mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 20:23:11 +01:00
afc65d2411
Allocate non-volatile registers in order to be compatible with ABI, regarding gpr_save. Quoted from https://www.ibm.com/docs/en/ssw_aix_72/assembler/assembler_pdf.pdf page55, > The preferred method of using GPRs is to use the volatile registers first. Next, use the nonvolatile registers > in descending order, starting with GPR31. This patch is based on @jsji 's initial draft. Tested on test-suite and SPEC, found no degradation. Reviewed By: jsji, ZarkoCA, xingxue Differential Revision: https://reviews.llvm.org/D100167
437 lines
15 KiB
LLVM
437 lines
15 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=ppc32-unknown-unknown | FileCheck %s --check-prefixes=ALL,PPC32
|
|
; RUN: llc < %s -mtriple=powerpc64-unknown-unknown | FileCheck %s --check-prefixes=ALL,PPC64,PPC64BE
|
|
; RUN: llc < %s -mtriple=powerpc64-ibm-aix-xcoff | FileCheck %s --check-prefixes=ALL,PPC64,PPC64BE,AIX-PPC64
|
|
; RUN: llc < %s -mtriple=powerpc64le-unknown-unknown | FileCheck %s --check-prefixes=ALL,PPC64,PPC64LE
|
|
|
|
; These two forms are equivalent:
|
|
; sub %y, (xor %x, -1)
|
|
; add (add %x, 1), %y
|
|
; Some targets may prefer one to the other.
|
|
|
|
define i8 @scalar_i8(i8 %x, i8 %y) nounwind {
|
|
; ALL-LABEL: scalar_i8:
|
|
; ALL: # %bb.0:
|
|
; ALL-NEXT: add 3, 3, 4
|
|
; ALL-NEXT: addi 3, 3, 1
|
|
; ALL-NEXT: blr
|
|
%t0 = add i8 %x, 1
|
|
%t1 = add i8 %y, %t0
|
|
ret i8 %t1
|
|
}
|
|
|
|
define i16 @scalar_i16(i16 %x, i16 %y) nounwind {
|
|
; ALL-LABEL: scalar_i16:
|
|
; ALL: # %bb.0:
|
|
; ALL-NEXT: add 3, 3, 4
|
|
; ALL-NEXT: addi 3, 3, 1
|
|
; ALL-NEXT: blr
|
|
%t0 = add i16 %x, 1
|
|
%t1 = add i16 %y, %t0
|
|
ret i16 %t1
|
|
}
|
|
|
|
define i32 @scalar_i32(i32 %x, i32 %y) nounwind {
|
|
; ALL-LABEL: scalar_i32:
|
|
; ALL: # %bb.0:
|
|
; ALL-NEXT: add 3, 3, 4
|
|
; ALL-NEXT: addi 3, 3, 1
|
|
; ALL-NEXT: blr
|
|
%t0 = add i32 %x, 1
|
|
%t1 = add i32 %y, %t0
|
|
ret i32 %t1
|
|
}
|
|
|
|
define i64 @scalar_i64(i64 %x, i64 %y) nounwind {
|
|
; PPC32-LABEL: scalar_i64:
|
|
; PPC32: # %bb.0:
|
|
; PPC32-NEXT: addc 4, 4, 6
|
|
; PPC32-NEXT: adde 3, 3, 5
|
|
; PPC32-NEXT: addic 4, 4, 1
|
|
; PPC32-NEXT: addze 3, 3
|
|
; PPC32-NEXT: blr
|
|
;
|
|
; PPC64-LABEL: scalar_i64:
|
|
; PPC64: # %bb.0:
|
|
; PPC64-NEXT: add 3, 3, 4
|
|
; PPC64-NEXT: addi 3, 3, 1
|
|
; PPC64-NEXT: blr
|
|
%t0 = add i64 %x, 1
|
|
%t1 = add i64 %y, %t0
|
|
ret i64 %t1
|
|
}
|
|
|
|
define <16 x i8> @vector_i128_i8(<16 x i8> %x, <16 x i8> %y) nounwind {
|
|
; PPC32-LABEL: vector_i128_i8:
|
|
; PPC32: # %bb.0:
|
|
; PPC32-NEXT: stwu 1, -64(1)
|
|
; PPC32-NEXT: stw 21, 20(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: lbz 21, 123(1)
|
|
