summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/X86/funnel-shift.ll
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/X86/funnel-shift.ll')
-rw-r--r--llvm/test/CodeGen/X86/funnel-shift.ll526
1 files changed, 526 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/X86/funnel-shift.ll b/llvm/test/CodeGen/X86/funnel-shift.ll
new file mode 100644
index 00000000000..87f4c3dcb9e
--- /dev/null
+++ b/llvm/test/CodeGen/X86/funnel-shift.ll
@@ -0,0 +1,526 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i686-- -mattr=sse2 | FileCheck %s --check-prefixes=ANY,X32-SSE2
+; RUN: llc < %s -mtriple=x86_64-- -mattr=avx2 | FileCheck %s --check-prefixes=ANY,X64-AVX2
+
+declare i8 @llvm.fshl.i8(i8, i8, i8)
+declare i16 @llvm.fshl.i16(i16, i16, i16)
+declare i32 @llvm.fshl.i32(i32, i32, i32)
+declare i64 @llvm.fshl.i64(i64, i64, i64)
+declare <4 x i32> @llvm.fshl.v4i32(<4 x i32>, <4 x i32>, <4 x i32>)
+
+declare i8 @llvm.fshr.i8(i8, i8, i8)
+declare i16 @llvm.fshr.i16(i16, i16, i16)
+declare i32 @llvm.fshr.i32(i32, i32, i32)
+declare i64 @llvm.fshr.i64(i64, i64, i64)
+declare <4 x i32> @llvm.fshr.v4i32(<4 x i32>, <4 x i32>, <4 x i32>)
+
+; General case - all operands can be variables - x86 has shld, but that's not matched.
+
+define i32 @fshl_i32(i32 %x, i32 %y, i32 %z) nounwind {
+; X32-SSE2-LABEL: fshl_i32:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: pushl %edi
+; X32-SSE2-NEXT: pushl %esi
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X32-SSE2-NEXT: movl $32, %ecx
+; X32-SSE2-NEXT: subl %edx, %ecx
+; X32-SSE2-NEXT: # kill: def $cl killed $cl killed $ecx
+; X32-SSE2-NEXT: shrl %cl, %edi
+; X32-SSE2-NEXT: andl $31, %edx
+; X32-SSE2-NEXT: movl %esi, %eax
+; X32-SSE2-NEXT: movl %edx, %ecx
+; X32-SSE2-NEXT: shll %cl, %eax
+; X32-SSE2-NEXT: orl %edi, %eax
+; X32-SSE2-NEXT: testl %edx, %edx
+; X32-SSE2-NEXT: cmovel %esi, %eax
+; X32-SSE2-NEXT: popl %esi
+; X32-SSE2-NEXT: popl %edi
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshl_i32:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: movl $32, %ecx
+; X64-AVX2-NEXT: subl %edx, %ecx
+; X64-AVX2-NEXT: # kill: def $cl killed $cl killed $ecx
+; X64-AVX2-NEXT: shrl %cl, %esi
+; X64-AVX2-NEXT: andl $31, %edx
+; X64-AVX2-NEXT: movl %edi, %eax
+; X64-AVX2-NEXT: movl %edx, %ecx
+; X64-AVX2-NEXT: shll %cl, %eax
+; X64-AVX2-NEXT: orl %esi, %eax
+; X64-AVX2-NEXT: testl %edx, %edx
+; X64-AVX2-NEXT: cmovel %edi, %eax
+; X64-AVX2-NEXT: retq
+ %f = call i32 @llvm.fshl.i32(i32 %x, i32 %y, i32 %z)
+ ret i32 %f
+}
+
+; Verify that weird types are minimally supported.
