maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AArch64/ldst-unscaledimm.ll

224 lines
8.1 KiB
LLVM
Raw Normal View History

AArch64/ARM64: enable more AArch64 tests on ARM64. No code changes for this bunch, just some test rejigs. llvm-svn: 206291
2014-04-15 22:00:29 +08:00
; RUN: llc -verify-machineinstrs -o - %s -mtriple=arm64-linux-gnu | FileCheck %s
[ARM64] Add RUN lines for "–target arm64 –mattr=-fp-armv8" on AArch64 no-fp test. This patch is a supplement of implementing predicate of FP, enabling aarch64 backend no-fp tests on arm64 target for verification. During this, one bug is exposed and fixed by this patch. llvm-svn: 207215
2014-04-25 17:44:20 +08:00
; RUN: llc -verify-machineinstrs < %s -mtriple=arm64-none-linux-gnu -mattr=-fp-armv8 | FileCheck --check-prefix=CHECK-NOFP %s
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
@var_8bit = global i8 0
@var_16bit = global i16 0
@var_32bit = global i32 0
@var_64bit = global i64 0
@var_float = global float 0.0
@var_double = global double 0.0
@varptr = global i8* null
define void @ldst_8bit() {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_-]*\):\( *\)$FUNC: *\$/;\1\2-LABEL:\3$FUNC:/g" $TEMP done sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: ldst_8bit:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
; No architectural support for loads to 16-bit or 8-bit since we
; promote i8 during lowering.
%addr_8bit = load i8** @varptr
; match a sign-extending load 8-bit -> 32-bit
%addr_sext32 = getelementptr i8* %addr_8bit, i64 -256
%val8_sext32 = load volatile i8* %addr_sext32
%val32_signed = sext i8 %val8_sext32 to i32
store volatile i32 %val32_signed, i32* @var_32bit
; CHECK: ldursb {{w[0-9]+}}, [{{x[0-9]+}}, #-256]
; match a zero-extending load volatile 8-bit -> 32-bit
%addr_zext32 = getelementptr i8* %addr_8bit, i64 -12
%val8_zext32 = load volatile i8* %addr_zext32
%val32_unsigned = zext i8 %val8_zext32 to i32
store volatile i32 %val32_unsigned, i32* @var_32bit
; CHECK: ldurb {{w[0-9]+}}, [{{x[0-9]+}}, #-12]
; match an any-extending load volatile 8-bit -> 32-bit
%addr_anyext = getelementptr i8* %addr_8bit, i64 -1
%val8_anyext = load volatile i8* %addr_anyext
%newval8 = add i8 %val8_anyext, 1
store volatile i8 %newval8, i8* @var_8bit
; CHECK: ldurb {{w[0-9]+}}, [{{x[0-9]+}}, #-1]
; match a sign-extending load volatile 8-bit -> 64-bit
%addr_sext64 = getelementptr i8* %addr_8bit, i64 -5
%val8_sext64 = load volatile i8* %addr_sext64
%val64_signed = sext i8 %val8_sext64 to i64
store volatile i64 %val64_signed, i64* @var_64bit
; CHECK: ldursb {{x[0-9]+}}, [{{x[0-9]+}}, #-5]
; match a zero-extending load volatile 8-bit -> 64-bit.
; This uses the fact that ldrb w0, [x0] will zero out the high 32-bits
; of x0 so it's identical to load volatileing to 32-bits.
%addr_zext64 = getelementptr i8* %addr_8bit, i64 -9
%val8_zext64 = load volatile i8* %addr_zext64
%val64_unsigned = zext i8 %val8_zext64 to i64
store volatile i64 %val64_unsigned, i64* @var_64bit
; CHECK: ldurb {{w[0-9]+}}, [{{x[0-9]+}}, #-9]
; truncating store volatile 32-bits to 8-bits
%addr_trunc32 = getelementptr i8* %addr_8bit, i64 -256
%val32 = load volatile i32* @var_32bit
%val8_trunc32 = trunc i32 %val32 to i8
store volatile i8 %val8_trunc32, i8* %addr_trunc32
; CHECK: sturb {{w[0-9]+}}, [{{x[0-9]+}}, #-256]
; truncating store volatile 64-bits to 8-bits
%addr_trunc64 = getelementptr i8* %addr_8bit, i64 -1
%val64 = load volatile i64* @var_64bit
%val8_trunc64 = trunc i64 %val64 to i8
store volatile i8 %val8_trunc64, i8* %addr_trunc64
; CHECK: sturb {{w[0-9]+}}, [{{x[0-9]+}}, #-1]
ret void
}
define void @ldst_16bit() {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_-]*\):\( *\)$FUNC: *\$/;\1\2-LABEL:\3$FUNC:/g" $TEMP done sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: ldst_16bit:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
; No architectural support for loads to 16-bit or 16-bit since we
; promote i16 during lowering.