; PPC32-NEXT: stw 22, 24(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: stw 23, 28(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: add 7, 21, 7
|
|
; PPC32-NEXT: lbz 23, 115(1)
|
|
; PPC32-NEXT: lbz 22, 119(1)
|
|
; PPC32-NEXT: lbz 21, 135(1)
|
|
; PPC32-NEXT: add 5, 23, 5
|
|
; PPC32-NEXT: lbz 23, 127(1)
|
|
; PPC32-NEXT: add 6, 22, 6
|
|
; PPC32-NEXT: lbz 22, 131(1)
|
|
; PPC32-NEXT: add 10, 21, 10
|
|
; PPC32-NEXT: stw 26, 40(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: add 8, 23, 8
|
|
; PPC32-NEXT: lbz 26, 83(1)
|
|
; PPC32-NEXT: add 9, 22, 9
|
|
; PPC32-NEXT: lbz 21, 147(1)
|
|
; PPC32-NEXT: stw 24, 32(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: stw 25, 36(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: add 26, 21, 26
|
|
; PPC32-NEXT: lbz 25, 79(1)
|
|
; PPC32-NEXT: lbz 24, 75(1)
|
|
; PPC32-NEXT: lbz 23, 139(1)
|
|
; PPC32-NEXT: lbz 22, 143(1)
|
|
; PPC32-NEXT: stw 29, 52(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: add 24, 23, 24
|
|
; PPC32-NEXT: lbz 29, 95(1)
|
|
; PPC32-NEXT: add 25, 22, 25
|
|
; PPC32-NEXT: lbz 21, 159(1)
|
|
; PPC32-NEXT: stw 27, 44(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: stw 28, 48(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: add 29, 21, 29
|
|
; PPC32-NEXT: lbz 28, 91(1)
|
|
; PPC32-NEXT: lbz 27, 87(1)
|
|
; PPC32-NEXT: lbz 23, 151(1)
|
|
; PPC32-NEXT: lbz 22, 155(1)
|
|
; PPC32-NEXT: lbz 4, 111(1)
|
|
; PPC32-NEXT: add 27, 23, 27
|
|
; PPC32-NEXT: lbz 21, 175(1)
|
|
; PPC32-NEXT: add 28, 22, 28
|
|
; PPC32-NEXT: lbz 11, 107(1)
|
|
; PPC32-NEXT: lbz 12, 171(1)
|
|
; PPC32-NEXT: add 4, 21, 4
|
|
; PPC32-NEXT: stw 30, 56(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: addi 4, 4, 1
|
|
; PPC32-NEXT: lbz 0, 103(1)
|
|
; PPC32-NEXT: add 11, 12, 11
|
|
; PPC32-NEXT: lbz 30, 99(1)
|
|
; PPC32-NEXT: lbz 23, 163(1)
|
|
; PPC32-NEXT: lbz 22, 167(1)
|
|
; PPC32-NEXT: add 30, 23, 30
|
|
; PPC32-NEXT: stb 4, 15(3)
|
|
; PPC32-NEXT: add 23, 22, 0
|
|
; PPC32-NEXT: addi 4, 11, 1
|
|
; PPC32-NEXT: stb 4, 14(3)
|
|
; PPC32-NEXT: addi 4, 23, 1
|
|
; PPC32-NEXT: stb 4, 13(3)
|
|
; PPC32-NEXT: addi 4, 30, 1
|
|
; PPC32-NEXT: stb 4, 12(3)
|
|
; PPC32-NEXT: addi 4, 29, 1
|
|
; PPC32-NEXT: stb 4, 11(3)
|
|
; PPC32-NEXT: addi 4, 28, 1
|
|
; PPC32-NEXT: stb 4, 10(3)
|
|
; PPC32-NEXT: addi 4, 27, 1
|
|
; PPC32-NEXT: stb 4, 9(3)
|
|
; PPC32-NEXT: addi 4, 26, 1
|
|
; PPC32-NEXT: stb 4, 8(3)
|
|
; PPC32-NEXT: addi 4, 25, 1
|
|
; PPC32-NEXT: stb 4, 7(3)
|
|
; PPC32-NEXT: addi 4, 24, 1
|
|
; PPC32-NEXT: stb 4, 6(3)
|
|
; PPC32-NEXT: addi 4, 10, 1
|
|
; PPC32-NEXT: stb 4, 5(3)
|
|
; PPC32-NEXT: addi 4, 9, 1
|
|
; PPC32-NEXT: stb 4, 4(3)
|
|
; PPC32-NEXT: addi 4, 8, 1
|
|
; PPC32-NEXT: stb 4, 3(3)
|
|
; PPC32-NEXT: addi 4, 7, 1
