maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/PowerPC/vaddsplat.ll

150 lines
4.8 KiB
LLVM
Raw Normal View History

Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
; RUN: llc -O0 -mcpu=pwr7 <%s | FileCheck %s
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
; Test optimizations of build_vector for 6-bit immediates.
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
%v4i32 = type <4 x i32>
%v8i16 = type <8 x i16>
%v16i8 = type <16 x i8>
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
define void @test_v4i32_pos_even(%v4i32* %P, %v4i32* %S) {
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
%p = load %v4i32* %P
%r = add %v4i32 %p, < i32 18, i32 18, i32 18, i32 18 >
store %v4i32 %r, %v4i32* %S
ret void
}
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
; CHECK: test_v4i32_pos_even:
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
; CHECK: vspltisw [[REG1:[0-9]+]], 9
; CHECK: vadduwm {{[0-9]+}}, [[REG1]], [[REG1]]
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
define void @test_v4i32_neg_even(%v4i32* %P, %v4i32* %S) {
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
%p = load %v4i32* %P
%r = add %v4i32 %p, < i32 -28, i32 -28, i32 -28, i32 -28 >
store %v4i32 %r, %v4i32* %S
ret void
}
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
; CHECK: test_v4i32_neg_even:
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
; CHECK: vspltisw [[REG1:[0-9]+]], -14
; CHECK: vadduwm {{[0-9]+}}, [[REG1]], [[REG1]]
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
define void @test_v8i16_pos_even(%v8i16* %P, %v8i16* %S) {
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
%p = load %v8i16* %P
%r = add %v8i16 %p, < i16 30, i16 30, i16 30, i16 30, i16 30, i16 30, i16 30, i16 30 >
store %v8i16 %r, %v8i16* %S
ret void
}
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
; CHECK: test_v8i16_pos_even:
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
; CHECK: vspltish [[REG1:[0-9]+]], 15
; CHECK: vadduhm {{[0-9]+}}, [[REG1]], [[REG1]]
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
define void @test_v8i16_neg_even(%v8i16* %P, %v8i16* %S) {
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
%p = load %v8i16* %P
%r = add %v8i16 %p, < i16 -32, i16 -32, i16 -32, i16 -32, i16 -32, i16 -32, i16 -32, i16 -32 >
store %v8i16 %r, %v8i16* %S
ret void
}
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
; CHECK: test_v8i16_neg_even:
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
; CHECK: vspltish [[REG1:[0-9]+]], -16
; CHECK: vadduhm {{[0-9]+}}, [[REG1]], [[REG1]]
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
define void @test_v16i8_pos_even(%v16i8* %P, %v16i8* %S) {
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
%p = load %v16i8* %P
%r = add %v16i8 %p, < i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16 >
store %v16i8 %r, %v16i8* %S
ret void
}
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
; CHECK: test_v16i8_pos_even:
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
; CHECK: vspltisb [[REG1:[0-9]+]], 8
; CHECK: vaddubm {{[0-9]+}}, [[REG1]], [[REG1]]
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
define void @test_v16i8_neg_even(%v16i8* %P, %v16i8* %S) {
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
%p = load %v16i8* %P