+declare i37 @llvm.fshl.i37(i37, i37, i37)
+define i37 @fshl_i37(i37 %x, i37 %y, i37 %z) nounwind {
+; X32-SSE2-LABEL: fshl_i37:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: pushl %ebp
+; X32-SSE2-NEXT: pushl %ebx
+; X32-SSE2-NEXT: pushl %edi
+; X32-SSE2-NEXT: pushl %esi
+; X32-SSE2-NEXT: subl $8, %esp
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X32-SSE2-NEXT: andl $31, %esi
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ebx
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT: movl %eax, %ebp
+; X32-SSE2-NEXT: andl $31, %ebp
+; X32-SSE2-NEXT: movl $37, %ecx
+; X32-SSE2-NEXT: subl %ebx, %ecx
+; X32-SSE2-NEXT: movl $0, %edx
+; X32-SSE2-NEXT: sbbl %eax, %edx
+; X32-SSE2-NEXT: andl $31, %edx
+; X32-SSE2-NEXT: pushl $0
+; X32-SSE2-NEXT: pushl $37
+; X32-SSE2-NEXT: pushl %edx
+; X32-SSE2-NEXT: pushl %ecx
+; X32-SSE2-NEXT: calll __umoddi3
+; X32-SSE2-NEXT: addl $16, %esp
+; X32-SSE2-NEXT: movl %eax, (%esp) # 4-byte Spill
+; X32-SSE2-NEXT: movl %eax, %ecx
+; X32-SSE2-NEXT: shrdl %cl, %esi, %edi
+; X32-SSE2-NEXT: pushl $0
+; X32-SSE2-NEXT: pushl $37
+; X32-SSE2-NEXT: pushl %ebp
+; X32-SSE2-NEXT: pushl %ebx
+; X32-SSE2-NEXT: calll __umoddi3
+; X32-SSE2-NEXT: addl $16, %esp
+; X32-SSE2-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X32-SSE2-NEXT: movl %edx, %ebp
+; X32-SSE2-NEXT: movl %eax, %ecx
+; X32-SSE2-NEXT: shll %cl, %ebp
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ebx
+; X32-SSE2-NEXT: shldl %cl, %edx, %ebx
+; X32-SSE2-NEXT: testb $32, %al
+; X32-SSE2-NEXT: cmovnel %ebp, %ebx
+; X32-SSE2-NEXT: movl $0, %edx
+; X32-SSE2-NEXT: cmovnel %edx, %ebp
+; X32-SSE2-NEXT: movl (%esp), %ecx # 4-byte Reload
+; X32-SSE2-NEXT: shrl %cl, %esi
+; X32-SSE2-NEXT: testb $32, %cl
+; X32-SSE2-NEXT: cmovnel %esi, %edi
+; X32-SSE2-NEXT: cmovnel %edx, %esi
+; X32-SSE2-NEXT: orl %ebx, %esi
+; X32-SSE2-NEXT: orl %ebp, %edi
+; X32-SSE2-NEXT: orl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-SSE2-NEXT: cmovel {{[0-9]+}}(%esp), %edi
+; X32-SSE2-NEXT: cmovel {{[0-9]+}}(%esp), %esi
+; X32-SSE2-NEXT: movl %edi, %eax
+; X32-SSE2-NEXT: movl %esi, %edx
+; X32-SSE2-NEXT: addl $8, %esp
+; X32-SSE2-NEXT: popl %esi
+; X32-SSE2-NEXT: popl %edi
+; X32-SSE2-NEXT: popl %ebx
+; X32-SSE2-NEXT: popl %ebp
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshl_i37:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: pushq %rbx
+; X64-AVX2-NEXT: movq %rdx, %r9
+; X64-AVX2-NEXT: movabsq $137438953471, %r10 # imm = 0x1FFFFFFFFF
+; X64-AVX2-NEXT: andq %r10, %rsi
+; X64-AVX2-NEXT: movl $37, %r8d
+; X64-AVX2-NEXT: subq %rdx, %r8
+; X64-AVX2-NEXT: andq %r10, %r9
+; X64-AVX2-NEXT: movabsq $-2492803253203993461, %r11 # imm = 0xDD67C8A60DD67C8B
+; X64-AVX2-NEXT: movq %r9, %rax
+; X64-AVX2-NEXT: mulq %r11
+; X64-AVX2-NEXT: shrq $5, %rdx
+; X64-AVX2-NEXT: imulq $37, %rdx, %rax
+; X64-AVX2-NEXT: subq %rax, %r9
+; X64-AVX2-NEXT: movq %rdi, %rbx
