp(<16 x float> %a, <16 x float> %b) nounwind {
 ; preserved ymm6-ymm15
 ; WIN64: testf16_regs
 ; WIN64: call
-; WIN64: vaddps  {{%ymm[6-7]}}, %ymm0, %ymm0
-; WIN64: vaddps  {{%ymm[6-7]}}, %ymm1, %ymm1
+; WIN64: vaddps  {{%ymm[6-7]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
+; WIN64: vaddps  {{%ymm[6-7]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
 ; WIN64: ret
 
 ; preserved ymm8-ymm15
 ; X64: testf16_regs
 ; X64: call
-; X64: vaddps  {{%ymm[8-9]}}, %ymm0, %ymm0
-; X64: vaddps  {{%ymm[8-9]}}, %ymm1, %ymm1
+; X64: vaddps  {{%ymm[8-9]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
+; X64: vaddps  {{%ymm[8-9]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
 ; X64: ret
 
 define <16 x float> @testf16_regs(<16 x float> %a, <16 x float> %b) nounwind {
   %y = alloca <16 x float>, align 16
   %x = fadd <16 x float> %a, %b
-  %1 = call intel_ocl_bicc <16 x float> @func_float16_ptr(<16 x float> %x, <16 x float>* %y) 
+  %1 = call intel_ocl_bicc <16 x float> @func_float16_ptr(<16 x float> %x, <16 x float>* %y)
   %2 = load <16 x float>* %y, align 16
   %3 = fadd <16 x float> %1, %b
   %4 = fadd <16 x float> %2, %3
@@ -87,23 +87,23 @@ define <16 x float> @testf16_regs(<16 x float> %a, <16 x float> %b) nounwind {
 ; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}}     # 32-byte Reload
 ; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}}     # 32-byte Reload
 
-; X64: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp)  ## 32-byte Spill
-; X64: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp)  ## 32-byte Spill
-; X64: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp)  ## 32-byte Spill
-; X64: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp)  ## 32-byte Spill
-; X64: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp)  ## 32-byte Spill
-; X64: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp)  ## 32-byte Spill
-; X64: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp)  ## 32-byte Spill
-; X64: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp)  ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
 ; X64: call
-; X64: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
-; X64: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
-; X64: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
-; X64: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
-; X64: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
-; X64: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
-; X64: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
-; X64: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
 define intel_ocl_bicc <16 x float> @test_prolog_epilog(<16 x float> %a, <16 x float> %b) nounwind {
    %c = call <16 x float> @func_float16(<16 x float> %a, <16 x float> %b)
    ret <16 x float> %c
@@ -127,3 +127,42 @@ define i32 @test_int(i32 %a, i32 %b) nounwind {
     %c = add i32 %c2, %b
        ret i32 %c
 }
+
+; WIN64: test_float4
+; WIN64-NOT: vzeroupper
+; WIN64: call
+; WIN64-NOT: vzeroupper
+; WIN64: call
+; WIN64: ret
+
+; X64: test_float4
+; X64-NOT: vzeroupper
+; X64: call
+; X64-NOT: vzeroupper
+; X64: call
+; X64: ret
+
+; X32: test_float4
+; X32: vzeroupper
+; X32: call
+; X32: vzeroupper
+; X32: call
+; X32: ret
+
+declare <4 x float> @func_float4(<4 x float>, <4 x float>, <4 x float>)
+
+define <8 x float> @test_float4(<8 x float> %a, <8 x float> %b, <8 x float> %c) nounwind readnone {
+entry:
+  %0 = shufflevector <8 x float> %a, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  %1 = shufflevector <8 x float> %b, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  %2 = shufflevector <8 x float> %c, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  %call.i = tail call intel_ocl_bicc <4 x float> @func_float4(<4 x float> %0, <4 x float> %1, <4 x float> %2) nounwind
+  %3 = shufflevector <4 x float> %call.i, <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
+  %4 = shufflevector <8 x float> %a, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  %5 = shufflevector <8 x float> %b, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  %6 = shufflevector <8 x float> %c, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  %call.i2 = tail call intel_ocl_bicc <4 x float> @func_float4(<4 x float> %4, <4 x float> %5, <4 x float> %6) nounwind
+  %7 = shufflevector <4 x float> %call.i2, <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
+  %8 = shufflevector <8 x float> %3, <8 x float> %7, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+  ret <8 x float> %8
+}