forked from OSchip/llvm-project
[X86] Add test cases to show that we fail to fold loads into i8 smulo and i8/i16/i32/i64 umulo lowering without the assistance of the peephole pass. NFC
llvm-svn: 350271
This commit is contained in:
Craig Topper
parent
ad72f68501
commit
ce46bfa848
|
|
@ -1,7 +1,7 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc -mtriple=x86_64-darwin-unknown < %s | FileCheck %s --check-prefix=SDAG
|
||||
; RUN: llc -mtriple=x86_64-darwin-unknown -fast-isel -fast-isel-abort=1 < %s | FileCheck %s --check-prefix=FAST
|
||||
; RUN: llc -mtriple=x86_64-darwin-unknown -mcpu=knl < %s | FileCheck %s --check-prefix=SDAG --check-prefix=KNL
|
||||
; RUN: llc -disable-peephole -mtriple=x86_64-darwin-unknown < %s | FileCheck %s --check-prefix=SDAG
|
||||
; RUN: llc -disable-peephole -mtriple=x86_64-darwin-unknown -fast-isel -fast-isel-abort=1 < %s | FileCheck %s --check-prefix=FAST
|
||||
; RUN: llc -disable-peephole -mtriple=x86_64-darwin-unknown -mcpu=knl < %s | FileCheck %s --check-prefix=SDAG --check-prefix=KNL
|
||||
|
||||
define {i64, i1} @t1() nounwind {
|
||||
; SDAG-LABEL: t1:
|
||||
|
|
@ -722,6 +722,443 @@ define i1 @bug27873(i64 %c1, i1 %c2) {
|
|||
ret i1 %x1
|
||||
}
|
||||
|
||||
define zeroext i1 @smuloi8_load(i8* %ptr1, i8 %v2, i8* %res) {
|
||||
; SDAG-LABEL: smuloi8_load:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: movb (%rdi), %al
|
||||
; SDAG-NEXT: imulb %sil
|
||||
; SDAG-NEXT: seto %cl
|
||||
; SDAG-NEXT: movb %al, (%rdx)
|
||||
; SDAG-NEXT: movl %ecx, %eax
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: smuloi8_load:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: movb (%rdi), %al
|
||||
; FAST-NEXT: imulb %sil
|
||||
; FAST-NEXT: seto %cl
|
||||
; FAST-NEXT: movb %al, (%rdx)
|
||||
; FAST-NEXT: andb $1, %cl
|
||||
; FAST-NEXT: movzbl %cl, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v1 = load i8, i8* %ptr1
|
||||
%t = call {i8, i1} @llvm.smul.with.overflow.i8(i8 %v1, i8 %v2)
|
||||
%val = extractvalue {i8, i1} %t, 0
|
||||
%obit = extractvalue {i8, i1} %t, 1
|
||||
store i8 %val, i8* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @smuloi8_load2(i8 %v1, i8* %ptr2, i8* %res) {
|
||||
; SDAG-LABEL: smuloi8_load2:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: movl %edi, %eax
|
||||
; SDAG-NEXT: movb (%rsi), %cl
|
||||
; SDAG-NEXT: ## kill: def $al killed $al killed $eax
|
||||
; SDAG-NEXT: imulb %cl
|
||||
; SDAG-NEXT: seto %cl
|
||||
; SDAG-NEXT: movb %al, (%rdx)
|
||||
; SDAG-NEXT: movl %ecx, %eax
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: smuloi8_load2:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: movl %edi, %eax
|
||||
; FAST-NEXT: ## kill: def $al killed $al killed $eax
|
||||
; FAST-NEXT: imulb (%rsi)
|
||||
; FAST-NEXT: seto %cl
|
||||
; FAST-NEXT: movb %al, (%rdx)
|
||||
; FAST-NEXT: andb $1, %cl
|
||||
; FAST-NEXT: movzbl %cl, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v2 = load i8, i8* %ptr2
|
||||
%t = call {i8, i1} @llvm.smul.with.overflow.i8(i8 %v1, i8 %v2)
|
||||
%val = extractvalue {i8, i1} %t, 0
|
||||
%obit = extractvalue {i8, i1} %t, 1
|
||||
store i8 %val, i8* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @smuloi16_load(i16* %ptr1, i16 %v2, i16* %res) {
|
||||
