diff options
Diffstat (limited to 'llvm/test/CodeGen/X86')
| -rw-r--r-- | llvm/test/CodeGen/X86/2007-08-09-IllegalX86-64Asm.ll | 109 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/isel-fpclass.ll | 433 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/masked_gather_scatter.ll | 60 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/pr160612.ll | 74 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/setcc-wide-types.ll | 65 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/x86-shrink-wrap-unwind.ll | 52 |
6 files changed, 610 insertions, 183 deletions
diff --git a/llvm/test/CodeGen/X86/2007-08-09-IllegalX86-64Asm.ll b/llvm/test/CodeGen/X86/2007-08-09-IllegalX86-64Asm.ll index 28b4541..7bdc4e1 100644 --- a/llvm/test/CodeGen/X86/2007-08-09-IllegalX86-64Asm.ll +++ b/llvm/test/CodeGen/X86/2007-08-09-IllegalX86-64Asm.ll @@ -44,7 +44,7 @@ define ptr @ubyte_divmod(ptr %a, ptr %b) { ; CHECK-NEXT: leaq {{[0-9]+}}(%rsp), %rsi ; CHECK-NEXT: callq __ubyte_convert_to_ctype ; CHECK-NEXT: testl %eax, %eax -; CHECK-NEXT: js LBB0_6 +; CHECK-NEXT: js LBB0_4 ; CHECK-NEXT: ## %bb.1: ## %cond_next.i ; CHECK-NEXT: leaq {{[0-9]+}}(%rsp), %rsi ; CHECK-NEXT: movq %rbx, %rdi @@ -53,84 +53,81 @@ define ptr @ubyte_divmod(ptr %a, ptr %b) { ; CHECK-NEXT: sarl $31, %ecx ; CHECK-NEXT: andl %eax, %ecx ; CHECK-NEXT: cmpl $-2, %ecx -; CHECK-NEXT: je LBB0_10 +; CHECK-NEXT: je LBB0_8 ; CHECK-NEXT: ## %bb.2: ## %cond_next.i ; CHECK-NEXT: cmpl $-1, %ecx -; CHECK-NEXT: jne LBB0_3 -; CHECK-NEXT: LBB0_8: ## %bb4 +; CHECK-NEXT: jne LBB0_6 +; CHECK-NEXT: LBB0_3: ## %bb4 ; CHECK-NEXT: movq _PyArray_API@GOTPCREL(%rip), %rax ; CHECK-NEXT: movq (%rax), %rax ; CHECK-NEXT: movq 16(%rax), %rax -; CHECK-NEXT: jmp LBB0_9 -; CHECK-NEXT: LBB0_6: ## %_ubyte_convert2_to_ctypes.exit +; CHECK-NEXT: jmp LBB0_10 +; CHECK-NEXT: LBB0_4: ## %_ubyte_convert2_to_ctypes.exit ; CHECK-NEXT: cmpl $-2, %eax -; CHECK-NEXT: je LBB0_10 -; CHECK-NEXT: ## %bb.7: ## %_ubyte_convert2_to_ctypes.exit -; CHECK-NEXT: cmpl $-1, %eax ; CHECK-NEXT: je LBB0_8 -; CHECK-NEXT: LBB0_3: ## %bb35 +; CHECK-NEXT: ## %bb.5: ## %_ubyte_convert2_to_ctypes.exit +; CHECK-NEXT: cmpl $-1, %eax +; CHECK-NEXT: je LBB0_3 +; CHECK-NEXT: LBB0_6: ## %bb35 ; CHECK-NEXT: movq _PyUFunc_API@GOTPCREL(%rip), %r14 ; CHECK-NEXT: movq (%r14), %rax ; CHECK-NEXT: callq *216(%rax) ; CHECK-NEXT: movzbl {{[0-9]+}}(%rsp), %edx ; CHECK-NEXT: testb %dl, %dl -; CHECK-NEXT: je LBB0_4 -; CHECK-NEXT: ## %bb.12: ## %cond_false.i -; CHECK-NEXT: setne %dil +; CHECK-NEXT: je LBB0_11 +; CHECK-NEXT: ## %bb.7: ## %cond_false.i ; CHECK-NEXT: movzbl {{[0-9]+}}(%rsp), %esi ; CHECK-NEXT: movzbl %sil, %ecx ; CHECK-NEXT: movl %ecx, %eax ; CHECK-NEXT: divb %dl ; CHECK-NEXT: movl %eax, %r15d ; CHECK-NEXT: testb %cl, %cl -; CHECK-NEXT: setne %al -; CHECK-NEXT: testb %dil, %al -; CHECK-NEXT: jne LBB0_5 -; CHECK-NEXT: LBB0_13: ## %cond_true.i200 -; CHECK-NEXT: testb %dl, %dl -; CHECK-NEXT: jne LBB0_15 -; CHECK-NEXT: ## %bb.14: ## %cond_true14.i -; CHECK-NEXT: movl $4, %edi -; CHECK-NEXT: callq _feraiseexcept -; CHECK-NEXT: LBB0_15: ## %ubyte_ctype_remainder.exit -; CHECK-NEXT: xorl %ebx, %ebx -; CHECK-NEXT: jmp LBB0_16 -; CHECK-NEXT: LBB0_10: ## %bb17 +; CHECK-NEXT: jne LBB0_12 +; CHECK-NEXT: jmp LBB0_14 +; CHECK-NEXT: LBB0_8: ## %bb17 ; CHECK-NEXT: callq _PyErr_Occurred ; CHECK-NEXT: testq %rax, %rax -; CHECK-NEXT: jne LBB0_23 -; CHECK-NEXT: ## %bb.11: ## %cond_next +; CHECK-NEXT: jne LBB0_27 +; CHECK-NEXT: ## %bb.9: ## %cond_next ; CHECK-NEXT: movq _PyArray_API@GOTPCREL(%rip), %rax ; CHECK-NEXT: movq (%rax), %rax ; CHECK-NEXT: movq 80(%rax), %rax -; CHECK-NEXT: LBB0_9: ## %bb4 +; CHECK-NEXT: LBB0_10: ## %bb4 ; CHECK-NEXT: movq 96(%rax), %rax ; CHECK-NEXT: movq %r14, %rdi ; CHECK-NEXT: movq %rbx, %rsi ; CHECK-NEXT: callq *40(%rax) -; CHECK-NEXT: jmp LBB0_24 -; CHECK-NEXT: LBB0_4: ## %cond_true.i +; CHECK-NEXT: jmp LBB0_28 +; CHECK-NEXT: LBB0_11: ## %cond_true.i ; CHECK-NEXT: movl $4, %edi ; CHECK-NEXT: callq _feraiseexcept ; CHECK-NEXT: movzbl {{[0-9]+}}(%rsp), %edx ; CHECK-NEXT: movzbl {{[0-9]+}}(%rsp), %esi +; CHECK-NEXT: xorl %r15d, %r15d ; CHECK-NEXT: testb %sil, %sil -; CHECK-NEXT: sete %al +; CHECK-NEXT: je LBB0_14 +; CHECK-NEXT: LBB0_12: ## %cond_false.i ; CHECK-NEXT: testb %dl, %dl -; CHECK-NEXT: sete %cl -; CHECK-NEXT: xorl %r15d, %r15d -; CHECK-NEXT: orb %al, %cl -; CHECK-NEXT: jne LBB0_13 -; CHECK-NEXT: LBB0_5: ## %cond_next17.i +; CHECK-NEXT: je LBB0_14 +; CHECK-NEXT: ## %bb.13: ## %cond_next17.i ; CHECK-NEXT: movzbl %sil, %eax ; CHECK-NEXT: divb %dl ; CHECK-NEXT: movzbl %ah, %ebx -; CHECK-NEXT: LBB0_16: ## %ubyte_ctype_remainder.exit +; CHECK-NEXT: jmp LBB0_18 +; CHECK-NEXT: LBB0_14: ## %cond_true.i200 +; CHECK-NEXT: testb %dl, %dl +; CHECK-NEXT: jne LBB0_17 +; CHECK-NEXT: ## %bb.16: ## %cond_true14.i +; CHECK-NEXT: movl $4, %edi +; CHECK-NEXT: callq _feraiseexcept +; CHECK-NEXT: LBB0_17: ## %ubyte_ctype_remainder.exit +; CHECK-NEXT: xorl %ebx, %ebx +; CHECK-NEXT: LBB0_18: ## %ubyte_ctype_remainder.exit ; CHECK-NEXT: movq (%r14), %rax ; CHECK-NEXT: callq *224(%rax) ; CHECK-NEXT: testl %eax, %eax -; CHECK-NEXT: je LBB0_19 -; CHECK-NEXT: ## %bb.17: ## %cond_true61 +; CHECK-NEXT: je LBB0_21 +; CHECK-NEXT: ## %bb.19: ## %cond_true61 ; CHECK-NEXT: movl %eax, %ebp ; CHECK-NEXT: movq (%r14), %rax ; CHECK-NEXT: movq _.str5@GOTPCREL(%rip), %rdi @@ -139,8 +136,8 @@ define ptr @ubyte_divmod(ptr %a, ptr %b) { ; CHECK-NEXT: leaq {{[0-9]+}}(%rsp), %rcx ; CHECK-NEXT: callq *200(%rax) ; CHECK-NEXT: testl %eax, %eax -; CHECK-NEXT: js LBB0_23 -; CHECK-NEXT: ## %bb.18: ## %cond_next73 +; CHECK-NEXT: js LBB0_27 +; CHECK-NEXT: ## %bb.20: ## %cond_next73 ; CHECK-NEXT: movl $1, {{[0-9]+}}(%rsp) ; CHECK-NEXT: movq (%r14), %rax ; CHECK-NEXT: movq {{[0-9]+}}(%rsp), %rsi @@ -149,13 +146,13 @@ define ptr @ubyte_divmod(ptr %a, ptr %b) { ; CHECK-NEXT: movl %ebp, %edx ; CHECK-NEXT: callq *232(%rax) ; CHECK-NEXT: testl %eax, %eax -; CHECK-NEXT: jne LBB0_23 -; CHECK-NEXT: LBB0_19: ## %cond_next89 +; CHECK-NEXT: jne LBB0_27 +; CHECK-NEXT: LBB0_21: ## %cond_next89 ; CHECK-NEXT: movl $2, %edi ; CHECK-NEXT: callq _PyTuple_New ; CHECK-NEXT: testq %rax, %rax -; CHECK-NEXT: je LBB0_23 -; CHECK-NEXT: ## %bb.20: ## %cond_next97 +; CHECK-NEXT: je LBB0_27 +; CHECK-NEXT: ## %bb.22: ## %cond_next97 ; CHECK-NEXT: movq %rax, %r14 ; CHECK-NEXT: movq _PyArray_API@GOTPCREL(%rip), %r12 ; CHECK-NEXT: movq (%r12), %rax @@ -163,8 +160,8 @@ define ptr @ubyte_divmod(ptr %a, ptr %b) { ; CHECK-NEXT: xorl %esi, %esi ; CHECK-NEXT: callq *304(%rdi) ; CHECK-NEXT: testq %rax, %rax -; CHECK-NEXT: je LBB0_21 -; CHECK-NEXT: ## %bb.25: ## %cond_next135 +; CHECK-NEXT: je LBB0_25 +; CHECK-NEXT: ## %bb.23: ## %cond_next135 ; CHECK-NEXT: movb %r15b, 16(%rax) ; CHECK-NEXT: movq %rax, 24(%r14) ; CHECK-NEXT: movq (%r12), %rax @@ -172,22 +169,22 @@ define ptr @ubyte_divmod(ptr %a, ptr %b) { ; CHECK-NEXT: xorl %esi, %esi ; CHECK-NEXT: callq *304(%rdi) ; CHECK-NEXT: testq %rax, %rax -; CHECK-NEXT: je LBB0_21 -; CHECK-NEXT: ## %bb.26: ## %cond_next182 +; CHECK-NEXT: je LBB0_25 +; CHECK-NEXT: ## %bb.24: ## %cond_next182 ; CHECK-NEXT: movb %bl, 16(%rax) ; CHECK-NEXT: movq %rax, 32(%r14) ; CHECK-NEXT: movq %r14, %rax -; CHECK-NEXT: jmp LBB0_24 -; CHECK-NEXT: LBB0_21: ## %cond_true113 +; CHECK-NEXT: jmp LBB0_28 +; CHECK-NEXT: LBB0_25: ## %cond_true113 ; CHECK-NEXT: decq (%r14) -; CHECK-NEXT: jne LBB0_23 -; CHECK-NEXT: ## %bb.22: ## %cond_true126 +; CHECK-NEXT: jne LBB0_27 +; CHECK-NEXT: ## %bb.26: ## %cond_true126 ; CHECK-NEXT: movq 8(%r14), %rax ; CHECK-NEXT: movq %r14, %rdi ; CHECK-NEXT: callq *48(%rax) -; CHECK-NEXT: LBB0_23: ## %UnifiedReturnBlock +; CHECK-NEXT: LBB0_27: ## %UnifiedReturnBlock ; CHECK-NEXT: xorl %eax, %eax -; CHECK-NEXT: LBB0_24: ## %UnifiedReturnBlock +; CHECK-NEXT: LBB0_28: ## %UnifiedReturnBlock ; CHECK-NEXT: addq $32, %rsp ; CHECK-NEXT: popq %rbx ; CHECK-NEXT: popq %r12 diff --git a/llvm/test/CodeGen/X86/isel-fpclass.ll b/llvm/test/CodeGen/X86/isel-fpclass.ll index df04b67..c2b7068 100644 --- a/llvm/test/CodeGen/X86/isel-fpclass.ll +++ b/llvm/test/CodeGen/X86/isel-fpclass.ll @@ -1,10 +1,10 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5 -; RUN: llc < %s -mtriple=i686-linux | FileCheck %s -check-prefixes=X86 +; RUN: llc < %s -mtriple=i686-linux | FileCheck %s -check-prefixes=X86,X86-SDAGISEL ; RUN: llc < %s -mtriple=x86_64-linux | FileCheck %s -check-prefixes=X64,X64-SDAGISEL ; RUN: llc < %s -mtriple=i686-linux -fast-isel -fast-isel-abort=1 | FileCheck %s -check-prefixes=X86-FASTISEL ; RUN: llc < %s -mtriple=x86_64-linux -fast-isel -fast-isel-abort=1 | FileCheck %s -check-prefixes=X64,X64-FASTISEL -; RUN: llc < %s -mtriple=i686-linux -global-isel -global-isel-abort=2 | FileCheck %s -check-prefixes=X86 -; RUN: llc < %s -mtriple=x86_64-linux -global-isel -global-isel-abort=2 | FileCheck %s -check-prefixes=X64,X64-GISEL +; RUN: llc < %s -mtriple=i686-linux -global-isel -global-isel-abort=1 | FileCheck %s -check-prefixes=X86,X86-GISEL +; RUN: llc < %s -mtriple=x86_64-linux -global-isel -global-isel-abort=1 | FileCheck %s -check-prefixes=X64-GISEL define i1 @isnone_f(float %x) nounwind { ; X86-LABEL: isnone_f: @@ -23,6 +23,11 @@ define i1 @isnone_f(float %x) nounwind { ; X86-FASTISEL-NEXT: fstp %st(0) ; X86-FASTISEL-NEXT: xorl %eax, %eax ; X86-FASTISEL-NEXT: retl +; +; X64-GISEL-LABEL: isnone_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: xorl %eax, %eax +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 0) ret i1 %0 @@ -45,22 +50,27 @@ define i1 @isany_f(float %x) nounwind { ; X86-FASTISEL-NEXT: fstp %st(0) ; X86-FASTISEL-NEXT: movb $1, %al ; X86-FASTISEL-NEXT: retl +; +; X64-GISEL-LABEL: isany_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: movb $1, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 1023) ret i1 %0 } define i1 @issignaling_f(float %x) nounwind { -; X86-LABEL: issignaling_f: -; X86: # %bb.0: -; X86-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF -; X86-NEXT: andl {{[0-9]+}}(%esp), %eax -; X86-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 -; X86-NEXT: setl %cl -; X86-NEXT: cmpl $2139095041, %eax # imm = 0x7F800001 -; X86-NEXT: setge %al -; X86-NEXT: andb %cl, %al -; X86-NEXT: retl +; X86-SDAGISEL-LABEL: issignaling_f: +; X86-SDAGISEL: # %bb.0: +; X86-SDAGISEL-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-SDAGISEL-NEXT: andl {{[0-9]+}}(%esp), %eax +; X86-SDAGISEL-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 +; X86-SDAGISEL-NEXT: setl %cl +; X86-SDAGISEL-NEXT: cmpl $2139095041, %eax # imm = 0x7F800001 +; X86-SDAGISEL-NEXT: setge %al +; X86-SDAGISEL-NEXT: andb %cl, %al +; X86-SDAGISEL-NEXT: retl ; ; X64-LABEL: issignaling_f: ; X64: # %bb.0: @@ -87,18 +97,44 @@ define i1 @issignaling_f(float %x) nounwind { ; X86-FASTISEL-NEXT: andb %cl, %al ; X86-FASTISEL-NEXT: popl %ecx ; X86-FASTISEL-NEXT: retl +; +; X86-GISEL-LABEL: issignaling_f: +; X86-GISEL: # %bb.0: +; X86-GISEL-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-GISEL-NEXT: xorl %ecx, %ecx +; X86-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-GISEL-NEXT: seta %dl +; X86-GISEL-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 +; X86-GISEL-NEXT: setb %al +; X86-GISEL-NEXT: andb %dl, %al +; X86-GISEL-NEXT: orb %cl, %al +; X86-GISEL-NEXT: retl +; +; X64-GISEL-LABEL: issignaling_f: +; X64-GISEL: # %bb.0: +; X64-GISEL-NEXT: movd %xmm0, %eax +; X64-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X64-GISEL-NEXT: xorl %ecx, %ecx +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: seta %dl +; X64-GISEL-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 +; X64-GISEL-NEXT: setb %al +; X64-GISEL-NEXT: andb %dl, %al +; X64-GISEL-NEXT: orb %cl, %al +; X64-GISEL-NEXT: retq %a0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 1) ; "snan" ret i1 %a0 } define i1 @isquiet_f(float %x) nounwind { -; X86-LABEL: isquiet_f: -; X86: # %bb.0: # %entry -; X86-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF -; X86-NEXT: andl {{[0-9]+}}(%esp), %eax -; X86-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 -; X86-NEXT: setge %al -; X86-NEXT: retl +; X86-SDAGISEL-LABEL: isquiet_f: +; X86-SDAGISEL: # %bb.0: # %entry +; X86-SDAGISEL-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-SDAGISEL-NEXT: andl {{[0-9]+}}(%esp), %eax +; X86-SDAGISEL-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 +; X86-SDAGISEL-NEXT: setge %al +; X86-SDAGISEL-NEXT: retl ; ; X64-LABEL: isquiet_f: ; X64: # %bb.0: # %entry @@ -119,19 +155,39 @@ define i1 @issignaling_f(float %x) nounwind { ; X86-FASTISEL-NEXT: setge %al ; X86-FASTISEL-NEXT: popl %ecx ; X86-FASTISEL-NEXT: retl +; +; X86-GISEL-LABEL: isquiet_f: +; X86-GISEL: # %bb.0: # %entry +; X86-GISEL-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-GISEL-NEXT: xorl %ecx, %ecx +; X86-GISEL-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 +; X86-GISEL-NEXT: setae %al +; X86-GISEL-NEXT: orb %cl, %al +; X86-GISEL-NEXT: retl +; +; X64-GISEL-LABEL: isquiet_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: movd %xmm0, %eax +; X64-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X64-GISEL-NEXT: xorl %ecx, %ecx +; X64-GISEL-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 +; X64-GISEL-NEXT: setae %al +; X64-GISEL-NEXT: orb %cl, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 2) ; "qnan" ret i1 %0 } define i1 @not_isquiet_f(float %x) nounwind { -; X86-LABEL: not_isquiet_f: -; X86: # %bb.0: # %entry -; X86-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF -; X86-NEXT: andl {{[0-9]+}}(%esp), %eax -; X86-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 -; X86-NEXT: setl %al -; X86-NEXT: retl +; X86-SDAGISEL-LABEL: not_isquiet_f: +; X86-SDAGISEL: # %bb.0: # %entry +; X86-SDAGISEL-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-SDAGISEL-NEXT: andl {{[0-9]+}}(%esp), %eax +; X86-SDAGISEL-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 +; X86-SDAGISEL-NEXT: setl %al +; X86-SDAGISEL-NEXT: retl ; ; X64-LABEL: not_isquiet_f: ; X64: # %bb.0: # %entry @@ -152,19 +208,57 @@ define i1 @not_isquiet_f(float %x) nounwind { ; X86-FASTISEL-NEXT: setl %al ; X86-FASTISEL-NEXT: popl %ecx ; X86-FASTISEL-NEXT: retl +; +; X86-GISEL-LABEL: not_isquiet_f: +; X86-GISEL: # %bb.0: # %entry +; X86-GISEL-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-GISEL-NEXT: xorl %ecx, %ecx +; X86-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-GISEL-NEXT: setb %dl +; X86-GISEL-NEXT: orb %cl, %dl +; X86-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-GISEL-NEXT: sete %cl +; X86-GISEL-NEXT: orb %dl, %cl +; X86-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-GISEL-NEXT: seta %dl +; X86-GISEL-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 +; X86-GISEL-NEXT: setb %al +; X86-GISEL-NEXT: andb %dl, %al +; X86-GISEL-NEXT: orb %cl, %al +; X86-GISEL-NEXT: retl +; +; X64-GISEL-LABEL: not_isquiet_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: movd %xmm0, %eax +; X64-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X64-GISEL-NEXT: xorl %ecx, %ecx +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: setb %dl +; X64-GISEL-NEXT: orb %cl, %dl +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: sete %cl +; X64-GISEL-NEXT: orb %dl, %cl +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: seta %dl +; X64-GISEL-NEXT: cmpl $2143289344, %eax # imm = 0x7FC00000 +; X64-GISEL-NEXT: setb %al +; X64-GISEL-NEXT: andb %dl, %al +; X64-GISEL-NEXT: orb %cl, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 1021) ; ~"qnan" ret i1 %0 } define i1 @isinf_f(float %x) nounwind { -; X86-LABEL: isinf_f: -; X86: # %bb.0: # %entry -; X86-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF -; X86-NEXT: andl {{[0-9]+}}(%esp), %eax -; X86-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 -; X86-NEXT: sete %al -; X86-NEXT: retl +; X86-SDAGISEL-LABEL: isinf_f: +; X86-SDAGISEL: # %bb.0: # %entry +; X86-SDAGISEL-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-SDAGISEL-NEXT: andl {{[0-9]+}}(%esp), %eax +; X86-SDAGISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-SDAGISEL-NEXT: sete %al +; X86-SDAGISEL-NEXT: retl ; ; X64-LABEL: isinf_f: ; X64: # %bb.0: # %entry @@ -185,19 +279,39 @@ define i1 @isinf_f(float %x) nounwind { ; X86-FASTISEL-NEXT: sete %al ; X86-FASTISEL-NEXT: popl %ecx ; X86-FASTISEL-NEXT: retl +; +; X86-GISEL-LABEL: isinf_f: +; X86-GISEL: # %bb.0: # %entry +; X86-GISEL-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-GISEL-NEXT: xorl %ecx, %ecx +; X86-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-GISEL-NEXT: sete %al +; X86-GISEL-NEXT: orb %cl, %al +; X86-GISEL-NEXT: retl +; +; X64-GISEL-LABEL: isinf_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: movd %xmm0, %eax +; X64-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X64-GISEL-NEXT: xorl %ecx, %ecx +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: sete %al +; X64-GISEL-NEXT: orb %cl, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 516) ; 0x204 = "inf" ret i1 %0 } define i1 @not_isinf_f(float %x) nounwind { -; X86-LABEL: not_isinf_f: -; X86: # %bb.0: # %entry -; X86-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF -; X86-NEXT: andl {{[0-9]+}}(%esp), %eax -; X86-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 -; X86-NEXT: setne %al -; X86-NEXT: retl +; X86-SDAGISEL-LABEL: not_isinf_f: +; X86-SDAGISEL: # %bb.0: # %entry +; X86-SDAGISEL-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-SDAGISEL-NEXT: andl {{[0-9]+}}(%esp), %eax +; X86-SDAGISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-SDAGISEL-NEXT: setne %al +; X86-SDAGISEL-NEXT: retl ; ; X64-LABEL: not_isinf_f: ; X64: # %bb.0: # %entry @@ -218,17 +332,43 @@ define i1 @not_isinf_f(float %x) nounwind { ; X86-FASTISEL-NEXT: setne %al ; X86-FASTISEL-NEXT: popl %ecx ; X86-FASTISEL-NEXT: retl +; +; X86-GISEL-LABEL: not_isinf_f: +; X86-GISEL: # %bb.0: # %entry +; X86-GISEL-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-GISEL-NEXT: xorl %ecx, %ecx +; X86-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-GISEL-NEXT: setb %dl +; X86-GISEL-NEXT: orb %cl, %dl +; X86-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-GISEL-NEXT: seta %al +; X86-GISEL-NEXT: orb %dl, %al +; X86-GISEL-NEXT: retl +; +; X64-GISEL-LABEL: not_isinf_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: movd %xmm0, %eax +; X64-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X64-GISEL-NEXT: xorl %ecx, %ecx +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: setb %dl +; X64-GISEL-NEXT: orb %cl, %dl +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: seta %al +; X64-GISEL-NEXT: orb %dl, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 507) ; ~0x204 = "~inf" ret i1 %0 } define i1 @is_plus_inf_f(float %x) nounwind { -; X86-LABEL: is_plus_inf_f: -; X86: # %bb.0: # %entry -; X86-NEXT: cmpl $2139095040, {{[0-9]+}}(%esp) # imm = 0x7F800000 -; X86-NEXT: sete %al -; X86-NEXT: retl +; X86-SDAGISEL-LABEL: is_plus_inf_f: +; X86-SDAGISEL: # %bb.0: # %entry +; X86-SDAGISEL-NEXT: cmpl $2139095040, {{[0-9]+}}(%esp) # imm = 0x7F800000 +; X86-SDAGISEL-NEXT: sete %al +; X86-SDAGISEL-NEXT: retl ; ; X64-LABEL: is_plus_inf_f: ; X64: # %bb.0: # %entry @@ -246,17 +386,34 @@ define i1 @is_plus_inf_f(float %x) nounwind { ; X86-FASTISEL-NEXT: sete %al ; X86-FASTISEL-NEXT: popl %ecx ; X86-FASTISEL-NEXT: retl +; +; X86-GISEL-LABEL: is_plus_inf_f: +; X86-GISEL: # %bb.0: # %entry +; X86-GISEL-NEXT: xorl %ecx, %ecx +; X86-GISEL-NEXT: cmpl $2139095040, {{[0-9]+}}(%esp) # imm = 0x7F800000 +; X86-GISEL-NEXT: sete %al +; X86-GISEL-NEXT: orb %cl, %al +; X86-GISEL-NEXT: retl +; +; X64-GISEL-LABEL: is_plus_inf_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: xorl %ecx, %ecx +; X64-GISEL-NEXT: movd %xmm0, %eax +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: sete %al +; X64-GISEL-NEXT: orb %cl, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 512) ; 0x200 = "+inf" ret i1 %0 } define i1 @is_minus_inf_f(float %x) nounwind { -; X86-LABEL: is_minus_inf_f: -; X86: # %bb.0: # %entry -; X86-NEXT: cmpl $-8388608, {{[0-9]+}}(%esp) # imm = 0xFF800000 -; X86-NEXT: sete %al -; X86-NEXT: retl +; X86-SDAGISEL-LABEL: is_minus_inf_f: +; X86-SDAGISEL: # %bb.0: # %entry +; X86-SDAGISEL-NEXT: cmpl $-8388608, {{[0-9]+}}(%esp) # imm = 0xFF800000 +; X86-SDAGISEL-NEXT: sete %al +; X86-SDAGISEL-NEXT: retl ; ; X64-LABEL: is_minus_inf_f: ; X64: # %bb.0: # %entry @@ -274,17 +431,34 @@ define i1 @is_minus_inf_f(float %x) nounwind { ; X86-FASTISEL-NEXT: sete %al ; X86-FASTISEL-NEXT: popl %ecx ; X86-FASTISEL-NEXT: retl +; +; X86-GISEL-LABEL: is_minus_inf_f: +; X86-GISEL: # %bb.0: # %entry +; X86-GISEL-NEXT: xorl %ecx, %ecx +; X86-GISEL-NEXT: cmpl $-8388608, {{[0-9]+}}(%esp) # imm = 0xFF800000 +; X86-GISEL-NEXT: sete %al +; X86-GISEL-NEXT: orb %cl, %al +; X86-GISEL-NEXT: retl +; +; X64-GISEL-LABEL: is_minus_inf_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: xorl %ecx, %ecx +; X64-GISEL-NEXT: movd %xmm0, %eax +; X64-GISEL-NEXT: cmpl $-8388608, %eax # imm = 0xFF800000 +; X64-GISEL-NEXT: sete %al +; X64-GISEL-NEXT: orb %cl, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 4) ; "-inf" ret i1 %0 } define i1 @not_is_minus_inf_f(float %x) nounwind { -; X86-LABEL: not_is_minus_inf_f: -; X86: # %bb.0: # %entry -; X86-NEXT: cmpl $-8388608, {{[0-9]+}}(%esp) # imm = 0xFF800000 -; X86-NEXT: setne %al -; X86-NEXT: retl +; X86-SDAGISEL-LABEL: not_is_minus_inf_f: +; X86-SDAGISEL: # %bb.0: # %entry +; X86-SDAGISEL-NEXT: cmpl $-8388608, {{[0-9]+}}(%esp) # imm = 0xFF800000 +; X86-SDAGISEL-NEXT: setne %al +; X86-SDAGISEL-NEXT: retl ; ; X64-LABEL: not_is_minus_inf_f: ; X64: # %bb.0: # %entry @@ -302,19 +476,55 @@ define i1 @not_is_minus_inf_f(float %x) nounwind { ; X86-FASTISEL-NEXT: setne %al ; X86-FASTISEL-NEXT: popl %ecx ; X86-FASTISEL-NEXT: retl +; +; X86-GISEL-LABEL: not_is_minus_inf_f: +; X86-GISEL: # %bb.0: # %entry +; X86-GISEL-NEXT: pushl %ebx +; X86-GISEL-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-GISEL-NEXT: movl %eax, %ecx +; X86-GISEL-NEXT: andl $2147483647, %ecx # imm = 0x7FFFFFFF +; X86-GISEL-NEXT: xorl %edx, %edx +; X86-GISEL-NEXT: cmpl $2139095040, %ecx # imm = 0x7F800000 +; X86-GISEL-NEXT: setb %bl +; X86-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-GISEL-NEXT: sete %ah +; X86-GISEL-NEXT: orb %dl, %ah +; X86-GISEL-NEXT: orb %bl, %ah +; X86-GISEL-NEXT: cmpl $2139095040, %ecx # imm = 0x7F800000 +; X86-GISEL-NEXT: seta %al +; X86-GISEL-NEXT: orb %ah, %al +; X86-GISEL-NEXT: popl %ebx +; X86-GISEL-NEXT: retl +; +; X64-GISEL-LABEL: not_is_minus_inf_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: movd %xmm0, %eax +; X64-GISEL-NEXT: movl %eax, %ecx +; X64-GISEL-NEXT: andl $2147483647, %ecx # imm = 0x7FFFFFFF +; X64-GISEL-NEXT: xorl %edx, %edx +; X64-GISEL-NEXT: cmpl $2139095040, %ecx # imm = 0x7F800000 +; X64-GISEL-NEXT: setb %sil +; X64-GISEL-NEXT: orb %dl, %sil +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: sete %dl +; X64-GISEL-NEXT: cmpl $2139095040, %ecx # imm = 0x7F800000 +; X64-GISEL-NEXT: seta %al +; X64-GISEL-NEXT: orb %dl, %al +; X64-GISEL-NEXT: orb %sil, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 1019) ; ~"-inf" ret i1 %0 } define i1 @isfinite_f(float %x) nounwind { -; X86-LABEL: isfinite_f: -; X86: # %bb.0: # %entry -; X86-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF -; X86-NEXT: andl {{[0-9]+}}(%esp), %eax -; X86-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 -; X86-NEXT: setl %al -; X86-NEXT: retl +; X86-SDAGISEL-LABEL: isfinite_f: +; X86-SDAGISEL: # %bb.0: # %entry +; X86-SDAGISEL-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-SDAGISEL-NEXT: andl {{[0-9]+}}(%esp), %eax +; X86-SDAGISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-SDAGISEL-NEXT: setl %al +; X86-SDAGISEL-NEXT: retl ; ; X64-LABEL: isfinite_f: ; X64: # %bb.0: # %entry @@ -335,19 +545,39 @@ define i1 @isfinite_f(float %x) nounwind { ; X86-FASTISEL-NEXT: setl %al ; X86-FASTISEL-NEXT: popl %ecx ; X86-FASTISEL-NEXT: retl +; +; X86-GISEL-LABEL: isfinite_f: +; X86-GISEL: # %bb.0: # %entry +; X86-GISEL-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-GISEL-NEXT: xorl %ecx, %ecx +; X86-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-GISEL-NEXT: setb %al +; X86-GISEL-NEXT: orb %cl, %al +; X86-GISEL-NEXT: retl +; +; X64-GISEL-LABEL: isfinite_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: movd %xmm0, %eax +; X64-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X64-GISEL-NEXT: xorl %ecx, %ecx +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: setb %al +; X64-GISEL-NEXT: orb %cl, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 504) ; 0x1f8 = "finite" ret i1 %0 } define i1 @not_isfinite_f(float %x) nounwind { -; X86-LABEL: not_isfinite_f: -; X86: # %bb.0: # %entry -; X86-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF -; X86-NEXT: andl {{[0-9]+}}(%esp), %eax -; X86-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 -; X86-NEXT: setge %al -; X86-NEXT: retl +; X86-SDAGISEL-LABEL: not_isfinite_f: +; X86-SDAGISEL: # %bb.0: # %entry +; X86-SDAGISEL-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-SDAGISEL-NEXT: andl {{[0-9]+}}(%esp), %eax +; X86-SDAGISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-SDAGISEL-NEXT: setge %al +; X86-SDAGISEL-NEXT: retl ; ; X64-LABEL: not_isfinite_f: ; X64: # %bb.0: # %entry @@ -368,17 +598,43 @@ define i1 @not_isfinite_f(float %x) nounwind { ; X86-FASTISEL-NEXT: setge %al ; X86-FASTISEL-NEXT: popl %ecx ; X86-FASTISEL-NEXT: retl +; +; X86-GISEL-LABEL: not_isfinite_f: +; X86-GISEL: # %bb.0: # %entry +; X86-GISEL-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X86-GISEL-NEXT: xorl %ecx, %ecx +; X86-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-GISEL-NEXT: sete %dl +; X86-GISEL-NEXT: orb %cl, %dl +; X86-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X86-GISEL-NEXT: seta %al +; X86-GISEL-NEXT: orb %dl, %al +; X86-GISEL-NEXT: retl +; +; X64-GISEL-LABEL: not_isfinite_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: movd %xmm0, %eax +; X64-GISEL-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; X64-GISEL-NEXT: xorl %ecx, %ecx +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: sete %dl +; X64-GISEL-NEXT: orb %cl, %dl +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: seta %al +; X64-GISEL-NEXT: orb %dl, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 519) ; ~0x1f8 = "~finite" ret i1 %0 } define i1 @is_plus_finite_f(float %x) nounwind { -; X86-LABEL: is_plus_finite_f: -; X86: # %bb.0: # %entry -; X86-NEXT: cmpl $2139095040, {{[0-9]+}}(%esp) # imm = 0x7F800000 -; X86-NEXT: setb %al -; X86-NEXT: retl +; X86-SDAGISEL-LABEL: is_plus_finite_f: +; X86-SDAGISEL: # %bb.0: # %entry +; X86-SDAGISEL-NEXT: cmpl $2139095040, {{[0-9]+}}(%esp) # imm = 0x7F800000 +; X86-SDAGISEL-NEXT: setb %al +; X86-SDAGISEL-NEXT: retl ; ; X64-LABEL: is_plus_finite_f: ; X64: # %bb.0: # %entry @@ -396,6 +652,23 @@ define i1 @is_plus_finite_f(float %x) nounwind { ; X86-FASTISEL-NEXT: setb %al ; X86-FASTISEL-NEXT: popl %ecx ; X86-FASTISEL-NEXT: retl +; +; X86-GISEL-LABEL: is_plus_finite_f: +; X86-GISEL: # %bb.0: # %entry +; X86-GISEL-NEXT: xorl %ecx, %ecx +; X86-GISEL-NEXT: cmpl $2139095040, {{[0-9]+}}(%esp) # imm = 0x7F800000 +; X86-GISEL-NEXT: setb %al +; X86-GISEL-NEXT: orb %cl, %al +; X86-GISEL-NEXT: retl +; +; X64-GISEL-LABEL: is_plus_finite_f: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: xorl %ecx, %ecx +; X64-GISEL-NEXT: movd %xmm0, %eax +; X64-GISEL-NEXT: cmpl $2139095040, %eax # imm = 0x7F800000 +; X64-GISEL-NEXT: setb %al +; X64-GISEL-NEXT: orb %cl, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f32(float %x, i32 448) ; 0x1c0 = "+finite" ret i1 %0 @@ -418,6 +691,11 @@ define i1 @isnone_d(double %x) nounwind { ; X86-FASTISEL-NEXT: fstp %st(0) ; X86-FASTISEL-NEXT: xorl %eax, %eax ; X86-FASTISEL-NEXT: retl +; +; X64-GISEL-LABEL: isnone_d: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: xorl %eax, %eax +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f64(double %x, i32 0) ret i1 %0 @@ -440,6 +718,11 @@ define i1 @isany_d(double %x) nounwind { ; X86-FASTISEL-NEXT: fstp %st(0) ; X86-FASTISEL-NEXT: movb $1, %al ; X86-FASTISEL-NEXT: retl +; +; X64-GISEL-LABEL: isany_d: +; X64-GISEL: # %bb.0: # %entry +; X64-GISEL-NEXT: movb $1, %al +; X64-GISEL-NEXT: retq entry: %0 = tail call i1 @llvm.is.fpclass.f64(double %x, i32 1023) ret i1 %0 diff --git a/llvm/test/CodeGen/X86/masked_gather_scatter.ll b/llvm/test/CodeGen/X86/masked_gather_scatter.ll index 4cde581..caec02e 100644 --- a/llvm/test/CodeGen/X86/masked_gather_scatter.ll +++ b/llvm/test/CodeGen/X86/masked_gather_scatter.ll @@ -4765,6 +4765,66 @@ define void @scaleidx_scatter_outofrange(<8 x float> %value, ptr %base, <8 x i32 } declare void @llvm.masked.scatter.v8f32.v8p0(<8 x float>, <8 x ptr>, i32 immarg, <8 x i1>) +define <16 x i32> @pr163023_sext(ptr %a0, <16 x i32> %a1) { +; X64-LABEL: pr163023_sext: +; X64: # %bb.0: +; X64-NEXT: kxnorw %k0, %k0, %k1 +; X64-NEXT: vpxor %xmm1, %xmm1, %xmm1 +; X64-NEXT: vpgatherdd (%rdi,%zmm0), %zmm1 {%k1} +; X64-NEXT: vmovdqa64 %zmm1, %zmm0 +; X64-NEXT: retq +; +; X86-LABEL: pr163023_sext: +; X86: # %bb.0: +; X86-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-NEXT: kxnorw %k0, %k0, %k1 +; X86-NEXT: vpxor %xmm1, %xmm1, %xmm1 +; X86-NEXT: vpgatherdd (%eax,%zmm0), %zmm1 {%k1} +; X86-NEXT: vmovdqa64 %zmm1, %zmm0 +; X86-NEXT: retl + %addr.p = ptrtoint ptr %a0 to i64 + %addr.v = insertelement <1 x i64> poison, i64 %addr.p, i64 0 + %addr.splat = shufflevector <1 x i64> %addr.v, <1 x i64> poison, <16 x i32> zeroinitializer + %ofs = sext <16 x i32> %a1 to <16 x i64> + %addr = add nuw <16 x i64> %addr.splat, %ofs + %ptr = inttoptr <16 x i64> %addr to <16 x ptr> + %gather = call <16 x i32> @llvm.masked.gather.v16i32.v16p0(<16 x ptr> %ptr, i32 4, <16 x i1> splat (i1 true), <16 x i32> poison) + ret <16 x i32> %gather +} + +define <16 x i32> @pr163023_zext(ptr %a0, <16 x i32> %a1) { +; X64-LABEL: pr163023_zext: +; X64: # %bb.0: +; X64-NEXT: vpmovzxdq {{.