%r = add %v16i8 %p, < i8 -18, i8 -18, i8 -18, i8 -18, i8 -18, i8 -18, i8 -18, i8 -18, i8 -18, i8 -18, i8 -18, i8 -18, i8 -18, i8 -18, i8 -18, i8 -18 >
store %v16i8 %r, %v16i8* %S
ret void
}
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
; CHECK: test_v16i8_neg_even:
Fix PR15155: lost vadd/vsplat optimization. During lowering of a BUILD_VECTOR, we look for opportunities to use a vector splat. When the splatted value fits in 5 signed bits, a single splat does the job. When it doesn't fit in 5 bits but does fit in 6, and is an even value, we can splat on half the value and add the result to itself. This last optimization hasn't been working recently because of improved constant folding. To circumvent this, create a pseudo VADD_SPLAT that can be expanded during instruction selection. llvm-svn: 175632
2013-02-20 23:50:31 +08:00
; CHECK: vspltisb [[REG1:[0-9]+]], -9
; CHECK: vaddubm {{[0-9]+}}, [[REG1]], [[REG1]]
Additional fixes for bug 15155. This handles the cases where the 6-bit splat element is odd, converting to a three-instruction sequence to add or subtract two splats. With this fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed. llvm-svn: 175663
2013-02-21 04:41:42 +08:00
define void @test_v4i32_pos_odd(%v4i32* %P, %v4i32* %S) {
%p = load %v4i32* %P
%r = add %v4i32 %p, < i32 27, i32 27, i32 27, i32 27 >
store %v4i32 %r, %v4i32* %S
ret void
}
; CHECK: test_v4i32_pos_odd:
; CHECK: vspltisw [[REG2:[0-9]+]], -16
; CHECK: vspltisw [[REG1:[0-9]+]], 11
; CHECK: vsubuwm {{[0-9]+}}, [[REG1]], [[REG2]]
define void @test_v4i32_neg_odd(%v4i32* %P, %v4i32* %S) {
%p = load %v4i32* %P
%r = add %v4i32 %p, < i32 -27, i32 -27, i32 -27, i32 -27 >
store %v4i32 %r, %v4i32* %S
ret void
}
; CHECK: test_v4i32_neg_odd:
; CHECK: vspltisw [[REG2:[0-9]+]], -16
; CHECK: vspltisw [[REG1:[0-9]+]], -11
; CHECK: vadduwm {{[0-9]+}}, [[REG1]], [[REG2]]
define void @test_v8i16_pos_odd(%v8i16* %P, %v8i16* %S) {
%p = load %v8i16* %P
%r = add %v8i16 %p, < i16 31, i16 31, i16 31, i16 31, i16 31, i16 31, i16 31, i16 31 >
store %v8i16 %r, %v8i16* %S
ret void
}
; CHECK: test_v8i16_pos_odd:
; CHECK: vspltish [[REG2:[0-9]+]], -16
; CHECK: vspltish [[REG1:[0-9]+]], 15
; CHECK: vsubuhm {{[0-9]+}}, [[REG1]], [[REG2]]
define void @test_v8i16_neg_odd(%v8i16* %P, %v8i16* %S) {
%p = load %v8i16* %P
%r = add %v8i16 %p, < i16 -31, i16 -31, i16 -31, i16 -31, i16 -31, i16 -31, i16 -31, i16 -31 >
store %v8i16 %r, %v8i16* %S
ret void
}
; CHECK: test_v8i16_neg_odd:
; CHECK: vspltish [[REG2:[0-9]+]], -16
; CHECK: vspltish [[REG1:[0-9]+]], -15
; CHECK: vadduhm {{[0-9]+}}, [[REG1]], [[REG2]]
define void @test_v16i8_pos_odd(%v16i8* %P, %v16i8* %S) {
%p = load %v16i8* %P
%r = add %v16i8 %p, < i8 17, i8 17, i8 17, i8 17, i8 17, i8 17, i8 17, i8 17, i8 17, i8 17, i8 17, i8 17, i8 17, i8 17, i8 17, i8 17 >
store %v16i8 %r, %v16i8* %S
ret void
}
; CHECK: test_v16i8_pos_odd:
; CHECK: vspltisb [[REG2:[0-9]+]], -16
; CHECK: vspltisb [[REG1:[0-9]+]], 1
; CHECK: vsububm {{[0-9]+}}, [[REG1]], [[REG2]]
define void @test_v16i8_neg_odd(%v16i8* %P, %v16i8* %S) {
%p = load %v16i8* %P
%r = add %v16i8 %p, < i8 -17, i8 -17, i8 -17, i8 -17, i8 -17, i8 -17, i8 -17, i8 -17, i8 -17, i8 -17, i8 -17, i8 -17, i8 -17, i8 -17, i8 -17, i8 -17 >
store %v16i8 %r, %v16i8* %S
ret void
}
; CHECK: test_v16i8_neg_odd:
; CHECK: vspltisb [[REG2:[0-9]+]], -16
; CHECK: vspltisb [[REG1:[0-9]+]], -1
; CHECK: vaddubm {{[0-9]+}}, [[REG1]], [[REG2]]