; SDAG-LABEL: smuloi16_load:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: imulw (%rdi), %si
|
||||
; SDAG-NEXT: seto %al
|
||||
; SDAG-NEXT: movw %si, (%rdx)
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: smuloi16_load:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: imulw (%rdi), %si
|
||||
; FAST-NEXT: seto %al
|
||||
; FAST-NEXT: movw %si, (%rdx)
|
||||
; FAST-NEXT: andb $1, %al
|
||||
; FAST-NEXT: movzbl %al, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v1 = load i16, i16* %ptr1
|
||||
%t = call {i16, i1} @llvm.smul.with.overflow.i16(i16 %v1, i16 %v2)
|
||||
%val = extractvalue {i16, i1} %t, 0
|
||||
%obit = extractvalue {i16, i1} %t, 1
|
||||
store i16 %val, i16* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @smuloi16_load2(i16 %v1, i16* %ptr2, i16* %res) {
|
||||
; SDAG-LABEL: smuloi16_load2:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: imulw (%rsi), %di
|
||||
; SDAG-NEXT: seto %al
|
||||
; SDAG-NEXT: movw %di, (%rdx)
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: smuloi16_load2:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: imulw (%rsi), %di
|
||||
; FAST-NEXT: seto %al
|
||||
; FAST-NEXT: movw %di, (%rdx)
|
||||
; FAST-NEXT: andb $1, %al
|
||||
; FAST-NEXT: movzbl %al, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v2 = load i16, i16* %ptr2
|
||||
%t = call {i16, i1} @llvm.smul.with.overflow.i16(i16 %v1, i16 %v2)
|
||||
%val = extractvalue {i16, i1} %t, 0
|
||||
%obit = extractvalue {i16, i1} %t, 1
|
||||
store i16 %val, i16* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @smuloi32_load(i32* %ptr1, i32 %v2, i32* %res) {
|
||||
; SDAG-LABEL: smuloi32_load:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: imull (%rdi), %esi
|
||||
; SDAG-NEXT: seto %al
|
||||
; SDAG-NEXT: movl %esi, (%rdx)
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: smuloi32_load:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: imull (%rdi), %esi
|
||||
; FAST-NEXT: seto %al
|
||||
; FAST-NEXT: movl %esi, (%rdx)
|
||||
; FAST-NEXT: andb $1, %al
|
||||
; FAST-NEXT: movzbl %al, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v1 = load i32, i32* %ptr1
|
||||
%t = call {i32, i1} @llvm.smul.with.overflow.i32(i32 %v1, i32 %v2)
|
||||
%val = extractvalue {i32, i1} %t, 0
|
||||
%obit = extractvalue {i32, i1} %t, 1
|
||||
store i32 %val, i32* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @smuloi32_load2(i32 %v1, i32* %ptr2, i32* %res) {
|
||||
; SDAG-LABEL: smuloi32_load2:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: imull (%rsi), %edi
|
||||
; SDAG-NEXT: seto %al
|
||||
; SDAG-NEXT: movl %edi, (%rdx)
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: smuloi32_load2:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: imull (%rsi), %edi
|
||||
; FAST-NEXT: seto %al
|
||||
; FAST-NEXT: movl %edi, (%rdx)
|
||||
; FAST-NEXT: andb $1, %al
|
||||
; FAST-NEXT: movzbl %al, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v2 = load i32, i32* %ptr2
|
||||
%t = call {i32, i1} @llvm.smul.with.overflow.i32(i32 %v1, i32 %v2)
|
||||
%val = extractvalue {i32, i1} %t, 0
|
||||
%obit = extractvalue {i32, i1} %t, 1
|
||||
store i32 %val, i32* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @smuloi64_load(i64* %ptr1, i64 %v2, i64* %res) {
|
||||
; SDAG-LABEL: smuloi64_load:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: imulq (%rdi), %rsi
