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/X86/vector-unsigned-cmp.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

537 lines
18 KiB
LLVM
Raw Normal View History

[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
; PR33276 - https://bugs.llvm.org/show_bug.cgi?id=33276
; If both operands of an unsigned icmp are known non-negative, then
; we don't need to flip the sign bits in order to map to signed pcmpgt*.
define <2 x i1> @ugt_v2i64(<2 x i64> %x, <2 x i64> %y) {
; SSE-LABEL: ugt_v2i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlq $1, %xmm0
; SSE-NEXT: psrlq $1, %xmm1
[X86] When lowering unsigned v2i64 setcc without SSE42, flip the sign bits in the v2i64 type then bitcast to v4i32. This may give slightly better opportunities for DAG combine to simplify with the operations before the setcc. It also matches the type the xors will eventually be promoted to anyway so it saves a legalization step. Almost all of the test changes are because our constant pool entry is now v2i64 instead of v4i32 on 64-bit targets. On 32-bit targets getConstant should be emitting a v4i32 build_vector and a v4i32->v2i64 bitcast. There are a couple test cases where it appears we now combine a bitwise not with one of these xors which caused a new constant vector to be generated. This prevented a constant pool entry from being shared. But if that's an issue we're concerned about, it seems we need to address it another way that just relying a bitcast to hide it. This came about from experiments I've been trying with pushing the promotion of and/or/xor to vXi64 later than LegalizeVectorOps where it is today. We run LegalizeVectorOps in a bottom up order. So the and/or/xor are promoted before their users are legalized. The bitcasts added for the promotion act as a barrier to computeKnownBits if we try to use it during vector legalization of a later operation. So by moving the promotion out we can hopefully get better results from computeKnownBits/computeNumSignBits like in LowerTruncate on AVX512. I've also looked at running LegalizeVectorOps in a top down order like LegalizeDAG, but thats showing some other issues. llvm-svn: 344071
2018-10-10 03:05:50 +08:00
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648]
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: pxor %xmm2, %xmm1
; SSE-NEXT: pxor %xmm2, %xmm0
; SSE-NEXT: movdqa %xmm0, %xmm2
; SSE-NEXT: pcmpgtd %xmm1, %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
; SSE-NEXT: pcmpeqd %xmm1, %xmm0
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
; SSE-NEXT: pand %xmm3, %xmm1
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: ugt_v2i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlq $1, %xmm0, %xmm0
; AVX-NEXT: vpsrlq $1, %xmm1, %xmm1
; AVX-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <2 x i64> %x, <i64 1, i64 1>
%sh2 = lshr <2 x i64> %y, <i64 1, i64 1>
%cmp = icmp ugt <2 x i64> %sh1, %sh2
ret <2 x i1> %cmp
}
define <2 x i1> @ult_v2i64(<2 x i64> %x, <2 x i64> %y) {
; SSE-LABEL: ult_v2i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlq $1, %xmm0
; SSE-NEXT: psrlq $1, %xmm1
[X86] When lowering unsigned v2i64 setcc without SSE42, flip the sign bits in the v2i64 type then bitcast to v4i32. This may give slightly better opportunities for DAG combine to simplify with the operations before the setcc. It also matches the type the xors will eventually be promoted to anyway so it saves a legalization step. Almost all of the test changes are because our constant pool entry is now v2i64 instead of v4i32 on 64-bit targets. On 32-bit targets getConstant should be emitting a v4i32 build_vector and a v4i32->v2i64 bitcast. There are a couple test cases where it appears we now combine a bitwise not with one of these xors which caused a new constant vector to be generated. This prevented a constant pool entry from being shared. But if that's an issue we're concerned about, it seems we need to address it another way that just relying a bitcast to hide it. This came about from experiments I've been trying with pushing the promotion of and/or/xor to vXi64 later than LegalizeVectorOps where it is today. We run LegalizeVectorOps in a bottom up order. So the and/or/xor are promoted before their users are legalized. The bitcasts added for the promotion act as a barrier to computeKnownBits if we try to use it during vector legalization of a later operation. So by moving the promotion out we can hopefully get better results from computeKnownBits/computeNumSignBits like in LowerTruncate on AVX512. I've also looked at running LegalizeVectorOps in a top down order like LegalizeDAG, but thats showing some other issues. llvm-svn: 344071
