forked from OSchip/llvm-project
126 lines
3.5 KiB
LLVM
126 lines
3.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
|
|
; RUN: -mcpu=pwr9 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | \
|
|
; RUN: FileCheck %s
|
|
|
|
; This test case tests multiply high for i32 and i64. When the values are
|
|
; sign-extended, mulh[d|w] is emitted. When values are zero-extended,
|
|
; mulh[d|w]u is emitted instead.
|
|
|
|
; The primary goal is transforming the pattern:
|
|
; (shift (mul (ext $a, <wide_type>), (ext $b, <wide_type>)), <narrow_type>)
|
|
; into (mulhs $a, $b) for sign extend, and (mulhu $a, $b) for zero extend,
|
|
; provided that the mulh operation is legal for <narrow_type>.
|
|
; The shift operation can be either the srl or sra operations.
|
|
|
|
; When no attribute is present on i32, the shift operation is srl.
|
|
define i32 @test_mulhw(i32 %a, i32 %b) {
|
|
; CHECK-LABEL: test_mulhw:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: mulhw r3, r3, r4
|
|
; CHECK-NEXT: clrldi r3, r3, 32
|
|
; CHECK-NEXT: blr
|
|
%1 = sext i32 %a to i64
|
|
%2 = sext i32 %b to i64
|
|
%mul = mul i64 %1, %2
|
|
%shr = lshr i64 %mul, 32
|
|
%tr = trunc i64 %shr to i32
|
|
ret i32 %tr
|
|
}
|
|
|
|
define i32 @test_mulhu(i32 %a, i32 %b) {
|
|
; CHECK-LABEL: test_mulhu:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: mulhwu r3, r3, r4
|
|
; CHECK-NEXT: clrldi r3, r3, 32
|
|
; CHECK-NEXT: blr
|
|
%1 = zext i32 %a to i64
|
|
%2 = zext i32 %b to i64
|
|
%mul = mul i64 %1, %2
|
|
%shr = lshr i64 %mul, 32
|
|
%tr = trunc i64 %shr to i32
|
|
ret i32 %tr
|
|
}
|
|
|
|
define i64 @test_mulhd(i64 %a, i64 %b) {
|
|
; CHECK-LABEL: test_mulhd:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: mulhd r3, r3, r4
|
|
; CHECK-NEXT: blr
|
|
%1 = sext i64 %a to i128
|
|
%2 = sext i64 %b to i128
|
|
%mul = mul i128 %1, %2
|
|
%shr = lshr i128 %mul, 64
|
|
%tr = trunc i128 %shr to i64
|
|
ret i64 %tr
|
|
}
|
|
|
|
define i64 @test_mulhdu(i64 %a, i64 %b) {
|
|
; CHECK-LABEL: test_mulhdu:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: mulhdu r3, r3, r4
|
|
; CHECK-NEXT: blr
|
|
%1 = zext i64 %a to i128
|
|
%2 = zext i64 %b to i128
|
|
%mul = mul i128 %1, %2
|
|
%shr = lshr i128 %mul, 64
|
|
%tr = trunc i128 %shr to i64
|
|
ret i64 %tr
|
|
}
|
|
|
|
; When the signext attribute is present on i32, the shift operation is sra.
|
|
; We are actually transforming (sra (mul sext_in_reg, sext_in_reg)) into mulh.
|
|
define signext i32 @test_mulhw_signext(i32 %a, i32 %b) {
|
|
; CHECK-LABEL: test_mulhw_signext:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: mulhw r3, r3, r4
|
|
; CHECK-NEXT: extsw r3, r3
|
|
; CHECK-NEXT: blr
|
|
%1 = sext i32 %a to i64
|
|
%2 = sext i32 %b to i64
|
|
%mul = mul i64 %1, %2
|
|
%shr = lshr i64 %mul, 32
|
|
%tr = trunc i64 %shr to i32
|
|
ret i32 %tr
|
|
}
|
|
|
|
define zeroext i32 @test_mulhu_zeroext(i32 %a, i32 %b) {
|
|
; CHECK-LABEL: test_mulhu_zeroext:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: mulhwu r3, r3, r4
|
|
; CHECK-NEXT: clrldi r3, r3, 32
|
|
; CHECK-NEXT: blr
|
|
%1 = zext i32 %a to i64
|
|
%2 = zext i32 %b to i64
|
|
%mul = mul i64 %1, %2
|
|
%shr = lshr i64 %mul, 32
|
|
%tr = trunc i64 %shr to i32
|
|
ret i32 %tr
|
|
}
|
|
|
|
define signext i64 @test_mulhd_signext(i64 %a, i64 %b) {
|
|
; CHECK-LABEL: test_mulhd_signext:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: mulhd r3, r3, r4
|
|
; CHECK-NEXT: blr
|
|
%1 = sext i64 %a to i128
|
|
%2 = sext i64 %b to i128
|
|
%mul = mul i128 %1, %2
|
|
%shr = lshr i128 %mul, 64
|
|
%tr = trunc i128 %shr to i64
|
|
ret i64 %tr
|
|
}
|
|
|
|
define zeroext i64 @test_mulhdu_zeroext(i64 %a, i64 %b) {
|
|
; CHECK-LABEL: test_mulhdu_zeroext:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: mulhdu r3, r3, r4
|
|
; CHECK-NEXT: blr
|
|
%1 = zext i64 %a to i128
|
|
%2 = zext i64 %b to i128
|
|
%mul = mul i128 %1, %2
|
|
%shr = lshr i128 %mul, 64
|
|
%tr = trunc i128 %shr to i64
|
|
ret i64 %tr
|
|
}
|