|
|
; PPC32-NEXT: stb 4, 2(3)
|
|
; PPC32-NEXT: addi 4, 6, 1
|
|
; PPC32-NEXT: stb 4, 1(3)
|
|
; PPC32-NEXT: addi 4, 5, 1
|
|
; PPC32-NEXT: stb 4, 0(3)
|
|
; PPC32-NEXT: lwz 30, 56(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 29, 52(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 28, 48(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 27, 44(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 26, 40(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 25, 36(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 24, 32(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 23, 28(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 22, 24(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 21, 20(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: addi 1, 1, 64
|
|
; PPC32-NEXT: blr
|
|
;
|
|
; AIX-PPC64-LABEL: vector_i128_i8:
|
|
; AIX-PPC64: # %bb.0:
|
|
; AIX-PPC64-NEXT: std 22, -80(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: lbz 22, 207(1)
|
|
; AIX-PPC64-NEXT: std 23, -72(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 24, -64(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 26, -48(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 25, -56(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 29, -24(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 28, -32(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 27, -40(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 31, -8(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 30, -16(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: lbz 23, 199(1)
|
|
; AIX-PPC64-NEXT: lbz 24, 191(1)
|
|
; AIX-PPC64-NEXT: add 6, 22, 6
|
|
; AIX-PPC64-NEXT: lbz 22, 231(1)
|
|
; AIX-PPC64-NEXT: add 5, 23, 5
|
|
; AIX-PPC64-NEXT: lbz 23, 223(1)
|
|
; AIX-PPC64-NEXT: add 4, 24, 4
|
|
; AIX-PPC64-NEXT: lbz 24, 215(1)
|
|
; AIX-PPC64-NEXT: add 9, 22, 9
|
|
; AIX-PPC64-NEXT: lbz 26, 127(1)
|
|
; AIX-PPC64-NEXT: add 8, 23, 8
|
|
; AIX-PPC64-NEXT: lbz 22, 255(1)
|
|
; AIX-PPC64-NEXT: add 7, 24, 7
|
|
; AIX-PPC64-NEXT: lbz 25, 119(1)
|
|
; AIX-PPC64-NEXT: addi 9, 9, 1
|
|
; AIX-PPC64-NEXT: lbz 23, 247(1)
|
|
; AIX-PPC64-NEXT: add 26, 22, 26
|
|
; AIX-PPC64-NEXT: lbz 24, 239(1)
|
|
; AIX-PPC64-NEXT: addi 8, 8, 1
|
|
; AIX-PPC64-NEXT: lbz 29, 151(1)
|
|
; AIX-PPC64-NEXT: add 25, 23, 25
|
|
; AIX-PPC64-NEXT: lbz 22, 279(1)
|
|
; AIX-PPC64-NEXT: add 10, 24, 10
|
|
; AIX-PPC64-NEXT: lbz 28, 143(1)
|
|
; AIX-PPC64-NEXT: addi 10, 10, 1
|
|
; AIX-PPC64-NEXT: lbz 23, 271(1)
|
|
; AIX-PPC64-NEXT: add 29, 22, 29
|
|
; AIX-PPC64-NEXT: lbz 27, 135(1)
|
|
; AIX-PPC64-NEXT: addi 7, 7, 1
|
|
; AIX-PPC64-NEXT: lbz 24, 263(1)
|
|
; AIX-PPC64-NEXT: add 28, 23, 28
|
|
; AIX-PPC64-NEXT: lbz 11, 183(1)
|
|