*#+}} zmm1 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero +; X64-NEXT: vextracti64x4 $1, %zmm0, %ymm0 +; X64-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero +; X64-NEXT: kxnorw %k0, %k0, %k1 +; X64-NEXT: vpxor %xmm2, %xmm2, %xmm2 +; X64-NEXT: vpxor %xmm3, %xmm3, %xmm3 +; X64-NEXT: kxnorw %k0, %k0, %k2 +; X64-NEXT: vpgatherqd (%rdi,%zmm0), %ymm3 {%k2} +; X64-NEXT: vpgatherqd (%rdi,%zmm1), %ymm2 {%k1} +; X64-NEXT: vinserti64x4 $1, %ymm3, %zmm2, %zmm0 +; X64-NEXT: retq +; +; X86-LABEL: pr163023_zext: +; X86: # %bb.0: +; X86-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-NEXT: kxnorw %k0, %k0, %k1 +; X86-NEXT: vpxor %xmm1, %xmm1, %xmm1 +; X86-NEXT: vpgatherdd (%eax,%zmm0), %zmm1 {%k1} +; X86-NEXT: vmovdqa64 %zmm1, %zmm0 +; X86-NEXT: retl + %addr.p = ptrtoint ptr %a0 to i64 + %addr.v = insertelement <1 x i64> poison, i64 %addr.p, i64 0 + %addr.splat = shufflevector <1 x i64> %addr.v, <1 x i64> poison, <16 x i32> zeroinitializer + %ofs = zext <16 x i32> %a1 to <16 x i64> + %addr = add nuw <16 x i64> %addr.splat, %ofs + %ptr = inttoptr <16 x i64> %addr to <16 x ptr> + %gather = call <16 x i32> @llvm.masked.gather.v16i32.v16p0(<16 x ptr> %ptr, i32 4, <16 x i1> splat (i1 true), <16 x i32> poison) + ret <16 x i32> %gather +} + ; ; PR45906 ; This used to cause fast-isel to generate bad copy instructions that would diff --git a/llvm/test/CodeGen/X86/pr160612.ll b/llvm/test/CodeGen/X86/pr160612.ll new file mode 100644 index 0000000..6572c42 --- /dev/null +++ b/llvm/test/CodeGen/X86/pr160612.ll @@ -0,0 +1,74 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -O2 | FileCheck %s + +; Test for issue #160612: OR conditions in branches should use multiple branches +; instead of materializing booleans with SETCC when no special optimizations apply. + +declare void @subroutine_foo() +declare void @subroutine_bar() + +; Original issue: (x == 0 || y == 0) was generating SETCC + TEST + BRANCH +; instead of using two conditional branches directly. +define void @func_a(i32 noundef %x, i32 noundef %y) { +; CHECK-LABEL: func_a: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: testl %edi, %edi +; CHECK-NEXT: je subroutine_foo@PLT # TAILCALL +; CHECK-NEXT: # %bb.1: # %entry +; CHECK-NEXT: testl %esi, %esi +; CHECK-NEXT: jne subroutine_bar@PLT # TAILCALL +; CHECK-NEXT: # %bb.2: # %if.then +; CHECK-NEXT: jmp subroutine_foo@PLT # TAILCALL +entry: + %cmp = icmp eq i32 %x, 0 + %cmp1 = icmp eq i32 %y, 0 + %or.cond = or i1 %cmp, %cmp1 + br i1 %or.cond, label %if.then, label %if.else + +if.then: + tail call void @subroutine_foo() + br label %if.end + +if.else: + tail call void @subroutine_bar() + br label %if.end + +if.end: + ret void +} + +; Reference implementation that already generated optimal code. +; This should continue to generate the same optimal code. +define void @func_b(i32 noundef %x, i32 noundef %y) { +; CHECK-LABEL: func_b: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: testl %edi, %edi +; CHECK-NEXT: je subroutine_foo@PLT # TAILCALL +; CHECK-NEXT: # %bb.1: # %if.else +; CHECK-NEXT: testl %esi, %esi +; CHECK-NEXT: je subroutine_foo@PLT # TAILCALL +; CHECK-NEXT: # %bb.2: # %if.else3 +; CHECK-NEXT: jmp subroutine_bar@PLT # TAILCALL +entry: + %cmp = icmp eq i32 %x, 0 + br i1 %cmp, label %if.then, label %if.else + +if.then: + tail call void @subroutine_foo() + br label %if.end4 + +if.else: + %cmp1 = icmp eq i32 %y, 0 + br i1 %cmp1, label %if.then2, label %if.else3 + +if.then2: + tail call void @subroutine_foo() + br label %if.end4 + +if.else3: + tail call void @subroutine_bar() + br label %if.end4 + +if.end4: + ret void +} diff --git a/llvm/test/CodeGen/X86/setcc-wide-types.ll b/llvm/test/CodeGen/X86/setcc-wide-types.ll index 69abf6e..d018c53 100644 --- a/llvm/test/CodeGen/X86/setcc-wide-types.ll +++ b/llvm/test/CodeGen/X86/setcc-wide-types.ll @@ -1493,15 +1493,23 @@ define i1 @allbits_i128_load_arg(ptr %w) { } define i1 @anybits_i256_load_arg(ptr %w) { -; ANY-LABEL: anybits_i256_load_arg: -; ANY: # %bb.0: -; ANY-NEXT: movq (%rdi), %rax -; ANY-NEXT: movq 8(%rdi), %rcx -; ANY-NEXT: orq 24(%rdi), %rcx -; ANY-NEXT: orq 16(%rdi), %rax -; ANY-NEXT: orq %rcx, %rax -; ANY-NEXT: setne %al -; ANY-NEXT: retq +; SSE-LABEL: anybits_i256_load_arg: +; SSE: # %bb.0: +; SSE-NEXT: movq (%rdi), %rax +; SSE-NEXT: movq 8(%rdi), %rcx +; SSE-NEXT: orq 24(%rdi), %rcx +; SSE-NEXT: orq 16(%rdi), %rax +; SSE-NEXT: orq %rcx, %rax +; SSE-NEXT: setne %al +; SSE-NEXT: retq +; +; AVXANY-LABEL: anybits_i256_load_arg: +; AVXANY: # %bb.0: +; AVXANY-NEXT: vmovdqu (%rdi), %ymm0 +; AVXANY-NEXT: vptest %ymm0, %ymm0 +; AVXANY-NEXT: setne %al +; AVXANY-NEXT: vzeroupper +; AVXANY-NEXT: retq %ld = load i256, ptr %w %cmp = icmp ne i256 %ld, 0 ret i1 %cmp @@ -1552,21 +1560,30 @@ define i1 @allbits_i256_load_arg(ptr %w) { } define i1 @anybits_i512_load_arg(ptr %w) { -; ANY-LABEL: anybits_i512_load_arg: -; ANY: # %bb.0: -; ANY-NEXT: movq 16(%rdi), %rax -; ANY-NEXT: movq (%rdi), %rcx -; ANY-NEXT: movq 8(%rdi), %rdx -; ANY-NEXT: movq 24(%rdi), %rsi -; ANY-NEXT: orq 56(%rdi), %rsi -; ANY-NEXT: orq 40(%rdi), %rdx -; ANY-NEXT: orq %rsi, %rdx -; ANY-NEXT: orq 48(%rdi), %rax -; ANY-NEXT: orq 32(%rdi), %rcx -; ANY-NEXT: orq %rax, %rcx -; ANY-NEXT: orq %rdx, %rcx -; ANY-NEXT: setne %al -; ANY-NEXT: retq +; NO512-LABEL: anybits_i512_load_arg: +; NO512: # %bb.0: +; NO512-NEXT: movq 