2018-10-10 03:05:50 +08:00
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648]
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: pxor %xmm2, %xmm0
; SSE-NEXT: pxor %xmm2, %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm2
; SSE-NEXT: pcmpgtd %xmm0, %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
; SSE-NEXT: pcmpeqd %xmm0, %xmm1
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; SSE-NEXT: pand %xmm3, %xmm1
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: ult_v2i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlq $1, %xmm0, %xmm0
; AVX-NEXT: vpsrlq $1, %xmm1, %xmm1
; AVX-NEXT: vpcmpgtq %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <2 x i64> %x, <i64 1, i64 1>
%sh2 = lshr <2 x i64> %y, <i64 1, i64 1>
%cmp = icmp ult <2 x i64> %sh1, %sh2
ret <2 x i1> %cmp
}
define <2 x i1> @uge_v2i64(<2 x i64> %x, <2 x i64> %y) {
; SSE-LABEL: uge_v2i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlq $1, %xmm0
; SSE-NEXT: psrlq $1, %xmm1
[X86] When lowering unsigned v2i64 setcc without SSE42, flip the sign bits in the v2i64 type then bitcast to v4i32. This may give slightly better opportunities for DAG combine to simplify with the operations before the setcc. It also matches the type the xors will eventually be promoted to anyway so it saves a legalization step. Almost all of the test changes are because our constant pool entry is now v2i64 instead of v4i32 on 64-bit targets. On 32-bit targets getConstant should be emitting a v4i32 build_vector and a v4i32->v2i64 bitcast. There are a couple test cases where it appears we now combine a bitwise not with one of these xors which caused a new constant vector to be generated. This prevented a constant pool entry from being shared. But if that's an issue we're concerned about, it seems we need to address it another way that just relying a bitcast to hide it. This came about from experiments I've been trying with pushing the promotion of and/or/xor to vXi64 later than LegalizeVectorOps where it is today. We run LegalizeVectorOps in a bottom up order. So the and/or/xor are promoted before their users are legalized. The bitcasts added for the promotion act as a barrier to computeKnownBits if we try to use it during vector legalization of a later operation. So by moving the promotion out we can hopefully get better results from computeKnownBits/computeNumSignBits like in LowerTruncate on AVX512. I've also looked at running LegalizeVectorOps in a top down order like LegalizeDAG, but thats showing some other issues. llvm-svn: 344071
2018-10-10 03:05:50 +08:00
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648]
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: pxor %xmm2, %xmm0
; SSE-NEXT: pxor %xmm2, %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm2
; SSE-NEXT: pcmpgtd %xmm0, %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
; SSE-NEXT: pcmpeqd %xmm0, %xmm1
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,3,3]
; SSE-NEXT: pand %xmm3, %xmm0
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,1,3,3]
; SSE-NEXT: por %xmm0, %xmm1
; SSE-NEXT: pcmpeqd %xmm0, %xmm0
; SSE-NEXT: pxor %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: uge_v2i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlq $1, %xmm0, %xmm0
; AVX-NEXT: vpsrlq $1, %xmm1, %xmm1
; AVX-NEXT: vpcmpgtq %xmm0, %xmm1, %xmm0
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <2 x i64> %x, <i64 1, i64 1>
%sh2 = lshr <2 x i64> %y, <i64 1, i64 1>
%cmp = icmp uge <2 x i64> %sh1, %sh2
ret <2 x i1> %cmp
}
define <2 x i1> @ule_v2i64(<2 x i64> %x, <2 x i64> %y) {
