[NFC][CodeGen][X86][AArch64] More tests for 'bit field extract' w/ constants

It would be best to introduce ISD::BitFieldExtract,
because clearly more than one backend faces the same problem.
But for now let's solve this in the x86-specific DAG combine.

https://bugs.llvm.org/show_bug.cgi?id=38938

llvm-svn: 342880
This commit is contained in:
Roman Lebedev 2018-09-24 13:24:20 +00:00
parent f432011d33
commit fb697d0f1b
2 changed files with 189 additions and 0 deletions

View File

@ -715,3 +715,76 @@ define i64 @bextr64_d3_load_indexzext(i64* %w, i8 %numskipbits, i8 %numlowbits)
%masked = lshr i64 %highbitscleared, %sh_prom
ret i64 %masked
}
; ---------------------------------------------------------------------------- ;
; Constant
; ---------------------------------------------------------------------------- ;
; https://bugs.llvm.org/show_bug.cgi?id=38938
define void @pr38938(i32* %a0, i64* %a1) {
; CHECK-LABEL: pr38938:
; CHECK: // %bb.0:
; CHECK-NEXT: ldr x8, [x1]
; CHECK-NEXT: ubfx x8, x8, #21, #10
; CHECK-NEXT: lsl x8, x8, #2
; CHECK-NEXT: ldr w9, [x0, x8]
; CHECK-NEXT: add w9, w9, #1 // =1
; CHECK-NEXT: str w9, [x0, x8]
; CHECK-NEXT: ret
%tmp = load i64, i64* %a1, align 8
%tmp1 = lshr i64 %tmp, 21
%tmp2 = and i64 %tmp1, 1023
%tmp3 = getelementptr inbounds i32, i32* %a0, i64 %tmp2
%tmp4 = load i32, i32* %tmp3, align 4
%tmp5 = add nsw i32 %tmp4, 1
store i32 %tmp5, i32* %tmp3, align 4
ret void
}
; The most canonical variant
define i32 @c0_i32(i32 %arg) {
; CHECK-LABEL: c0_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ubfx w0, w0, #19, #10
; CHECK-NEXT: ret
%tmp0 = lshr i32 %arg, 19
%tmp1 = and i32 %tmp0, 1023
ret i32 %tmp1
}
; Should be still fine, but the mask is shifted
define i32 @c1_i32(i32 %arg) {
; CHECK-LABEL: c1_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: lsr w8, w0, #19
; CHECK-NEXT: and w0, w8, #0xffc
; CHECK-NEXT: ret
%tmp0 = lshr i32 %arg, 19
%tmp1 = and i32 %tmp0, 4092
ret i32 %tmp1
}
; Should be still fine, but the result is shifted left afterwards
define i32 @c2_i32(i32 %arg) {
; CHECK-LABEL: c2_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ubfx w8, w0, #19, #10
; CHECK-NEXT: lsl w0, w8, #2
; CHECK-NEXT: ret
%tmp0 = lshr i32 %arg, 19
%tmp1 = and i32 %tmp0, 1023
%tmp2 = shl i32 %tmp1, 2
ret i32 %tmp2
}
; The mask covers newly shifted-in bit
define i32 @c4_i32_bad(i32 %arg) {
; CHECK-LABEL: c4_i32_bad:
; CHECK: // %bb.0:
; CHECK-NEXT: lsr w8, w0, #19
; CHECK-NEXT: and w0, w8, #0x1ffe
; CHECK-NEXT: ret
%tmp0 = lshr i32 %arg, 19
%tmp1 = and i32 %tmp0, 16382
ret i32 %tmp1
}