%addr_8bit = load i8** @varptr
; match a sign-extending load 16-bit -> 32-bit
%addr8_sext32 = getelementptr i8* %addr_8bit, i64 -256
%addr_sext32 = bitcast i8* %addr8_sext32 to i16*
%val16_sext32 = load volatile i16* %addr_sext32
%val32_signed = sext i16 %val16_sext32 to i32
store volatile i32 %val32_signed, i32* @var_32bit
; CHECK: ldursh {{w[0-9]+}}, [{{x[0-9]+}}, #-256]
; match a zero-extending load volatile 16-bit -> 32-bit. With offset that would be unaligned.
%addr8_zext32 = getelementptr i8* %addr_8bit, i64 15
%addr_zext32 = bitcast i8* %addr8_zext32 to i16*
%val16_zext32 = load volatile i16* %addr_zext32
%val32_unsigned = zext i16 %val16_zext32 to i32
store volatile i32 %val32_unsigned, i32* @var_32bit
; CHECK: ldurh {{w[0-9]+}}, [{{x[0-9]+}}, #15]
; match an any-extending load volatile 16-bit -> 32-bit
%addr8_anyext = getelementptr i8* %addr_8bit, i64 -1
%addr_anyext = bitcast i8* %addr8_anyext to i16*
%val16_anyext = load volatile i16* %addr_anyext
%newval16 = add i16 %val16_anyext, 1
store volatile i16 %newval16, i16* @var_16bit
; CHECK: ldurh {{w[0-9]+}}, [{{x[0-9]+}}, #-1]
; match a sign-extending load volatile 16-bit -> 64-bit
%addr8_sext64 = getelementptr i8* %addr_8bit, i64 -5
%addr_sext64 = bitcast i8* %addr8_sext64 to i16*
%val16_sext64 = load volatile i16* %addr_sext64
%val64_signed = sext i16 %val16_sext64 to i64
store volatile i64 %val64_signed, i64* @var_64bit
; CHECK: ldursh {{x[0-9]+}}, [{{x[0-9]+}}, #-5]
; match a zero-extending load volatile 16-bit -> 64-bit.
; This uses the fact that ldrb w0, [x0] will zero out the high 32-bits
; of x0 so it's identical to load volatileing to 32-bits.
%addr8_zext64 = getelementptr i8* %addr_8bit, i64 9
%addr_zext64 = bitcast i8* %addr8_zext64 to i16*
%val16_zext64 = load volatile i16* %addr_zext64
%val64_unsigned = zext i16 %val16_zext64 to i64
store volatile i64 %val64_unsigned, i64* @var_64bit
; CHECK: ldurh {{w[0-9]+}}, [{{x[0-9]+}}, #9]
; truncating store volatile 32-bits to 16-bits
%addr8_trunc32 = getelementptr i8* %addr_8bit, i64 -256
%addr_trunc32 = bitcast i8* %addr8_trunc32 to i16*
%val32 = load volatile i32* @var_32bit
%val16_trunc32 = trunc i32 %val32 to i16
store volatile i16 %val16_trunc32, i16* %addr_trunc32
; CHECK: sturh {{w[0-9]+}}, [{{x[0-9]+}}, #-256]
; truncating store volatile 64-bits to 16-bits
%addr8_trunc64 = getelementptr i8* %addr_8bit, i64 -1
%addr_trunc64 = bitcast i8* %addr8_trunc64 to i16*
%val64 = load volatile i64* @var_64bit
%val16_trunc64 = trunc i64 %val64 to i16
store volatile i16 %val16_trunc64, i16* %addr_trunc64
; CHECK: sturh {{w[0-9]+}}, [{{x[0-9]+}}, #-1]
ret void
}
define void @ldst_32bit() {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_-]*\):\( *\)$FUNC: *\$/;\1\2-LABEL:\3$FUNC:/g" $TEMP done sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: ldst_32bit:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
%addr_8bit = load i8** @varptr
; Straight 32-bit load/store
%addr32_8_noext = getelementptr i8* %addr_8bit, i64 1
%addr32_noext = bitcast i8* %addr32_8_noext to i32*
%val32_noext = load volatile i32* %addr32_noext
store volatile i32 %val32_noext, i32* %addr32_noext
; CHECK: ldur {{w[0-9]+}}, [{{x[0-9]+}}, #1]
; CHECK: stur {{w[0-9]+}}, [{{x[0-9]+}}, #1]
; Zero-extension to 64-bits
%addr32_8_zext = getelementptr i8* %addr_8bit, i64 -256
%addr32_zext = bitcast i8* %addr32_8_zext to i32*
%val32_zext = load volatile i32* %addr32_zext
%val64_unsigned = zext i32 %val32_zext to i64
store volatile i64 %val64_unsigned, i64* @var_64bit
; CHECK: ldur {{w[0-9]+}}, [{{x[0-9]+}}, #-256]
AArch64/ARM64: enable more AArch64 tests on ARM64. No code changes for this bunch, just some test rejigs. llvm-svn: 206291
2014-04-15 22:00:29 +08:00
; CHECK: str {{x[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:var_64bit]
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
; Sign-extension to 64-bits
%addr32_8_sext = getelementptr i8* %addr_8bit, i64 -12
%addr32_sext = bitcast i8* %addr32_8_sext to i32*
%val32_sext = load volatile i32* %addr32_sext
%val64_signed = sext i32 %val32_sext to i64
store volatile i64 %val64_signed, i64* @var_64bit
; CHECK: ldursw {{x[0-9]+}}, [{{x[0-9]+}}, #-12]