; SSE-LABEL: ule_v2i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlq $1, %xmm0
; SSE-NEXT: psrlq $1, %xmm1
[X86] When lowering unsigned v2i64 setcc without SSE42, flip the sign bits in the v2i64 type then bitcast to v4i32. This may give slightly better opportunities for DAG combine to simplify with the operations before the setcc. It also matches the type the xors will eventually be promoted to anyway so it saves a legalization step. Almost all of the test changes are because our constant pool entry is now v2i64 instead of v4i32 on 64-bit targets. On 32-bit targets getConstant should be emitting a v4i32 build_vector and a v4i32->v2i64 bitcast. There are a couple test cases where it appears we now combine a bitwise not with one of these xors which caused a new constant vector to be generated. This prevented a constant pool entry from being shared. But if that's an issue we're concerned about, it seems we need to address it another way that just relying a bitcast to hide it. This came about from experiments I've been trying with pushing the promotion of and/or/xor to vXi64 later than LegalizeVectorOps where it is today. We run LegalizeVectorOps in a bottom up order. So the and/or/xor are promoted before their users are legalized. The bitcasts added for the promotion act as a barrier to computeKnownBits if we try to use it during vector legalization of a later operation. So by moving the promotion out we can hopefully get better results from computeKnownBits/computeNumSignBits like in LowerTruncate on AVX512. I've also looked at running LegalizeVectorOps in a top down order like LegalizeDAG, but thats showing some other issues. llvm-svn: 344071
2018-10-10 03:05:50 +08:00
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648]
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: pxor %xmm2, %xmm1
; SSE-NEXT: pxor %xmm2, %xmm0
; SSE-NEXT: movdqa %xmm0, %xmm2
; SSE-NEXT: pcmpgtd %xmm1, %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
; SSE-NEXT: pcmpeqd %xmm1, %xmm0
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,3,3]
; SSE-NEXT: pand %xmm3, %xmm0
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,1,3,3]
; SSE-NEXT: por %xmm0, %xmm1
; SSE-NEXT: pcmpeqd %xmm0, %xmm0
; SSE-NEXT: pxor %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: ule_v2i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlq $1, %xmm0, %xmm0
; AVX-NEXT: vpsrlq $1, %xmm1, %xmm1
; AVX-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <2 x i64> %x, <i64 1, i64 1>
%sh2 = lshr <2 x i64> %y, <i64 1, i64 1>
%cmp = icmp ule <2 x i64> %sh1, %sh2
ret <2 x i1> %cmp
}
define <4 x i1> @ugt_v4i32(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: ugt_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrld $1, %xmm0
; SSE-NEXT: psrld $1, %xmm1
; SSE-NEXT: pcmpgtd %xmm1, %xmm0
; SSE-NEXT: retq
;
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; AVX-LABEL: ugt_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; AVX-NEXT: vpsrld $1, %xmm0, %xmm0
; AVX-NEXT: vpsrld $1, %xmm1, %xmm1
; AVX-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
%sh1 = lshr <4 x i32> %x, <i32 1, i32 1, i32 1, i32 1>
%sh2 = lshr <4 x i32> %y, <i32 1, i32 1, i32 1, i32 1>
%cmp = icmp ugt <4 x i32> %sh1, %sh2
ret <4 x i1> %cmp
}
define <4 x i1> @ult_v4i32(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: ult_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrld $1, %xmm0
; SSE-NEXT: psrld $1, %xmm1
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; SSE-NEXT: pcmpgtd %xmm0, %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm0
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: retq
;
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; AVX-LABEL: ult_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; AVX-NEXT: vpsrld $1, %xmm0, %xmm0
; AVX-NEXT: vpsrld $1, %xmm1, %xmm1
; AVX-NEXT: vpcmpgtd %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
%sh1 = lshr <4 x i32> %x, <i32 1, i32 1, i32 1, i32 1>
%sh2 = lshr <4 x i32> %y, <i32 1, i32 1, i32 1, i32 1>
%cmp = icmp ult <4 x i32> %sh1, %sh2
ret <4 x i1> %cmp
}