View File

@ -5613,6 +5613,7 @@ define i64 @bextr64_d5_skipextrauses(i64 %val, i64 %numskipbits, i64 %numlowbits
; Constant
; ---------------------------------------------------------------------------- ;
; https://bugs.llvm.org/show_bug.cgi?id=38938
define void @pr38938(i32* %a0, i64* %a1) {
; X86-LABEL: pr38938:
; X86: # %bb.0:
@ -5640,3 +5641,118 @@ define void @pr38938(i32* %a0, i64* %a1) {
store i32 %tmp5, i32* %tmp3, align 4
ret void
}
; The most canonical variant
define i32 @c0_i32(i32 %arg) {
; X86-NOBMI-LABEL: c0_i32:
; X86-NOBMI: # %bb.0:
; X86-NOBMI-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NOBMI-NEXT: shrl $19, %eax
; X86-NOBMI-NEXT: andl $1023, %eax # imm = 0x3FF
; X86-NOBMI-NEXT: retl
;
; X86-BMI1NOTBM-LABEL: c0_i32:
; X86-BMI1NOTBM: # %bb.0:
; X86-BMI1NOTBM-NEXT: movl $2579, %eax # imm = 0xA13
; X86-BMI1NOTBM-NEXT: bextrl %eax, {{[0-9]+}}(%esp), %eax
; X86-BMI1NOTBM-NEXT: retl
;
; X86-BMI1TBM-LABEL: c0_i32:
; X86-BMI1TBM: # %bb.0:
; X86-BMI1TBM-NEXT: bextrl $2579, {{[0-9]+}}(%esp), %eax # imm = 0xA13
; X86-BMI1TBM-NEXT: retl
;
; X86-BMI1NOTBMBMI2-LABEL: c0_i32:
; X86-BMI1NOTBMBMI2: # %bb.0:
; X86-BMI1NOTBMBMI2-NEXT: movl $2579, %eax # imm = 0xA13
; X86-BMI1NOTBMBMI2-NEXT: bextrl %eax, {{[0-9]+}}(%esp), %eax
; X86-BMI1NOTBMBMI2-NEXT: retl
;
; X64-NOBMI-LABEL: c0_i32:
; X64-NOBMI: # %bb.0:
; X64-NOBMI-NEXT: movl %edi, %eax
; X64-NOBMI-NEXT: shrl $19, %eax
; X64-NOBMI-NEXT: andl $1023, %eax # imm = 0x3FF
; X64-NOBMI-NEXT: retq
;
; X64-BMI1NOTBM-LABEL: c0_i32:
; X64-BMI1NOTBM: # %bb.0:
; X64-BMI1NOTBM-NEXT: movl $2579, %eax # imm = 0xA13
; X64-BMI1NOTBM-NEXT: bextrl %eax, %edi, %eax
; X64-BMI1NOTBM-NEXT: retq
;
; X64-BMI1TBM-LABEL: c0_i32:
; X64-BMI1TBM: # %bb.0:
; X64-BMI1TBM-NEXT: bextrl $2579, %edi, %eax # imm = 0xA13
; X64-BMI1TBM-NEXT: retq
;
; X64-BMI1NOTBMBMI2-LABEL: c0_i32:
; X64-BMI1NOTBMBMI2: # %bb.0:
; X64-BMI1NOTBMBMI2-NEXT: movl $2579, %eax # imm = 0xA13
; X64-BMI1NOTBMBMI2-NEXT: bextrl %eax, %edi, %eax
; X64-BMI1NOTBMBMI2-NEXT: retq
%tmp0 = lshr i32 %arg, 19
%tmp1 = and i32 %tmp0, 1023
ret i32 %tmp1
}
; Should be still fine, but the mask is shifted
define i32 @c1_i32(i32 %arg) {
; X86-LABEL: c1_i32:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shrl $19, %eax
; X86-NEXT: andl $4092, %eax # imm = 0xFFC
; X86-NEXT: retl
;
; X64-LABEL: c1_i32:
; X64: # %bb.0:
; X64-NEXT: movl %edi, %eax
; X64-NEXT: shrl $19, %eax
; X64-NEXT: andl $4092, %eax # imm = 0xFFC
; X64-NEXT: retq
%tmp0 = lshr i32 %arg, 19
%tmp1 = and i32 %tmp0, 4092
ret i32 %tmp1
}
; Should be still fine, but the result is shifted left afterwards
define i32 @c2_i32(i32 %arg) {
; X86-LABEL: c2_i32:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shrl $17, %eax
; X86-NEXT: andl $4092, %eax # imm = 0xFFC
; X86-NEXT: retl
;
; X64-LABEL: c2_i32:
; X64: # %bb.0:
; X64-NEXT: movl %edi, %eax
; X64-NEXT: shrl $17, %eax
; X64-NEXT: andl $4092, %eax # imm = 0xFFC
; X64-NEXT: retq
%tmp0 = lshr i32 %arg, 19
%tmp1 = and i32 %tmp0, 1023
%tmp2 = shl i32 %tmp1, 2
ret i32 %tmp2
}
; The mask covers newly shifted-in bit
define i32 @c4_i32_bad(i32 %arg) {
; X86-LABEL: c4_i32_bad:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shrl $19, %eax
; X86-NEXT: andl $-2, %eax
; X86-NEXT: retl
;
; X64-LABEL: c4_i32_bad:
; X64: # %bb.0:
; X64-NEXT: movl %edi, %eax
; X64-NEXT: shrl $19, %eax
; X64-NEXT: andl $-2, %eax
; X64-NEXT: retq
%tmp0 = lshr i32 %arg, 19
%tmp1 = and i32 %tmp0, 16382
ret i32 %tmp1
}