; AIX-PPC64-NEXT: addi 6, 6, 1
|
|
; AIX-PPC64-NEXT: lbz 22, 311(1)
|
|
; AIX-PPC64-NEXT: add 27, 24, 27
|
|
; AIX-PPC64-NEXT: lbz 12, 175(1)
|
|
; AIX-PPC64-NEXT: addi 5, 5, 1
|
|
; AIX-PPC64-NEXT: lbz 0, 303(1)
|
|
; AIX-PPC64-NEXT: add 11, 22, 11
|
|
; AIX-PPC64-NEXT: lbz 31, 167(1)
|
|
; AIX-PPC64-NEXT: addi 11, 11, 1
|
|
; AIX-PPC64-NEXT: lbz 23, 295(1)
|
|
; AIX-PPC64-NEXT: add 12, 0, 12
|
|
; AIX-PPC64-NEXT: lbz 30, 159(1)
|
|
; AIX-PPC64-NEXT: addi 4, 4, 1
|
|
; AIX-PPC64-NEXT: lbz 24, 287(1)
|
|
; AIX-PPC64-NEXT: add 31, 23, 31
|
|
; AIX-PPC64-NEXT: stb 11, 15(3)
|
|
; AIX-PPC64-NEXT: addi 11, 12, 1
|
|
; AIX-PPC64-NEXT: add 30, 24, 30
|
|
; AIX-PPC64-NEXT: stb 11, 14(3)
|
|
; AIX-PPC64-NEXT: addi 11, 31, 1
|
|
; AIX-PPC64-NEXT: stb 11, 13(3)
|
|
; AIX-PPC64-NEXT: addi 11, 30, 1
|
|
; AIX-PPC64-NEXT: stb 11, 12(3)
|
|
; AIX-PPC64-NEXT: addi 11, 29, 1
|
|
; AIX-PPC64-NEXT: stb 11, 11(3)
|
|
; AIX-PPC64-NEXT: addi 11, 28, 1
|
|
; AIX-PPC64-NEXT: stb 11, 10(3)
|
|
; AIX-PPC64-NEXT: addi 11, 27, 1
|
|
; AIX-PPC64-NEXT: stb 11, 9(3)
|
|
; AIX-PPC64-NEXT: addi 11, 26, 1
|
|
; AIX-PPC64-NEXT: stb 11, 8(3)
|
|
; AIX-PPC64-NEXT: addi 11, 25, 1
|
|
; AIX-PPC64-NEXT: stb 11, 7(3)
|
|
; AIX-PPC64-NEXT: stb 10, 6(3)
|
|
; AIX-PPC64-NEXT: stb 9, 5(3)
|
|
; AIX-PPC64-NEXT: stb 8, 4(3)
|
|
; AIX-PPC64-NEXT: stb 7, 3(3)
|
|
; AIX-PPC64-NEXT: stb 6, 2(3)
|
|
; AIX-PPC64-NEXT: stb 5, 1(3)
|
|
; AIX-PPC64-NEXT: stb 4, 0(3)
|
|
; AIX-PPC64-NEXT: ld 31, -8(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 30, -16(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 29, -24(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 28, -32(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 27, -40(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 26, -48(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 25, -56(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 24, -64(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 23, -72(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 22, -80(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: blr
|
|
;
|
|
; PPC64LE-LABEL: vector_i128_i8:
|
|
; PPC64LE: # %bb.0:
|
|
; PPC64LE-NEXT: xxlnor 34, 34, 34
|
|
; PPC64LE-NEXT: vsububm 2, 3, 2
|
|
; PPC64LE-NEXT: blr
|
|
%t0 = add <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>
|
|
%t1 = add <16 x i8> %y, %t0
|
|
ret <16 x i8> %t1
|
|
}
|
|
|
|
define <8 x i16> @vector_i128_i16(<8 x i16> %x, <8 x i16> %y) nounwind {
|
|
; PPC32-LABEL: vector_i128_i16:
|
|
; PPC32: # %bb.0:
|
|
; PPC32-NEXT: stwu 1, -32(1)
|
|
; PPC32-NEXT: stw 26, 8(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: stw 27, 12(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: stw 28, 16(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: stw 29, 20(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: stw 30, 24(1) # 4-byte Folded Spill