define <4 x i1> @uge_v4i32(<4 x i32> %x, <4 x i32> %y) {
; SSE2-LABEL: uge_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE2: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE2-NEXT: psrld $1, %xmm0
; SSE2-NEXT: psrld $1, %xmm1
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; SSE2-NEXT: pcmpgtd %xmm0, %xmm1
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE2-NEXT: pcmpeqd %xmm0, %xmm0
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; SSE2-NEXT: pxor %xmm1, %xmm0
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: uge_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE41: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE41-NEXT: psrld $1, %xmm0
; SSE41-NEXT: psrld $1, %xmm1
; SSE41-NEXT: pmaxud %xmm0, %xmm1
; SSE41-NEXT: pcmpeqd %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX-LABEL: uge_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrld $1, %xmm0, %xmm0
; AVX-NEXT: vpsrld $1, %xmm1, %xmm1
; AVX-NEXT: vpmaxud %xmm1, %xmm0, %xmm1
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <4 x i32> %x, <i32 1, i32 1, i32 1, i32 1>
%sh2 = lshr <4 x i32> %y, <i32 1, i32 1, i32 1, i32 1>
%cmp = icmp uge <4 x i32> %sh1, %sh2
ret <4 x i1> %cmp
}
define <4 x i1> @ule_v4i32(<4 x i32> %x, <4 x i32> %y) {
; SSE2-LABEL: ule_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE2: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE2-NEXT: psrld $1, %xmm0
; SSE2-NEXT: psrld $1, %xmm1
; SSE2-NEXT: pcmpgtd %xmm1, %xmm0
; SSE2-NEXT: pcmpeqd %xmm1, %xmm1
; SSE2-NEXT: pxor %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: ule_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE41: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE41-NEXT: psrld $1, %xmm0
; SSE41-NEXT: psrld $1, %xmm1
; SSE41-NEXT: pminud %xmm0, %xmm1
; SSE41-NEXT: pcmpeqd %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX-LABEL: ule_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrld $1, %xmm0, %xmm0
; AVX-NEXT: vpsrld $1, %xmm1, %xmm1
; AVX-NEXT: vpminud %xmm1, %xmm0, %xmm1
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <4 x i32> %x, <i32 1, i32 1, i32 1, i32 1>
%sh2 = lshr <4 x i32> %y, <i32 1, i32 1, i32 1, i32 1>
%cmp = icmp ule <4 x i32> %sh1, %sh2
ret <4 x i1> %cmp
}
define <8 x i1> @ugt_v8i16(<8 x i16> %x, <8 x i16> %y) {
; SSE-LABEL: ugt_v8i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlw $1, %xmm0
; SSE-NEXT: psrlw $1, %xmm1
; SSE-NEXT: pcmpgtw %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: ugt_v8i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlw $1, %xmm0, %xmm0
; AVX-NEXT: vpsrlw $1, %xmm1, %xmm1
; AVX-NEXT: vpcmpgtw %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <8 x i16> %x, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%sh2 = lshr <8 x i16> %y, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%cmp = icmp ugt <8 x i16> %sh1, %sh2
ret <8 x i1> %cmp
}
define <8 x i1> @ult_v8i16(<8 x i16> %x, <8 x i16> %y) {
; SSE-LABEL: ult_v8i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlw $1, %xmm0
; SSE-NEXT: psrlw $1, %xmm1
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; SSE-NEXT: pcmpgtw %xmm0, %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm0
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: ult_v8i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlw $1, %xmm0, %xmm0
; AVX-NEXT: vpsrlw $1, %xmm1, %xmm1
; AVX-NEXT: vpcmpgtw %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <8 x i16> %x, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%sh2 = lshr <8 x i16> %y, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%cmp = icmp ult <8 x i16> %sh1, %sh2
ret <8 x i1> %cmp
}
define <8 x i1> @uge_v8i16(<8 x i16> %x, <8 x i16> %y) {
; SSE2-LABEL: uge_v8i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE2: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE2-NEXT: psrlw $1, %xmm0
; SSE2-NEXT: psrlw $1, %xmm1
[X86][SSE] Don't use LowerVSETCCWithSUBUS for unsigned compare with +ve operands (PR47448) We already simplify the unsigned comparisons if we've found the operands are non-negative, but we were still calling LowerVSETCCWithSUBUS which resulted in the PR47448 regressions.