AArch64/ARM64: enable more AArch64 tests on ARM64. No code changes for this bunch, just some test rejigs. llvm-svn: 206291
2014-04-15 22:00:29 +08:00
; CHECK: str {{x[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:var_64bit]
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
; Truncation from 64-bits
%addr64_8_trunc = getelementptr i8* %addr_8bit, i64 255
%addr64_trunc = bitcast i8* %addr64_8_trunc to i64*
%addr32_8_trunc = getelementptr i8* %addr_8bit, i64 -20
%addr32_trunc = bitcast i8* %addr32_8_trunc to i32*
%val64_trunc = load volatile i64* %addr64_trunc
%val32_trunc = trunc i64 %val64_trunc to i32
store volatile i32 %val32_trunc, i32* %addr32_trunc
; CHECK: ldur {{x[0-9]+}}, [{{x[0-9]+}}, #255]
; CHECK: stur {{w[0-9]+}}, [{{x[0-9]+}}, #-20]
ret void
}
define void @ldst_float() {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_-]*\):\( *\)$FUNC: *\$/;\1\2-LABEL:\3$FUNC:/g" $TEMP done sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: ldst_float:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
%addr_8bit = load i8** @varptr
%addrfp_8 = getelementptr i8* %addr_8bit, i64 -5
%addrfp = bitcast i8* %addrfp_8 to float*
%valfp = load volatile float* %addrfp
; CHECK: ldur {{s[0-9]+}}, [{{x[0-9]+}}, #-5]
[AArch64] Make the use of FP instructions optional, but enabled by default. This adds a new subtarget feature called FPARMv8 (implied by NEON), and predicates the support of the FP instructions and registers on this feature. llvm-svn: 193739
2013-10-31 17:32:11 +08:00
; CHECK-NOFP-NOT: ldur {{s[0-9]+}},
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
store volatile float %valfp, float* %addrfp
; CHECK: stur {{s[0-9]+}}, [{{x[0-9]+}}, #-5]
[AArch64] Make the use of FP instructions optional, but enabled by default. This adds a new subtarget feature called FPARMv8 (implied by NEON), and predicates the support of the FP instructions and registers on this feature. llvm-svn: 193739
2013-10-31 17:32:11 +08:00
; CHECK-NOFP-NOT: stur {{s[0-9]+}},
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
ret void
}
define void @ldst_double() {
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_-]*\):\( *\)$FUNC: *\$/;\1\2-LABEL:\3$FUNC:/g" $TEMP done sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; CHECK-LABEL: ldst_double:
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
%addr_8bit = load i8** @varptr
%addrfp_8 = getelementptr i8* %addr_8bit, i64 4
%addrfp = bitcast i8* %addrfp_8 to double*
%valfp = load volatile double* %addrfp
; CHECK: ldur {{d[0-9]+}}, [{{x[0-9]+}}, #4]
[AArch64] Make the use of FP instructions optional, but enabled by default. This adds a new subtarget feature called FPARMv8 (implied by NEON), and predicates the support of the FP instructions and registers on this feature. llvm-svn: 193739
2013-10-31 17:32:11 +08:00
; CHECK-NOFP-NOT: ldur {{d[0-9]+}},
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
store volatile double %valfp, double* %addrfp
; CHECK: stur {{d[0-9]+}}, [{{x[0-9]+}}, #4]
[AArch64] Make the use of FP instructions optional, but enabled by default. This adds a new subtarget feature called FPARMv8 (implied by NEON), and predicates the support of the FP instructions and registers on this feature. llvm-svn: 193739
2013-10-31 17:32:11 +08:00
; CHECK-NOFP-NOT: stur {{d[0-9]+}},
Add AArch64 as an experimental target. This patch adds support for AArch64 (ARM's 64-bit architecture) to LLVM in the "experimental" category. Currently, it won't be built unless requested explicitly. This initial commit should have support for: + Assembly of all scalar (i.e. non-NEON, non-Crypto) instructions (except the late addition CRC instructions). + CodeGen features required for C++03 and C99. + Compilation for the "small" memory model: code+static data < 4GB. + Absolute and position-independent code. + GNU-style (i.e. "__thread") TLS. + Debugging information. The principal omission, currently, is performance tuning. This patch excludes the NEON support also reviewed due to an outbreak of batshit insanity in our legal department. That will be committed soon bringing the changes to precisely what has been approved. Further reviews would be gratefully received. llvm-svn: 174054
2013-01-31 20:12:40 +08:00
ret void
}