|
||||
; SDAG-NEXT: seto %al
|
||||
; SDAG-NEXT: movq %rsi, (%rdx)
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: smuloi64_load:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: imulq (%rdi), %rsi
|
||||
; FAST-NEXT: seto %al
|
||||
; FAST-NEXT: movq %rsi, (%rdx)
|
||||
; FAST-NEXT: andb $1, %al
|
||||
; FAST-NEXT: movzbl %al, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v1 = load i64, i64* %ptr1
|
||||
%t = call {i64, i1} @llvm.smul.with.overflow.i64(i64 %v1, i64 %v2)
|
||||
%val = extractvalue {i64, i1} %t, 0
|
||||
%obit = extractvalue {i64, i1} %t, 1
|
||||
store i64 %val, i64* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @smuloi64_load2(i64 %v1, i64* %ptr2, i64* %res) {
|
||||
; SDAG-LABEL: smuloi64_load2:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: imulq (%rsi), %rdi
|
||||
; SDAG-NEXT: seto %al
|
||||
; SDAG-NEXT: movq %rdi, (%rdx)
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: smuloi64_load2:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: imulq (%rsi), %rdi
|
||||
; FAST-NEXT: seto %al
|
||||
; FAST-NEXT: movq %rdi, (%rdx)
|
||||
; FAST-NEXT: andb $1, %al
|
||||
; FAST-NEXT: movzbl %al, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v2 = load i64, i64* %ptr2
|
||||
%t = call {i64, i1} @llvm.smul.with.overflow.i64(i64 %v1, i64 %v2)
|
||||
%val = extractvalue {i64, i1} %t, 0
|
||||
%obit = extractvalue {i64, i1} %t, 1
|
||||
store i64 %val, i64* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @umuloi8_load(i8* %ptr1, i8 %v2, i8* %res) {
|
||||
; SDAG-LABEL: umuloi8_load:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: movb (%rdi), %al
|
||||
; SDAG-NEXT: mulb %sil
|
||||
; SDAG-NEXT: seto %cl
|
||||
; SDAG-NEXT: movb %al, (%rdx)
|
||||
; SDAG-NEXT: movl %ecx, %eax
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: umuloi8_load:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: movb (%rdi), %al
|
||||
; FAST-NEXT: mulb %sil
|
||||
; FAST-NEXT: seto %cl
|
||||
; FAST-NEXT: movb %al, (%rdx)
|
||||
; FAST-NEXT: andb $1, %cl
|
||||
; FAST-NEXT: movzbl %cl, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v1 = load i8, i8* %ptr1
|
||||
%t = call {i8, i1} @llvm.umul.with.overflow.i8(i8 %v1, i8 %v2)
|
||||
%val = extractvalue {i8, i1} %t, 0
|
||||
%obit = extractvalue {i8, i1} %t, 1
|
||||
store i8 %val, i8* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @umuloi8_load2(i8 %v1, i8* %ptr2, i8* %res) {
|
||||
; SDAG-LABEL: umuloi8_load2:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: movl %edi, %eax
|
||||
; SDAG-NEXT: movb (%rsi), %cl
|
||||
; SDAG-NEXT: ## kill: def $al killed $al killed $eax
|
||||
; SDAG-NEXT: mulb %cl
|
||||
; SDAG-NEXT: seto %cl
|
||||
; SDAG-NEXT: movb %al, (%rdx)
|
||||
; SDAG-NEXT: movl %ecx, %eax
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: umuloi8_load2:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: movl %edi, %eax
|
||||
; FAST-NEXT: ## kill: def $al killed $al killed $eax
|
||||
; FAST-NEXT: mulb (%rsi)
|
||||
; FAST-NEXT: seto %cl
|
||||
; FAST-NEXT: movb %al, (%rdx)
|
||||
; FAST-NEXT: andb $1, %cl
|
||||
; FAST-NEXT: movzbl %cl, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v2 = load i8, i8* %ptr2
|
||||
%t = call {i8, i1} @llvm.umul.with.overflow.i8(i8 %v1, i8 %v2)