2020-09-07 23:11:40 +08:00
; SSE2-NEXT: pcmpgtw %xmm0, %xmm1
; SSE2-NEXT: pcmpeqd %xmm0, %xmm0
; SSE2-NEXT: pxor %xmm1, %xmm0
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: uge_v8i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE41: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE41-NEXT: psrlw $1, %xmm0
; SSE41-NEXT: psrlw $1, %xmm1
; SSE41-NEXT: pmaxuw %xmm0, %xmm1
; SSE41-NEXT: pcmpeqw %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX-LABEL: uge_v8i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlw $1, %xmm0, %xmm0
; AVX-NEXT: vpsrlw $1, %xmm1, %xmm1
; AVX-NEXT: vpmaxuw %xmm1, %xmm0, %xmm1
; AVX-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <8 x i16> %x, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%sh2 = lshr <8 x i16> %y, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%cmp = icmp uge <8 x i16> %sh1, %sh2
ret <8 x i1> %cmp
}
define <8 x i1> @ule_v8i16(<8 x i16> %x, <8 x i16> %y) {
; SSE2-LABEL: ule_v8i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE2: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE2-NEXT: psrlw $1, %xmm0
; SSE2-NEXT: psrlw $1, %xmm1
[X86][SSE] Don't use LowerVSETCCWithSUBUS for unsigned compare with +ve operands (PR47448) We already simplify the unsigned comparisons if we've found the operands are non-negative, but we were still calling LowerVSETCCWithSUBUS which resulted in the PR47448 regressions.
2020-09-07 23:11:40 +08:00
; SSE2-NEXT: pcmpgtw %xmm1, %xmm0
; SSE2-NEXT: pcmpeqd %xmm1, %xmm1
; SSE2-NEXT: pxor %xmm1, %xmm0
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: ule_v8i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE41: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE41-NEXT: psrlw $1, %xmm0
; SSE41-NEXT: psrlw $1, %xmm1
; SSE41-NEXT: pminuw %xmm0, %xmm1
; SSE41-NEXT: pcmpeqw %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX-LABEL: ule_v8i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlw $1, %xmm0, %xmm0
; AVX-NEXT: vpsrlw $1, %xmm1, %xmm1
; AVX-NEXT: vpminuw %xmm1, %xmm0, %xmm1
; AVX-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <8 x i16> %x, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%sh2 = lshr <8 x i16> %y, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%cmp = icmp ule <8 x i16> %sh1, %sh2
ret <8 x i1> %cmp
}
define <16 x i1> @ugt_v16i8(<16 x i8> %x, <16 x i8> %y) {
; SSE-LABEL: ugt_v16i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlw $1, %xmm0
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
; SSE-NEXT: pand %xmm2, %xmm0
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlw $1, %xmm1
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; SSE-NEXT: pand %xmm2, %xmm1
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: pcmpgtb %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: ugt_v16i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlw $1, %xmm0, %xmm0
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
; AVX-NEXT: vpand %xmm2, %xmm0, %xmm0
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlw $1, %xmm1, %xmm1
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; AVX-NEXT: vpand %xmm2, %xmm1, %xmm1
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpcmpgtb %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <16 x i8> %x, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
%sh2 = lshr <16 x i8> %y, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
%cmp = icmp ugt <16 x i8> %sh1, %sh2
ret <16 x i1> %cmp
}
define <16 x i1> @ult_v16i8(<16 x i8> %x, <16 x i8> %y) {
; SSE-LABEL: ult_v16i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlw $1, %xmm0
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
; SSE-NEXT: pand %xmm2, %xmm0
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlw $1, %xmm1
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; SSE-NEXT: pand %xmm1, %xmm2
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: pcmpgtb %xmm0, %xmm2
