CellSPU:

Incorporate Tilmann's 128-bit operation patch. Evidently, it gets the
llvm-gcc bootstrap a bit further along.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@67048 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 69 insertions, 51 deletions

diff --git a/test/CodeGen/CellSPU/trunc.ll b/test/CodeGen/CellSPU/trunc.ll
index 1c6e1f6..db22564 100644
--- a/test/CodeGen/CellSPU/trunc.ll
+++ b/test/CodeGen/CellSPU/trunc.ll
@@ -1,76 +1,94 @@
 ; RUN: llvm-as -o - %s | llc -march=cellspu > %t1.s
-; RUN: grep shufb   %t1.s | count 10
+; RUN: grep shufb   %t1.s | count 19
 ; RUN: grep {ilhu.*1799}  %t1.s | count 1
-; RUN: grep {ilhu.*771}  %t1.s | count 1
+; RUN: grep {ilhu.*771}  %t1.s | count 2
 ; RUN: grep {ilhu.*1543}  %t1.s | count 1
 ; RUN: grep {ilhu.*1029}  %t1.s | count 1
-; RUN: grep {ilhu.*515}  %t1.s | count 2
-; RUN: grep xsbh  %t1.s | count 2
-; RUN: grep sfh  %t1.s | count 1
+; RUN: grep {ilhu.*515}  %t1.s | count 1
+; RUN: grep {ilhu.*3855}  %t1.s | count 1
+; RUN: grep {ilhu.*3599}  %t1.s | count 1
+; RUN: grep {ilhu.*3085}  %t1.s | count 1
+; RUN: grep {iohl.*3855}  %t1.s | count 1
+; RUN: grep {iohl.*3599}  %t1.s | count 2
+; RUN: grep {iohl.*1543}  %t1.s | count 2
+; RUN: grep {iohl.*771}  %t1.s | count 2
+; RUN: grep {iohl.*515}  %t1.s | count 1
+; RUN: grep {iohl.*1799}  %t1.s | count 1
+; RUN: grep lqa  %t1.s | count 1
+; RUN: grep cbd  %t1.s | count 4
+; RUN: grep chd  %t1.s | count 3
+; RUN: grep cwd  %t1.s | count 1
+; RUN: grep cdd  %t1.s | count 1
 
 ; ModuleID = 'trunc.bc'
 target datalayout = "E-p:32:32:128-i1:8:128-i8:8:128-i16:16:128-i32:32:128-i64:32:128-f32:32:128-f64:64:128-v64:64:64-v128:128:128-a0:0:128-s0:128:128"
 target triple = "spu"
 
-; codegen for i128 arguments is not implemented yet on CellSPU
-; once this changes uncomment the functions below
-; and update the expected results accordingly
+define <16 x i8> @trunc_i128_i8(i128 %u, <16 x i8> %v) {
+entry:
+	%0 = trunc i128 %u to i8
+    %tmp1 = insertelement <16 x i8> %v, i8 %0, i32 15 
+    ret <16 x i8> %tmp1
+}
 
-;define i8 @trunc_i128_i8(i128 %u) nounwind readnone {
-;entry:
-;	%0 = trunc i128 %u to i8
-;	ret i8 %0
-;}
-;define i16 @trunc_i128_i16(i128 %u) nounwind readnone {
-;entry:
-;	%0 = trunc i128 %u to i16
-;	ret i16 %0
-;}
-;define i32 @trunc_i128_i32(i128 %u) nounwind readnone {
-;entry:
-;	%0 = trunc i128 %u to i32
-;	ret i32 %0
-;}
-;define i64 @trunc_i128_i64(i128 %u) nounwind readnone {
-;entry:
-;	%0 = trunc i128 %u to i64
-;	ret i64 %0
-;}
+define <8 x i16> @trunc_i128_i16(i128 %u, <8 x i16> %v) {
+entry:
+    %0 = trunc i128 %u to i16
+    %tmp1 = insertelement <8 x i16> %v, i16 %0, i32 8 
+    ret <8 x i16> %tmp1
+}
 