|
|
; PPC32-NEXT: lhz 11, 70(1)
|
|
; PPC32-NEXT: lhz 12, 66(1)
|
|
; PPC32-NEXT: lhz 0, 62(1)
|
|
; PPC32-NEXT: add 10, 11, 10
|
|
; PPC32-NEXT: lhz 30, 58(1)
|
|
; PPC32-NEXT: add 9, 12, 9
|
|
; PPC32-NEXT: lhz 29, 50(1)
|
|
; PPC32-NEXT: add 8, 0, 8
|
|
; PPC32-NEXT: lhz 28, 42(1)
|
|
; PPC32-NEXT: add 7, 30, 7
|
|
; PPC32-NEXT: lhz 27, 46(1)
|
|
; PPC32-NEXT: add 5, 29, 5
|
|
; PPC32-NEXT: lhz 26, 54(1)
|
|
; PPC32-NEXT: add 3, 28, 3
|
|
; PPC32-NEXT: add 4, 27, 4
|
|
; PPC32-NEXT: addi 3, 3, 1
|
|
; PPC32-NEXT: add 6, 26, 6
|
|
; PPC32-NEXT: addi 4, 4, 1
|
|
; PPC32-NEXT: addi 5, 5, 1
|
|
; PPC32-NEXT: addi 6, 6, 1
|
|
; PPC32-NEXT: addi 7, 7, 1
|
|
; PPC32-NEXT: addi 8, 8, 1
|
|
; PPC32-NEXT: addi 9, 9, 1
|
|
; PPC32-NEXT: addi 10, 10, 1
|
|
; PPC32-NEXT: lwz 30, 24(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 29, 20(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 28, 16(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 27, 12(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: lwz 26, 8(1) # 4-byte Folded Reload
|
|
; PPC32-NEXT: addi 1, 1, 32
|
|
; PPC32-NEXT: blr
|
|
;
|
|
; AIX-PPC64-LABEL: vector_i128_i16:
|
|
; AIX-PPC64: # %bb.0:
|
|
; AIX-PPC64-NEXT: std 26, -48(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 27, -40(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 28, -32(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 29, -24(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 30, -16(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: std 31, -8(1) # 8-byte Folded Spill
|
|
; AIX-PPC64-NEXT: lhz 11, 118(1)
|
|
; AIX-PPC64-NEXT: lhz 12, 182(1)
|
|
; AIX-PPC64-NEXT: lhz 0, 174(1)
|
|
; AIX-PPC64-NEXT: lhz 31, 166(1)
|
|
; AIX-PPC64-NEXT: add 11, 12, 11
|
|
; AIX-PPC64-NEXT: lhz 30, 158(1)
|
|
; AIX-PPC64-NEXT: add 10, 0, 10
|
|
; AIX-PPC64-NEXT: lhz 29, 142(1)
|
|
; AIX-PPC64-NEXT: add 9, 31, 9
|
|
; AIX-PPC64-NEXT: lhz 28, 126(1)
|
|
; AIX-PPC64-NEXT: add 8, 30, 8
|
|
; AIX-PPC64-NEXT: lhz 27, 134(1)
|
|
; AIX-PPC64-NEXT: add 6, 29, 6
|
|
; AIX-PPC64-NEXT: lhz 26, 150(1)
|
|
; AIX-PPC64-NEXT: add 4, 28, 4
|
|
; AIX-PPC64-NEXT: add 5, 27, 5
|
|
; AIX-PPC64-NEXT: addi 11, 11, 1
|
|
; AIX-PPC64-NEXT: add 7, 26, 7
|
|
; AIX-PPC64-NEXT: addi 10, 10, 1
|
|
; AIX-PPC64-NEXT: addi 9, 9, 1
|
|
; AIX-PPC64-NEXT: addi 8, 8, 1
|
|
; AIX-PPC64-NEXT: addi 7, 7, 1
|
|
; AIX-PPC64-NEXT: addi 6, 6, 1
|
|
; AIX-PPC64-NEXT: addi 5, 5, 1
|
|
; AIX-PPC64-NEXT: addi 4, 4, 1
|
|
; AIX-PPC64-NEXT: sth 11, 14(3)
|
|
; AIX-PPC64-NEXT: sth 10, 12(3)
|
|
; AIX-PPC64-NEXT: sth 9, 10(3)
|
|
; AIX-PPC64-NEXT: sth 8, 8(3)
|
|
; AIX-PPC64-NEXT: sth 7, 6(3)