; SSE-NEXT: movdqa %xmm2, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: ult_v16i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlw $1, %xmm0, %xmm0
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
; AVX-NEXT: vpand %xmm2, %xmm0, %xmm0
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlw $1, %xmm1, %xmm1
[x86] avoid flipping sign bits for vector icmp by using known bits If we know that both operands of an unsigned integer vector comparison are non-negative, then it's safe to directly use a signed-compare-greater-than instruction (the only non-equality integer vector compare predicate provided by SSE/AVX). We're intentionally not changing the condition code to signed in order to preserve the existing transforms that use min/max/psubus below here. This should solve PR33276: https://bugs.llvm.org/show_bug.cgi?id=33276 Differential Revision: https://reviews.llvm.org/D33862 llvm-svn: 304909
2017-06-07 21:46:34 +08:00
; AVX-NEXT: vpand %xmm2, %xmm1, %xmm1
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <16 x i8> %x, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
%sh2 = lshr <16 x i8> %y, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
%cmp = icmp ult <16 x i8> %sh1, %sh2
ret <16 x i1> %cmp
}
define <16 x i1> @uge_v16i8(<16 x i8> %x, <16 x i8> %y) {
; SSE-LABEL: uge_v16i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlw $1, %xmm0
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
; SSE-NEXT: pand %xmm2, %xmm0
; SSE-NEXT: psrlw $1, %xmm1
; SSE-NEXT: pand %xmm2, %xmm1
; SSE-NEXT: pmaxub %xmm0, %xmm1
; SSE-NEXT: pcmpeqb %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: uge_v16i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlw $1, %xmm0, %xmm0
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
; AVX-NEXT: vpand %xmm2, %xmm0, %xmm0
; AVX-NEXT: vpsrlw $1, %xmm1, %xmm1
; AVX-NEXT: vpand %xmm2, %xmm1, %xmm1
; AVX-NEXT: vpmaxub %xmm1, %xmm0, %xmm1
; AVX-NEXT: vpcmpeqb %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <16 x i8> %x, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
%sh2 = lshr <16 x i8> %y, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
%cmp = icmp uge <16 x i8> %sh1, %sh2
ret <16 x i1> %cmp
}
define <16 x i1> @ule_v16i8(<16 x i8> %x, <16 x i8> %y) {
; SSE-LABEL: ule_v16i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; SSE-NEXT: psrlw $1, %xmm0
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
; SSE-NEXT: pand %xmm2, %xmm0
; SSE-NEXT: psrlw $1, %xmm1
; SSE-NEXT: pand %xmm2, %xmm1
; SSE-NEXT: pminub %xmm0, %xmm1
; SSE-NEXT: pcmpeqb %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: ule_v16i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[x86] add tests for unsigned vector compares with known signbits; NFC (PR33276) llvm-svn: 304612
2017-06-03 07:24:28 +08:00
; AVX-NEXT: vpsrlw $1, %xmm0, %xmm0
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
; AVX-NEXT: vpand %xmm2, %xmm0, %xmm0
; AVX-NEXT: vpsrlw $1, %xmm1, %xmm1
; AVX-NEXT: vpand %xmm2, %xmm1, %xmm1
; AVX-NEXT: vpminub %xmm1, %xmm0, %xmm1
; AVX-NEXT: vpcmpeqb %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%sh1 = lshr <16 x i8> %x, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
%sh2 = lshr <16 x i8> %y, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
%cmp = icmp ule <16 x i8> %sh1, %sh2
ret <16 x i1> %cmp
}
[X86][SSE] Add test cases for PR47448
2020-09-07 22:53:15 +08:00
define <8 x i16> @PR47448_uge(i16 signext %0) {
; SSE2-LABEL: PR47448_uge:
; SSE2: # %bb.0:
; SSE2-NEXT: andl $7, %edi
; SSE2-NEXT: movd %edi, %xmm0
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [0,1,2,3,4,5,6,7]
[X86][SSE] Don't use LowerVSETCCWithSUBUS for unsigned compare with +ve operands (PR47448) We already simplify the unsigned comparisons if we've found the operands are non-negative, but we were still calling LowerVSETCCWithSUBUS which resulted in the PR47448 regressions.