+; X64-AVX2-NEXT: movl %r9d, %ecx
+; X64-AVX2-NEXT: shlq %cl, %rbx
+; X64-AVX2-NEXT: movq %r8, %rax
+; X64-AVX2-NEXT: andq %r10, %rax
+; X64-AVX2-NEXT: mulq %r11
+; X64-AVX2-NEXT: shrl $5, %edx
+; X64-AVX2-NEXT: imull $37, %edx, %eax
+; X64-AVX2-NEXT: subl %eax, %r8d
+; X64-AVX2-NEXT: movl %r8d, %ecx
+; X64-AVX2-NEXT: shrq %cl, %rsi
+; X64-AVX2-NEXT: orq %rbx, %rsi
+; X64-AVX2-NEXT: testq %r9, %r9
+; X64-AVX2-NEXT: cmoveq %rdi, %rsi
+; X64-AVX2-NEXT: movq %rsi, %rax
+; X64-AVX2-NEXT: popq %rbx
+; X64-AVX2-NEXT: retq
+ %f = call i37 @llvm.fshl.i37(i37 %x, i37 %y, i37 %z)
+ ret i37 %f
+}
+
+; extract(concat(0b1110000, 0b1111111) << 2) = 0b1000011
+
+declare i7 @llvm.fshl.i7(i7, i7, i7)
+define i7 @fshl_i7_const_fold() {
+; ANY-LABEL: fshl_i7_const_fold:
+; ANY: # %bb.0:
+; ANY-NEXT: movb $67, %al
+; ANY-NEXT: ret{{[l|q]}}
+ %f = call i7 @llvm.fshl.i7(i7 112, i7 127, i7 2)
+ ret i7 %f
+}
+
+; With constant shift amount, this is 'shld' with constant operand.
+
+define i32 @fshl_i32_const_shift(i32 %x, i32 %y) nounwind {
+; X32-SSE2-LABEL: fshl_i32_const_shift:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT: shldl $9, %ecx, %eax
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshl_i32_const_shift:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: shldl $9, %esi, %edi
+; X64-AVX2-NEXT: movl %edi, %eax
+; X64-AVX2-NEXT: retq
+ %f = call i32 @llvm.fshl.i32(i32 %x, i32 %y, i32 9)
+ ret i32 %f
+}
+
+; Check modulo math on shift amount.
+
+define i32 @fshl_i32_const_overshift(i32 %x, i32 %y) nounwind {
+; X32-SSE2-LABEL: fshl_i32_const_overshift:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT: shldl $9, %ecx, %eax
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshl_i32_const_overshift:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: shldl $9, %esi, %edi
+; X64-AVX2-NEXT: movl %edi, %eax
+; X64-AVX2-NEXT: retq
+ %f = call i32 @llvm.fshl.i32(i32 %x, i32 %y, i32 41)
+ ret i32 %f
+}
+
+; 64-bit should also work.
+
+define i64 @fshl_i64_const_overshift(i64 %x, i64 %y) nounwind {
+; X32-SSE2-LABEL: fshl_i64_const_overshift:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X32-SSE2-NEXT: shldl $9, %ecx, %edx
+; X32-SSE2-NEXT: shrdl $23, %ecx, %eax
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshl_i64_const_overshift:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: shldq $41, %rsi, %rdi
+; X64-AVX2-NEXT: movq %rdi, %rax
+; X64-AVX2-NEXT: retq
+ %f = call i64 @llvm.fshl.i64(i64 %x, i64 %y, i64 105)
+ ret i64 %f
+}
+
+; This should work without any node-specific logic.
+
+define i8 @fshl_i8_const_fold() nounwind {
+; ANY-LABEL: fshl_i8_const_fold:
+; ANY: # %bb.0:
+; ANY-NEXT: movb $-128, %al
+; ANY-NEXT: ret{{[l|q]}}
+ %f = call i8 @llvm.fshl.i8(i8 255, i8 0, i8 7)
+ ret i8 %f
+}
+
+; Repeat everything for funnel shift right.
+
+; General case - all operands can be variables - x86 has 'shrd', but this doesn't match.