|
||||
%val = extractvalue {i8, i1} %t, 0
|
||||
%obit = extractvalue {i8, i1} %t, 1
|
||||
store i8 %val, i8* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @umuloi16_load(i16* %ptr1, i16 %v2, i16* %res) {
|
||||
; SDAG-LABEL: umuloi16_load:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: movq %rdx, %rcx
|
||||
; SDAG-NEXT: movzwl (%rdi), %eax
|
||||
; SDAG-NEXT: mulw %si
|
||||
; SDAG-NEXT: seto %dl
|
||||
; SDAG-NEXT: movw %ax, (%rcx)
|
||||
; SDAG-NEXT: movl %edx, %eax
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: umuloi16_load:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: movq %rdx, %rcx
|
||||
; FAST-NEXT: movzwl (%rdi), %eax
|
||||
; FAST-NEXT: mulw %si
|
||||
; FAST-NEXT: seto %dl
|
||||
; FAST-NEXT: movw %ax, (%rcx)
|
||||
; FAST-NEXT: andb $1, %dl
|
||||
; FAST-NEXT: movzbl %dl, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v1 = load i16, i16* %ptr1
|
||||
%t = call {i16, i1} @llvm.umul.with.overflow.i16(i16 %v1, i16 %v2)
|
||||
%val = extractvalue {i16, i1} %t, 0
|
||||
%obit = extractvalue {i16, i1} %t, 1
|
||||
store i16 %val, i16* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @umuloi16_load2(i16 %v1, i16* %ptr2, i16* %res) {
|
||||
; SDAG-LABEL: umuloi16_load2:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: movq %rdx, %rcx
|
||||
; SDAG-NEXT: movl %edi, %eax
|
||||
; SDAG-NEXT: movzwl (%rsi), %edx
|
||||
; SDAG-NEXT: ## kill: def $ax killed $ax killed $eax
|
||||
; SDAG-NEXT: mulw %dx
|
||||
; SDAG-NEXT: seto %dl
|
||||
; SDAG-NEXT: movw %ax, (%rcx)
|
||||
; SDAG-NEXT: movl %edx, %eax
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: umuloi16_load2:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: movq %rdx, %rcx
|
||||
; FAST-NEXT: movl %edi, %eax
|
||||
; FAST-NEXT: ## kill: def $ax killed $ax killed $eax
|
||||
; FAST-NEXT: mulw (%rsi)
|
||||
; FAST-NEXT: seto %dl
|
||||
; FAST-NEXT: movw %ax, (%rcx)
|
||||
; FAST-NEXT: andb $1, %dl
|
||||
; FAST-NEXT: movzbl %dl, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v2 = load i16, i16* %ptr2
|
||||
%t = call {i16, i1} @llvm.umul.with.overflow.i16(i16 %v1, i16 %v2)
|
||||
%val = extractvalue {i16, i1} %t, 0
|
||||
%obit = extractvalue {i16, i1} %t, 1
|
||||
store i16 %val, i16* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @umuloi32_load(i32* %ptr1, i32 %v2, i32* %res) {
|
||||
; SDAG-LABEL: umuloi32_load:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: movq %rdx, %rcx
|
||||
; SDAG-NEXT: movl (%rdi), %eax
|
||||
; SDAG-NEXT: mull %esi
|
||||
; SDAG-NEXT: seto %dl
|
||||
; SDAG-NEXT: movl %eax, (%rcx)
|
||||
; SDAG-NEXT: movl %edx, %eax
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: umuloi32_load:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: movq %rdx, %rcx
|
||||
; FAST-NEXT: movl (%rdi), %eax
|
||||
; FAST-NEXT: mull %esi
|
||||
; FAST-NEXT: seto %dl
|
||||
; FAST-NEXT: movl %eax, (%rcx)
|
||||
; FAST-NEXT: andb $1, %dl
|
||||
; FAST-NEXT: movzbl %dl, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v1 = load i32, i32* %ptr1
|
||||
%t = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %v1, i32 %v2)
|
||||
%val = extractvalue {i32, i1} %t, 0
|
||||
%obit = extractvalue {i32, i1} %t, 1
|
||||
store i32 %val, i32* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @umuloi32_load2(i32 %v1, i32* %ptr2, i32* %res) {