16(%rdi), %rax +; NO512-NEXT: movq (%rdi), %rcx +; NO512-NEXT: movq 8(%rdi), %rdx +; NO512-NEXT: movq 24(%rdi), %rsi +; NO512-NEXT: orq 56(%rdi), %rsi +; NO512-NEXT: orq 40(%rdi), %rdx +; NO512-NEXT: orq %rsi, %rdx +; NO512-NEXT: orq 48(%rdi), %rax +; NO512-NEXT: orq 32(%rdi), %rcx +; NO512-NEXT: orq %rax, %rcx +; NO512-NEXT: orq %rdx, %rcx +; NO512-NEXT: setne %al +; NO512-NEXT: retq +; +; AVX512-LABEL: anybits_i512_load_arg: +; AVX512: # %bb.0: +; AVX512-NEXT: vmovdqu64 (%rdi), %zmm0 +; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k0 +; AVX512-NEXT: kortestw %k0, %k0 +; AVX512-NEXT: setne %al +; AVX512-NEXT: vzeroupper +; AVX512-NEXT: retq %ld = load i512, ptr %w %cmp = icmp ne i512 %ld, 0 ret i1 %cmp diff --git a/llvm/test/CodeGen/X86/x86-shrink-wrap-unwind.ll b/llvm/test/CodeGen/X86/x86-shrink-wrap-unwind.ll index b2064b1..02d4d88 100644 --- a/llvm/test/CodeGen/X86/x86-shrink-wrap-unwind.ll +++ b/llvm/test/CodeGen/X86/x86-shrink-wrap-unwind.ll @@ -181,40 +181,38 @@ define zeroext i1 @segmentedStack(ptr readonly %vk1, ptr readonly %vk2, i64 %key ; CHECK-LABEL: segmentedStack: ; CHECK: ## %bb.0: ; CHECK-NEXT: cmpq %gs:816, %rsp -; CHECK-NEXT: jbe LBB3_6 +; CHECK-NEXT: jbe LBB3_7 ; CHECK-NEXT: LBB3_1: ## %entry ; CHECK-NEXT: pushq %rax ; CHECK-NEXT: .cfi_def_cfa_offset 16 -; CHECK-NEXT: testq %rdi, %rdi -; CHECK-NEXT: sete %al -; CHECK-NEXT: testq %rsi, %rsi -; CHECK-NEXT: sete %cl -; CHECK-NEXT: orb %al, %cl ; CHECK-NEXT: movq %rdi, %rax ; CHECK-NEXT: orq %rsi, %rax ; CHECK-NEXT: sete %al -; CHECK-NEXT: testb %cl, %cl -; CHECK-NEXT: jne LBB3_4 -; CHECK-NEXT: ## %bb.2: ## %if.end4.i +; CHECK-NEXT: testq %rdi, %rdi +; CHECK-NEXT: je LBB3_5 +; CHECK-NEXT: ## %bb.2: ## %entry +; CHECK-NEXT: testq %rsi, %rsi +; CHECK-NEXT: je LBB3_5 +; CHECK-NEXT: ## %bb.3: ## %if.end4.i ; CHECK-NEXT: movq 8(%rdi), %rdx ; CHECK-NEXT: cmpq 8(%rsi), %rdx -; CHECK-NEXT: jne LBB3_5 -; CHECK-NEXT: ## %bb.3: ## %land.rhs.i.i +; CHECK-NEXT: jne LBB3_6 +; CHECK-NEXT: ## %bb.4: ## %land.rhs.i.i ; CHECK-NEXT: movq (%rsi), %rsi ; CHECK-NEXT: movq (%rdi), %rdi ; CHECK-NEXT: callq _memcmp ; CHECK-NEXT: testl %eax, %eax ; CHECK-NEXT: sete %al -; CHECK-NEXT: LBB3_4: ## %__go_ptr_strings_equal.exit +; CHECK-NEXT: LBB3_5: ## %__go_ptr_strings_equal.exit ; CHECK-NEXT: ## kill: def $al killed $al killed $eax ; CHECK-NEXT: popq %rcx ; CHECK-NEXT: retq -; CHECK-NEXT: LBB3_5: +; CHECK-NEXT: LBB3_6: ; CHECK-NEXT: xorl %eax, %eax ; CHECK-NEXT: ## kill: def $al killed $al killed $eax ; CHECK-NEXT: popq %rcx ; CHECK-NEXT: retq -; CHECK-NEXT: LBB3_6: +; CHECK-NEXT: LBB3_7: ; CHECK-NEXT: movl $8, %r10d ; CHECK-NEXT: movl $0, %r11d ; CHECK-NEXT: callq ___morestack @@ -224,43 +222,41 @@ define zeroext i1 @segmentedStack(ptr readonly %vk1, ptr readonly %vk2, i64 %key ; NOCOMPACTUNWIND-LABEL: segmentedStack: ; NOCOMPACTUNWIND: # %bb.0: ; NOCOMPACTUNWIND-NEXT: cmpq %fs:112, %rsp -; NOCOMPACTUNWIND-NEXT: jbe .LBB3_6 +; NOCOMPACTUNWIND-NEXT: jbe .LBB3_7 ; NOCOMPACTUNWIND-NEXT: .LBB3_1: # %entry ; NOCOMPACTUNWIND-NEXT: pushq %rax ; NOCOMPACTUNWIND-NEXT: .cfi_def_cfa_offset 16 -; NOCOMPACTUNWIND-NEXT: testq %rdi, %rdi -; NOCOMPACTUNWIND-NEXT: sete %al -; NOCOMPACTUNWIND-NEXT: testq %rsi, %rsi -; NOCOMPACTUNWIND-NEXT: sete %cl -; NOCOMPACTUNWIND-NEXT: orb %al, %cl ; NOCOMPACTUNWIND-NEXT: movq %rdi, %rax ; NOCOMPACTUNWIND-NEXT: orq %rsi, %rax ; NOCOMPACTUNWIND-NEXT: sete %al -; NOCOMPACTUNWIND-NEXT: testb %cl, %cl -; NOCOMPACTUNWIND-NEXT: jne .LBB3_4 -; NOCOMPACTUNWIND-NEXT: # %bb.2: # %if.end4.i +; NOCOMPACTUNWIND-NEXT: testq %rdi, %rdi +; NOCOMPACTUNWIND-NEXT: je .LBB3_5 +; NOCOMPACTUNWIND-NEXT: # %bb.2: # %entry +; NOCOMPACTUNWIND-NEXT: testq %rsi, %rsi +; NOCOMPACTUNWIND-NEXT: je .LBB3_5 +; NOCOMPACTUNWIND-NEXT: # %bb.3: # %if.end4.i ; NOCOMPACTUNWIND-NEXT: movq 8(%rdi), %rdx ; NOCOMPACTUNWIND-NEXT: cmpq 8(%rsi), %rdx -; NOCOMPACTUNWIND-NEXT: jne .LBB3_5 -; NOCOMPACTUNWIND-NEXT: # %bb.3: # %land.rhs.i.i +; NOCOMPACTUNWIND-NEXT: jne .LBB3_6 +; NOCOMPACTUNWIND-NEXT: # %bb.4: # %land.rhs.i.i ; NOCOMPACTUNWIND-NEXT: movq (%rsi), %rsi ; NOCOMPACTUNWIND-NEXT: movq (%rdi), %rdi ; NOCOMPACTUNWIND-NEXT: callq memcmp@PLT ; NOCOMPACTUNWIND-NEXT: testl %eax, %eax ; NOCOMPACTUNWIND-NEXT: sete %al -; NOCOMPACTUNWIND-NEXT: .LBB3_4: # %__go_ptr_strings_equal.exit +; NOCOMPACTUNWIND-NEXT: .LBB3_5: # %__go_ptr_strings_equal.exit ; NOCOMPACTUNWIND-NEXT: # kill: def $al killed $al killed $eax ; NOCOMPACTUNWIND-NEXT: popq %rcx ; NOCOMPACTUNWIND-NEXT: .cfi_def_cfa_offset 8 ; NOCOMPACTUNWIND-NEXT: retq -; NOCOMPACTUNWIND-NEXT: .LBB3_5: +; NOCOMPACTUNWIND-NEXT: .LBB3_6: ; NOCOMPACTUNWIND-NEXT: .cfi_def_cfa_offset 16 ; NOCOMPACTUNWIND-NEXT: xorl %eax, %eax ; NOCOMPACTUNWIND-NEXT: # kill: def $al killed $al killed $eax ; NOCOMPACTUNWIND-NEXT: popq %rcx ; NOCOMPACTUNWIND-NEXT: .cfi_def_cfa_offset 8 ; NOCOMPACTUNWIND-NEXT: retq -; NOCOMPACTUNWIND-NEXT: .LBB3_6: +; NOCOMPACTUNWIND-NEXT: .LBB3_7: ; NOCOMPACTUNWIND-NEXT: movl $8, %r10d ; NOCOMPACTUNWIND-NEXT: movl $0, %r11d ; NOCOMPACTUNWIND-NEXT: callq __morestack |