+
+define i32 @fshr_i32(i32 %x, i32 %y, i32 %z) nounwind {
+; X32-SSE2-LABEL: fshr_i32:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: pushl %ebx
+; X32-SSE2-NEXT: pushl %edi
+; X32-SSE2-NEXT: pushl %esi
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X32-SSE2-NEXT: movl $32, %ebx
+; X32-SSE2-NEXT: subl %edx, %ebx
+; X32-SSE2-NEXT: andl $31, %edx
+; X32-SSE2-NEXT: movl %esi, %edi
+; X32-SSE2-NEXT: movl %edx, %ecx
+; X32-SSE2-NEXT: shrl %cl, %edi
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT: movl %ebx, %ecx
+; X32-SSE2-NEXT: shll %cl, %eax
+; X32-SSE2-NEXT: orl %edi, %eax
+; X32-SSE2-NEXT: testl %edx, %edx
+; X32-SSE2-NEXT: cmovel %esi, %eax
+; X32-SSE2-NEXT: popl %esi
+; X32-SSE2-NEXT: popl %edi
+; X32-SSE2-NEXT: popl %ebx
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshr_i32:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: movl $32, %r8d
+; X64-AVX2-NEXT: subl %edx, %r8d
+; X64-AVX2-NEXT: andl $31, %edx
+; X64-AVX2-NEXT: movl %esi, %eax
+; X64-AVX2-NEXT: movl %edx, %ecx
+; X64-AVX2-NEXT: shrl %cl, %eax
+; X64-AVX2-NEXT: movl %r8d, %ecx
+; X64-AVX2-NEXT: shll %cl, %edi
+; X64-AVX2-NEXT: orl %eax, %edi
+; X64-AVX2-NEXT: testl %edx, %edx
+; X64-AVX2-NEXT: cmovel %esi, %edi
+; X64-AVX2-NEXT: movl %edi, %eax
+; X64-AVX2-NEXT: retq
+ %f = call i32 @llvm.fshr.i32(i32 %x, i32 %y, i32 %z)
+ ret i32 %f
+}
+
+; Verify that weird types are minimally supported.
+declare i37 @llvm.fshr.i37(i37, i37, i37)
+define i37 @fshr_i37(i37 %x, i37 %y, i37 %z) nounwind {
+; X32-SSE2-LABEL: fshr_i37:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: pushl %ebp
+; X32-SSE2-NEXT: pushl %ebx
+; X32-SSE2-NEXT: pushl %edi
+; X32-SSE2-NEXT: pushl %esi
+; X32-SSE2-NEXT: pushl %eax
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X32-SSE2-NEXT: andl $31, %esi
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ebp
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT: andl $31, %eax
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X32-SSE2-NEXT: pushl $0
+; X32-SSE2-NEXT: pushl $37
+; X32-SSE2-NEXT: pushl %eax
+; X32-SSE2-NEXT: pushl %ebp
+; X32-SSE2-NEXT: calll __umoddi3
+; X32-SSE2-NEXT: addl $16, %esp
+; X32-SSE2-NEXT: movl %eax, %ebx
+; X32-SSE2-NEXT: movl %edx, (%esp) # 4-byte Spill
+; X32-SSE2-NEXT: movl $37, %eax
+; X32-SSE2-NEXT: subl %ebp, %eax
+; X32-SSE2-NEXT: movl $0, %edx
+; X32-SSE2-NEXT: sbbl {{[0-9]+}}(%esp), %edx
+; X32-SSE2-NEXT: andl $31, %edx
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ebp
+; X32-SSE2-NEXT: movl %ebx, %ecx
+; X32-SSE2-NEXT: shrdl %cl, %esi, %ebp
+; X32-SSE2-NEXT: pushl $0
+; X32-SSE2-NEXT: pushl $37
+; X32-SSE2-NEXT: pushl %edx
+; X32-SSE2-NEXT: pushl %eax
+; X32-SSE2-NEXT: calll __umoddi3
+; X32-SSE2-NEXT: addl $16, %esp
+; X32-SSE2-NEXT: movl %eax, %ecx
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X32-SSE2-NEXT: movl %edx, %eax
+; X32-SSE2-NEXT: shll %cl, %eax
+; X32-SSE2-NEXT: shldl %cl, %edx, %edi