-define <16 x i8> @trunc_i64_i8(i64 %u, <16 x i8> %v) nounwind readnone {
+define <4 x i32> @trunc_i128_i32(i128 %u, <4 x i32> %v) {
 entry:
-	%0 = trunc i64 %u to i8
-        %tmp1 = insertelement <16 x i8> %v, i8 %0, i32 10
-	ret <16 x i8> %tmp1
+    %0 = trunc i128 %u to i32
+    %tmp1 = insertelement <4 x i32> %v, i32 %0, i32 2
+    ret <4 x i32> %tmp1
 }
-define <8 x i16> @trunc_i64_i16(i64 %u, <8 x i16> %v) nounwind readnone {
+
+define <2 x i64> @trunc_i128_i64(i128 %u, <2 x i64> %v) {
 entry:
-	%0 = trunc i64 %u to i16
-        %tmp1 = insertelement <8 x i16> %v, i16 %0, i32 6
-	ret <8 x i16> %tmp1
+    %0 = trunc i128 %u to i64
+    %tmp1 = insertelement <2 x i64> %v, i64 %0, i32 1
+    ret <2 x i64> %tmp1
 }
-define i32 @trunc_i64_i32(i64 %u, i32 %v) nounwind readnone {
+
+define <16 x i8> @trunc_i64_i8(i64 %u, <16 x i8> %v) {
 entry:
-	%0 = trunc i64 %u to i32
-	ret i32 %0
+    %0 = trunc i64 %u to i8
+    %tmp1 = insertelement <16 x i8> %v, i8 %0, i32 10
+    ret <16 x i8> %tmp1
 }
 
-define i8 @trunc_i32_i8(i32 %u, i8 %v) nounwind readnone {
+define <8 x i16> @trunc_i64_i16(i64 %u, <8 x i16> %v) {
 entry:
-	%0 = trunc i32 %u to i8
-	%1 = sub i8 %0, %v
-	ret i8 %1
+    %0 = trunc i64 %u to i16
+    %tmp1 = insertelement <8 x i16> %v, i16 %0, i32 6
+    ret <8 x i16> %tmp1
 }
-define <8 x i16> @trunc_i32_i16(i32 %u, <8 x i16> %v) nounwind readnone {
+
+define i32 @trunc_i64_i32(i64 %u) {
+entry:
+    %0 = trunc i64 %u to i32
+    ret i32 %0
+}
+
+define <16 x i8> @trunc_i32_i8(i32 %u, <16 x i8> %v) {
+entry:
+    %0 = trunc i32 %u to i8
+    %tmp1 = insertelement <16 x i8> %v, i8 %0, i32 7
+    ret <16 x i8> %tmp1
+}
+
+define <8 x i16> @trunc_i32_i16(i32 %u, <8 x i16> %v) {
 entry:
-	%0 = trunc i32 %u to i16
-        %tmp1 = insertelement <8 x i16> %v, i16 %0, i32 3
-	ret <8 x i16> %tmp1
+    %0 = trunc i32 %u to i16
+    %tmp1 = insertelement <8 x i16> %v, i16 %0, i32 3
+    ret <8 x i16> %tmp1
 }
 
-define <16 x i8> @trunc_i16_i8(i16 %u, <16 x i8> %v) nounwind readnone {
+define <16 x i8> @trunc_i16_i8(i16 %u, <16 x i8> %v) {
 entry:
-	%0 = trunc i16 %u to i8
-        %tmp1 = insertelement <16 x i8> %v, i8 %0, i32 5
-	ret <16 x i8> %tmp1
+    %0 = trunc i16 %u to i8
+    %tmp1 = insertelement <16 x i8> %v, i8 %0, i32 5
+    ret <16 x i8> %tmp1
 }