|
|
; AIX-PPC64-NEXT: sth 6, 4(3)
|
|
; AIX-PPC64-NEXT: sth 5, 2(3)
|
|
; AIX-PPC64-NEXT: sth 4, 0(3)
|
|
; AIX-PPC64-NEXT: ld 31, -8(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 30, -16(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 29, -24(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 28, -32(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 27, -40(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: ld 26, -48(1) # 8-byte Folded Reload
|
|
; AIX-PPC64-NEXT: blr
|
|
;
|
|
; PPC64LE-LABEL: vector_i128_i16:
|
|
; PPC64LE: # %bb.0:
|
|
; PPC64LE-NEXT: xxlnor 34, 34, 34
|
|
; PPC64LE-NEXT: vsubuhm 2, 3, 2
|
|
; PPC64LE-NEXT: blr
|
|
%t0 = add <8 x i16> %x, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
|
|
%t1 = add <8 x i16> %y, %t0
|
|
ret <8 x i16> %t1
|
|
}
|
|
|
|
define <4 x i32> @vector_i128_i32(<4 x i32> %x, <4 x i32> %y) nounwind {
|
|
; PPC32-LABEL: vector_i128_i32:
|
|
; PPC32: # %bb.0:
|
|
; PPC32-NEXT: add 3, 7, 3
|
|
; PPC32-NEXT: add 4, 8, 4
|
|
; PPC32-NEXT: add 5, 9, 5
|
|
; PPC32-NEXT: add 6, 10, 6
|
|
; PPC32-NEXT: addi 3, 3, 1
|
|
; PPC32-NEXT: addi 4, 4, 1
|
|
; PPC32-NEXT: addi 5, 5, 1
|
|
; PPC32-NEXT: addi 6, 6, 1
|
|
; PPC32-NEXT: blr
|
|
;
|
|
; PPC64BE-LABEL: vector_i128_i32:
|
|
; PPC64BE: # %bb.0:
|
|
; PPC64BE-NEXT: add 6, 10, 6
|
|
; PPC64BE-NEXT: add 5, 9, 5
|
|
; PPC64BE-NEXT: add 4, 8, 4
|
|
; PPC64BE-NEXT: add 3, 7, 3
|
|
; PPC64BE-NEXT: addi 6, 6, 1
|
|
; PPC64BE-NEXT: addi 5, 5, 1
|
|
; PPC64BE-NEXT: addi 4, 4, 1
|
|
; PPC64BE-NEXT: addi 3, 3, 1
|
|
; PPC64BE-NEXT: blr
|
|
;
|
|
; PPC64LE-LABEL: vector_i128_i32:
|
|
; PPC64LE: # %bb.0:
|
|
; PPC64LE-NEXT: xxlnor 34, 34, 34
|
|
; PPC64LE-NEXT: vsubuwm 2, 3, 2
|
|
; PPC64LE-NEXT: blr
|
|
%t0 = add <4 x i32> %x, <i32 1, i32 1, i32 1, i32 1>
|
|
%t1 = add <4 x i32> %y, %t0
|
|
ret <4 x i32> %t1
|
|
}
|
|
|
|
define <2 x i64> @vector_i128_i64(<2 x i64> %x, <2 x i64> %y) nounwind {
|
|
; PPC32-LABEL: vector_i128_i64:
|
|
; PPC32: # %bb.0:
|
|
; PPC32-NEXT: not 4, 4
|
|
; PPC32-NEXT: not 3, 3
|
|
; PPC32-NEXT: subc 4, 8, 4
|
|
; PPC32-NEXT: not 6, 6
|
|
; PPC32-NEXT: subfe 3, 3, 7
|
|
; PPC32-NEXT: not 5, 5
|
|
; PPC32-NEXT: subc 6, 10, 6
|
|
; PPC32-NEXT: subfe 5, 5, 9
|
|
; PPC32-NEXT: blr
|
|
;
|
|
; PPC64BE-LABEL: vector_i128_i64:
|
|
; PPC64BE: # %bb.0:
|
|
; PPC64BE-NEXT: add 3, 5, 3
|
|
; PPC64BE-NEXT: add 4, 6, 4
|
|
; PPC64BE-NEXT: addi 3, 3, 1
|
|
; PPC64BE-NEXT: addi 4, 4, 1
|
|
; PPC64BE-NEXT: blr
|
|
;
|
|
; PPC64LE-LABEL: vector_i128_i64:
|
|
; PPC64LE: # %bb.0:
|
|
; PPC64LE-NEXT: xxlnor 34, 34, 34
|
|
; PPC64LE-NEXT: vsubudm 2, 3, 2
|
|
; PPC64LE-NEXT: blr
|
|
%t0 = add <2 x i64> %x, <i64 1, i64 1>
|
|
%t1 = add <2 x i64> %y, %t0
|
|
ret <2 x i64> %t1
|
|
}
|