+; X32-SSE2-NEXT: testb $32, %cl
+; X32-SSE2-NEXT: cmovnel %eax, %edi
+; X32-SSE2-NEXT: movl $0, %edx
+; X32-SSE2-NEXT: cmovnel %edx, %eax
+; X32-SSE2-NEXT: movl %ebx, %ecx
+; X32-SSE2-NEXT: shrl %cl, %esi
+; X32-SSE2-NEXT: testb $32, %bl
+; X32-SSE2-NEXT: cmovnel %esi, %ebp
+; X32-SSE2-NEXT: cmovnel %edx, %esi
+; X32-SSE2-NEXT: orl %edi, %esi
+; X32-SSE2-NEXT: orl %eax, %ebp
+; X32-SSE2-NEXT: orl %ebx, (%esp) # 4-byte Folded Spill
+; X32-SSE2-NEXT: cmovel {{[0-9]+}}(%esp), %ebp
+; X32-SSE2-NEXT: cmovel {{[0-9]+}}(%esp), %esi
+; X32-SSE2-NEXT: movl %ebp, %eax
+; X32-SSE2-NEXT: movl %esi, %edx
+; X32-SSE2-NEXT: addl $4, %esp
+; X32-SSE2-NEXT: popl %esi
+; X32-SSE2-NEXT: popl %edi
+; X32-SSE2-NEXT: popl %ebx
+; X32-SSE2-NEXT: popl %ebp
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshr_i37:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: pushq %rbx
+; X64-AVX2-NEXT: movq %rdx, %r9
+; X64-AVX2-NEXT: movabsq $137438953471, %r11 # imm = 0x1FFFFFFFFF
+; X64-AVX2-NEXT: movq %rsi, %r10
+; X64-AVX2-NEXT: andq %r11, %r10
+; X64-AVX2-NEXT: movl $37, %r8d
+; X64-AVX2-NEXT: subq %rdx, %r8
+; X64-AVX2-NEXT: andq %r11, %r9
+; X64-AVX2-NEXT: movabsq $-2492803253203993461, %rbx # imm = 0xDD67C8A60DD67C8B
+; X64-AVX2-NEXT: movq %r9, %rax
+; X64-AVX2-NEXT: mulq %rbx
+; X64-AVX2-NEXT: shrq $5, %rdx
+; X64-AVX2-NEXT: imulq $37, %rdx, %rax
+; X64-AVX2-NEXT: subq %rax, %r9
+; X64-AVX2-NEXT: movl %r9d, %ecx
+; X64-AVX2-NEXT: shrq %cl, %r10
+; X64-AVX2-NEXT: movq %r8, %rax
+; X64-AVX2-NEXT: andq %r11, %rax
+; X64-AVX2-NEXT: mulq %rbx
+; X64-AVX2-NEXT: shrl $5, %edx
+; X64-AVX2-NEXT: imull $37, %edx, %eax
+; X64-AVX2-NEXT: subl %eax, %r8d
+; X64-AVX2-NEXT: movl %r8d, %ecx
+; X64-AVX2-NEXT: shlq %cl, %rdi
+; X64-AVX2-NEXT: orq %r10, %rdi
+; X64-AVX2-NEXT: testq %r9, %r9
+; X64-AVX2-NEXT: cmoveq %rsi, %rdi
+; X64-AVX2-NEXT: movq %rdi, %rax
+; X64-AVX2-NEXT: popq %rbx
+; X64-AVX2-NEXT: retq
+ %f = call i37 @llvm.fshr.i37(i37 %x, i37 %y, i37 %z)
+ ret i37 %f
+}
+
+; extract(concat(0b1110000, 0b1111111) >> 2) = 0b0011111
+
+declare i7 @llvm.fshr.i7(i7, i7, i7)
+define i7 @fshr_i7_const_fold() nounwind {
+; ANY-LABEL: fshr_i7_const_fold:
+; ANY: # %bb.0:
+; ANY-NEXT: movb $31, %al
+; ANY-NEXT: ret{{[l|q]}}
+ %f = call i7 @llvm.fshr.i7(i7 112, i7 127, i7 2)
+ ret i7 %f
+}
+
+; With constant shift amount, this is 'shrd' or 'shld'.
+
+define i32 @fshr_i32_const_shift(i32 %x, i32 %y) nounwind {
+; X32-SSE2-LABEL: fshr_i32_const_shift:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT: shldl $23, %ecx, %eax
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshr_i32_const_shift:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: shldl $23, %esi, %edi
+; X64-AVX2-NEXT: movl %edi, %eax
+; X64-AVX2-NEXT: retq
+ %f = call i32 @llvm.fshr.i32(i32 %x, i32 %y, i32 9)
+ ret i32 %f
+}
+
+; Check modulo math on shift amount. 41-32=9, but right-shift became left, so 32-9=23.