|
||||
; SDAG-LABEL: umuloi32_load2:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: movq %rdx, %rcx
|
||||
; SDAG-NEXT: movl %edi, %eax
|
||||
; SDAG-NEXT: movl (%rsi), %edx
|
||||
; SDAG-NEXT: mull %edx
|
||||
; SDAG-NEXT: seto %dl
|
||||
; SDAG-NEXT: movl %eax, (%rcx)
|
||||
; SDAG-NEXT: movl %edx, %eax
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: umuloi32_load2:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: movq %rdx, %rcx
|
||||
; FAST-NEXT: movl %edi, %eax
|
||||
; FAST-NEXT: mull (%rsi)
|
||||
; FAST-NEXT: seto %dl
|
||||
; FAST-NEXT: movl %eax, (%rcx)
|
||||
; FAST-NEXT: andb $1, %dl
|
||||
; FAST-NEXT: movzbl %dl, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v2 = load i32, i32* %ptr2
|
||||
%t = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %v1, i32 %v2)
|
||||
%val = extractvalue {i32, i1} %t, 0
|
||||
%obit = extractvalue {i32, i1} %t, 1
|
||||
store i32 %val, i32* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @umuloi64_load(i64* %ptr1, i64 %v2, i64* %res) {
|
||||
; SDAG-LABEL: umuloi64_load:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: movq %rdx, %rcx
|
||||
; SDAG-NEXT: movq (%rdi), %rax
|
||||
; SDAG-NEXT: mulq %rsi
|
||||
; SDAG-NEXT: seto %dl
|
||||
; SDAG-NEXT: movq %rax, (%rcx)
|
||||
; SDAG-NEXT: movl %edx, %eax
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: umuloi64_load:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: movq %rdx, %rcx
|
||||
; FAST-NEXT: movq (%rdi), %rax
|
||||
; FAST-NEXT: mulq %rsi
|
||||
; FAST-NEXT: seto %dl
|
||||
; FAST-NEXT: movq %rax, (%rcx)
|
||||
; FAST-NEXT: andb $1, %dl
|
||||
; FAST-NEXT: movzbl %dl, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v1 = load i64, i64* %ptr1
|
||||
%t = call {i64, i1} @llvm.umul.with.overflow.i64(i64 %v1, i64 %v2)
|
||||
%val = extractvalue {i64, i1} %t, 0
|
||||
%obit = extractvalue {i64, i1} %t, 1
|
||||
store i64 %val, i64* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
define zeroext i1 @umuloi64_load2(i64 %v1, i64* %ptr2, i64* %res) {
|
||||
; SDAG-LABEL: umuloi64_load2:
|
||||
; SDAG: ## %bb.0:
|
||||
; SDAG-NEXT: movq %rdx, %rcx
|
||||
; SDAG-NEXT: movq %rdi, %rax
|
||||
; SDAG-NEXT: movq (%rsi), %rdx
|
||||
; SDAG-NEXT: mulq %rdx
|
||||
; SDAG-NEXT: seto %dl
|
||||
; SDAG-NEXT: movq %rax, (%rcx)
|
||||
; SDAG-NEXT: movl %edx, %eax
|
||||
; SDAG-NEXT: retq
|
||||
;
|
||||
; FAST-LABEL: umuloi64_load2:
|
||||
; FAST: ## %bb.0:
|
||||
; FAST-NEXT: movq %rdx, %rcx
|
||||
; FAST-NEXT: movq %rdi, %rax
|
||||
; FAST-NEXT: mulq (%rsi)
|
||||
; FAST-NEXT: seto %dl
|
||||
; FAST-NEXT: movq %rax, (%rcx)
|
||||
; FAST-NEXT: andb $1, %dl
|
||||
; FAST-NEXT: movzbl %dl, %eax
|
||||
; FAST-NEXT: retq
|
||||
%v2 = load i64, i64* %ptr2
|
||||
%t = call {i64, i1} @llvm.umul.with.overflow.i64(i64 %v1, i64 %v2)
|
||||
%val = extractvalue {i64, i1} %t, 0
|
||||
%obit = extractvalue {i64, i1} %t, 1
|
||||
store i64 %val, i64* %res
|
||||
ret i1 %obit
|
||||
}
|
||||
|
||||
declare {i8, i1} @llvm.smul.with.overflow.i8 (i8, i8 ) nounwind readnone
|
||||
declare {i16, i1} @llvm.smul.with.overflow.i16(i16, i16) nounwind readnone
|
||||
declare {i32, i1} @llvm.smul.with.overflow.i32(i32, i32) nounwind readnone
|
||||
|
|
|
|||
Loading…
Reference in New Issue