2020-09-07 23:11:40 +08:00
; SSE2-NEXT: pcmpgtw %xmm0, %xmm1
; SSE2-NEXT: pcmpeqd %xmm0, %xmm0
; SSE2-NEXT: pxor %xmm1, %xmm0
[X86][SSE] Add test cases for PR47448
2020-09-07 22:53:15 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: PR47448_uge:
; SSE41: # %bb.0:
; SSE41-NEXT: andl $7, %edi
; SSE41-NEXT: movd %edi, %xmm0
; SSE41-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm0[0,0,0,0]
; SSE41-NEXT: movdqa {{.*#+}} xmm0 = [0,1,2,3,4,5,6,7]
; SSE41-NEXT: pmaxuw %xmm1, %xmm0
; SSE41-NEXT: pcmpeqw %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: PR47448_uge:
; AVX1: # %bb.0:
; AVX1-NEXT: andl $7, %edi
; AVX1-NEXT: vmovd %edi, %xmm0
; AVX1-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX1-NEXT: vpmaxuw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
[X86][SSE] Add test cases for PR47448
2020-09-07 22:53:15 +08:00
; AVX1-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: PR47448_uge:
; AVX2: # %bb.0:
; AVX2-NEXT: andl $7, %edi
; AVX2-NEXT: vmovd %edi, %xmm0
; AVX2-NEXT: vpbroadcastw %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX2-NEXT: vpmaxuw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
[X86][SSE] Add test cases for PR47448
2020-09-07 22:53:15 +08:00
; AVX2-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: retq
%2 = and i16 %0, 7
%3 = insertelement <8 x i16> undef, i16 %2, i32 0
%4 = shufflevector <8 x i16> %3, <8 x i16> undef, <8 x i32> zeroinitializer
%5 = icmp uge <8 x i16> %4, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
%6 = sext <8 x i1> %5 to <8 x i16>
ret <8 x i16> %6
}
define <8 x i16> @PR47448_ugt(i16 signext %0) {
; SSE-LABEL: PR47448_ugt:
; SSE: # %bb.0:
; SSE-NEXT: andl $7, %edi
; SSE-NEXT: movd %edi, %xmm0
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; SSE-NEXT: pcmpgtw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
[X86][SSE] Add test cases for PR47448
2020-09-07 22:53:15 +08:00
; SSE-NEXT: retq
;
; AVX1-LABEL: PR47448_ugt:
; AVX1: # %bb.0:
; AVX1-NEXT: andl $7, %edi
; AVX1-NEXT: vmovd %edi, %xmm0
; AVX1-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX1-NEXT: vpcmpgtw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
[X86][SSE] Add test cases for PR47448
2020-09-07 22:53:15 +08:00
; AVX1-NEXT: retq
;
; AVX2-LABEL: PR47448_ugt:
; AVX2: # %bb.0:
; AVX2-NEXT: andl $7, %edi
; AVX2-NEXT: vmovd %edi, %xmm0
; AVX2-NEXT: vpbroadcastw %xmm0, %xmm0
[NFC][X86][Codegen] Megacommit: mass-regenerate all check lines that were already autogenerated The motivation is that the update script has at least two deviations (`<...>@GOT`/`<...>@PLT`/ and not hiding pointer arithmetics) from what pretty much all the checklines were generated with, and most of the tests are still not updated, so each time one of the non-up-to-date tests is updated to see the effect of the code change, there is a lot of noise. Instead of having to deal with that each time, let's just deal with everything at once. This has been done via: ``` cd llvm-project/llvm/test/CodeGen/X86 grep -rl "; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py" | xargs -L1 <...>/llvm-project/llvm/utils/update_llc_test_checks.py --llc-binary <...>/llvm-project/build/bin/llc ``` Not all tests were regenerated, however.
2021-06-12 04:26:17 +08:00
; AVX2-NEXT: vpcmpgtw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
[X86][SSE] Add test cases for PR47448
2020-09-07 22:53:15 +08:00
; AVX2-NEXT: retq
%2 = and i16 %0, 7
%3 = insertelement <8 x i16> undef, i16 %2, i32 0
%4 = shufflevector <8 x i16> %3, <8 x i16> undef, <8 x i32> zeroinitializer
%5 = icmp ugt <8 x i16> %4, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
%6 = sext <8 x i1> %5 to <8 x i16>
ret <8 x i16> %6
}