+
+define i32 @fshr_i32_const_overshift(i32 %x, i32 %y) nounwind {
+; X32-SSE2-LABEL: fshr_i32_const_overshift:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT: shldl $23, %ecx, %eax
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshr_i32_const_overshift:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: shldl $23, %esi, %edi
+; X64-AVX2-NEXT: movl %edi, %eax
+; X64-AVX2-NEXT: retq
+ %f = call i32 @llvm.fshr.i32(i32 %x, i32 %y, i32 41)
+ ret i32 %f
+}
+
+; 64-bit should also work. 105-64 = 41, but right-shift became left, so 64-41=23.
+
+define i64 @fshr_i64_const_overshift(i64 %x, i64 %y) nounwind {
+; X32-SSE2-LABEL: fshr_i64_const_overshift:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X32-SSE2-NEXT: shrdl $9, %ecx, %eax
+; X32-SSE2-NEXT: shldl $23, %ecx, %edx
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshr_i64_const_overshift:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: shldq $23, %rsi, %rdi
+; X64-AVX2-NEXT: movq %rdi, %rax
+; X64-AVX2-NEXT: retq
+ %f = call i64 @llvm.fshr.i64(i64 %x, i64 %y, i64 105)
+ ret i64 %f
+}
+
+; This should work without any node-specific logic.
+
+define i8 @fshr_i8_const_fold() nounwind {
+; ANY-LABEL: fshr_i8_const_fold:
+; ANY: # %bb.0:
+; ANY-NEXT: movb $-2, %al
+; ANY-NEXT: ret{{[l|q]}}
+ %f = call i8 @llvm.fshr.i8(i8 255, i8 0, i8 7)
+ ret i8 %f
+}
+
+define i32 @fshl_i32_shift_by_bitwidth(i32 %x, i32 %y) nounwind {
+; X32-SSE2-LABEL: fshl_i32_shift_by_bitwidth:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshl_i32_shift_by_bitwidth:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: movl %edi, %eax
+; X64-AVX2-NEXT: retq
+ %f = call i32 @llvm.fshl.i32(i32 %x, i32 %y, i32 32)
+ ret i32 %f
+}
+
+define i32 @fshr_i32_shift_by_bitwidth(i32 %x, i32 %y) nounwind {
+; X32-SSE2-LABEL: fshr_i32_shift_by_bitwidth:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshr_i32_shift_by_bitwidth:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: movl %esi, %eax
+; X64-AVX2-NEXT: retq
+ %f = call i32 @llvm.fshr.i32(i32 %x, i32 %y, i32 32)
+ ret i32 %f
+}
+
+define <4 x i32> @fshl_v4i32_shift_by_bitwidth(<4 x i32> %x, <4 x i32> %y) nounwind {
+; ANY-LABEL: fshl_v4i32_shift_by_bitwidth:
+; ANY: # %bb.0:
+; ANY-NEXT: ret{{[l|q]}}
+ %f = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> %x, <4 x i32> %y, <4 x i32> <i32 32, i32 32, i32 32, i32 32>)
+ ret <4 x i32> %f
+}
+
+define <4 x i32> @fshr_v4i32_shift_by_bitwidth(<4 x i32> %x, <4 x i32> %y) nounwind {
+; X32-SSE2-LABEL: fshr_v4i32_shift_by_bitwidth:
+; X32-SSE2: # %bb.0:
+; X32-SSE2-NEXT: movaps %xmm1, %xmm0
+; X32-SSE2-NEXT: retl
+;
+; X64-AVX2-LABEL: fshr_v4i32_shift_by_bitwidth:
+; X64-AVX2: # %bb.0:
+; X64-AVX2-NEXT: vmovaps %xmm1, %xmm0
+; X64-AVX2-NEXT: retq
+ %f = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> %x, <4 x i32> %y, <4 x i32> <i32 32, i32 32, i32 32, i32 32>)
+ ret <4 x i32> %f
+}
+
OpenPOWER on IntegriCloud